laion-ai
/
ongo
Generate a painting using text.
Prediction
laion-ai/ongo:1b3cd151IDe56jbor6ajhhpdoheuhum6egcuStatusSucceededSourceWebHardware–Total durationCreatedInput
- seed
- -1
- steps
- "100"
- width
- 256
- height
- 256
- prompt
- white snow covered mountain under blue sky during daytime painting
- batch_size
- "3"
- guidance_scale
- 5
- aesthetic_rating
- 9
- aesthetic_weight
- 0.5
{ "seed": -1, "steps": "100", "width": 256, "height": 256, "prompt": "white snow covered mountain under blue sky during daytime painting", "batch_size": "3", "guidance_scale": 5, "aesthetic_rating": 9, "aesthetic_weight": 0.5 }
Install Replicate’s Node.js client library:npm install replicate
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run laion-ai/ongo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "laion-ai/ongo:1b3cd15121ec450baa71bbbdacddef9217519f12ca12ccfef36eeaa20ad89b9d", { input: { seed: -1, steps: "100", width: 256, height: 256, prompt: "white snow covered mountain under blue sky during daytime painting", batch_size: "3", guidance_scale: 5, aesthetic_rating: 9, aesthetic_weight: 0.5 } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the client:import replicate
Run laion-ai/ongo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "laion-ai/ongo:1b3cd15121ec450baa71bbbdacddef9217519f12ca12ccfef36eeaa20ad89b9d", input={ "seed": -1, "steps": "100", "width": 256, "height": 256, "prompt": "white snow covered mountain under blue sky during daytime painting", "batch_size": "3", "guidance_scale": 5, "aesthetic_rating": 9, "aesthetic_weight": 0.5 } ) # The laion-ai/ongo model can stream output as it's running. # The predict method returns an iterator, and you can iterate over that output. for item in output: # https://replicate.com/laion-ai/ongo/api#output-schema print(item)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run laion-ai/ongo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "1b3cd15121ec450baa71bbbdacddef9217519f12ca12ccfef36eeaa20ad89b9d", "input": { "seed": -1, "steps": "100", "width": 256, "height": 256, "prompt": "white snow covered mountain under blue sky during daytime painting", "batch_size": "3", "guidance_scale": 5, "aesthetic_rating": 9, "aesthetic_weight": 0.5 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2022-06-05T03:20:22.769553Z", "created_at": "2022-06-05T03:19:45.357269Z", "data_removed": false, "error": null, "id": "e56jbor6ajhhpdoheuhum6egcu", "input": { "seed": -1, "steps": "100", "width": 256, "height": 256, "prompt": "white snow covered mountain under blue sky during daytime painting", "batch_size": "3", "guidance_scale": 5, "aesthetic_rating": 9, "aesthetic_weight": 0.5 }, "logs": "Encoding text with BERT\nEncoding text with CLIP\nUsing aesthetic embedding 9 with weight 0.5\nLoading image\nUsing inpaint model but no image is provided. Initializing with zeros.\nPacking CLIP and BERT embeddings into kwargs\nRunning diffusion...\n\n0it [00:00, ?it/s]\n\n 0%| | 0/100 [00:00<?, ?it/s]\u001b[A\n1it [00:01, 1.45s/it]\n\n 1%| | 1/100 [00:01<02:23, 1.45s/it]\u001b[A\n2it [00:02, 1.17s/it]\n\n 2%|▏ | 2/100 [00:02<01:54, 1.17s/it]\u001b[A\n3it [00:03, 1.08s/it]\n\n 3%|▎ | 3/100 [00:03<01:45, 1.08s/it]\u001b[A\n4it [00:03, 1.33it/s]\n\n 4%|▍ | 4/100 [00:03<01:12, 1.33it/s]\u001b[A\n5it [00:03, 1.76it/s]\n\n 5%|▌ | 5/100 [00:03<00:54, 1.76it/s]\u001b[A\n6it [00:04, 1.63it/s]\n\n 6%|▌ | 6/100 [00:04<00:57, 1.63it/s]\u001b[A\n7it [00:04, 2.04it/s]\n\n 7%|▋ | 7/100 [00:04<00:45, 2.04it/s]\u001b[A\n8it [00:05, 2.42it/s]\n\n 8%|▊ | 8/100 [00:05<00:38, 2.42it/s]\u001b[A\n9it [00:05, 2.77it/s]\n\n 9%|▉ | 9/100 [00:05<00:32, 2.77it/s]\u001b[A\n10it [00:05, 3.06it/s]\n\n 10%|█ | 10/100 [00:05<00:29, 3.06it/s]\u001b[A\n11it [00:06, 2.25it/s]\n\n 11%|█ | 11/100 [00:06<00:39, 2.25it/s]\u001b[A\n12it [00:06, 2.62it/s]\n\n 12%|█▏ | 12/100 [00:06<00:33, 2.62it/s]\u001b[A\n13it [00:06, 2.94it/s]\n\n 13%|█▎ | 13/100 [00:06<00:29, 2.94it/s]\u001b[A\n14it [00:07, 3.20it/s]\n\n 14%|█▍ | 14/100 [00:07<00:26, 3.20it/s]\u001b[A\n15it [00:07, 3.40it/s]\n\n 15%|█▌ | 15/100 [00:07<00:24, 3.40it/s]\u001b[A\n16it [00:07, 2.38it/s]\n\n 16%|█▌ | 16/100 [00:07<00:35, 2.38it/s]\u001b[A\n17it [00:08, 2.73it/s]\n\n 17%|█▋ | 17/100 [00:08<00:30, 2.73it/s]\u001b[A\n18it [00:08, 3.03it/s]\n\n 18%|█▊ | 18/100 [00:08<00:27, 3.03it/s]\u001b[A\n19it [00:08, 3.28it/s]\n\n 19%|█▉ | 19/100 [00:08<00:24, 3.28it/s]\u001b[A\n20it [00:08, 3.47it/s]\n\n 20%|██ | 20/100 [00:08<00:23, 3.47it/s]\u001b[A\n21it [00:09, 2.40it/s]\n\n 21%|██ | 21/100 [00:09<00:32, 2.40it/s]\u001b[A\n22it [00:09, 2.75it/s]\n\n 22%|██▏ | 22/100 [00:09<00:28, 2.75it/s]\u001b[A\n23it [00:10, 3.04it/s]\n\n 23%|██▎ | 23/100 [00:10<00:25, 3.04it/s]\u001b[A\n24it [00:10, 3.28it/s]\n\n 24%|██▍ | 24/100 [00:10<00:23, 3.28it/s]\u001b[A\n25it [00:10, 3.47it/s]\n\n 25%|██▌ | 25/100 [00:10<00:21, 3.47it/s]\u001b[A\n26it [00:11, 2.39it/s]\n\n 26%|██▌ | 26/100 [00:11<00:30, 2.39it/s]\u001b[A\n27it [00:11, 2.74it/s]\n\n 27%|██▋ | 27/100 [00:11<00:26, 2.74it/s]\u001b[A\n28it [00:11, 3.03it/s]\n\n 28%|██▊ | 28/100 [00:11<00:23, 3.03it/s]\u001b[A\n29it [00:12, 3.28it/s]\n\n 29%|██▉ | 29/100 [00:12<00:21, 3.28it/s]\u001b[A\n30it [00:12, 3.46it/s]\n\n 30%|███ | 30/100 [00:12<00:20, 3.46it/s]\u001b[A\n31it [00:13, 2.39it/s]\n\n 31%|███ | 31/100 [00:13<00:28, 2.39it/s]\u001b[A\n32it [00:13, 2.73it/s]\n\n 32%|███▏ | 32/100 [00:13<00:24, 2.73it/s]\u001b[A\n33it [00:13, 3.02it/s]\n\n 33%|███▎ | 33/100 [00:13<00:22, 3.02it/s]\u001b[A\n34it [00:13, 3.27it/s]\n\n 34%|███▍ | 34/100 [00:13<00:20, 3.27it/s]\u001b[A\n35it [00:14, 3.45it/s]\n\n 35%|███▌ | 35/100 [00:14<00:18, 3.45it/s]\u001b[A\n36it [00:14, 2.38it/s]\n\n 36%|███▌ | 36/100 [00:14<00:26, 2.38it/s]\u001b[A\n37it [00:15, 2.73it/s]\n\n 37%|███▋ | 37/100 [00:15<00:23, 2.73it/s]\u001b[A\n38it [00:15, 3.02it/s]\n\n 38%|███▊ | 38/100 [00:15<00:20, 3.02it/s]\u001b[A\n39it [00:15, 3.27it/s]\n\n 39%|███▉ | 39/100 [00:15<00:18, 3.27it/s]\u001b[A\n40it [00:15, 3.44it/s]\n\n 40%|████ | 40/100 [00:15<00:17, 3.44it/s]\u001b[A\n41it [00:16, 2.37it/s]\n\n 41%|████ | 41/100 [00:16<00:24, 2.37it/s]\u001b[A\n42it [00:16, 2.72it/s]\n\n 42%|████▏ | 42/100 [00:16<00:21, 2.72it/s]\u001b[A\n43it [00:17, 3.02it/s]\n\n 43%|████▎ | 43/100 [00:17<00:18, 3.02it/s]\u001b[A\n44it [00:17, 3.26it/s]\n\n 44%|████▍ | 44/100 [00:17<00:17, 3.26it/s]\u001b[A\n45it [00:17, 3.43it/s]\n\n 45%|████▌ | 45/100 [00:17<00:16, 3.43it/s]\u001b[A\n46it [00:18, 2.38it/s]\n\n 46%|████▌ | 46/100 [00:18<00:22, 2.38it/s]\u001b[A\n47it [00:18, 2.73it/s]\n\n 47%|████▋ | 47/100 [00:18<00:19, 2.73it/s]\u001b[A\n48it [00:18, 3.03it/s]\n\n 48%|████▊ | 48/100 [00:18<00:17, 3.03it/s]\u001b[A\n49it [00:18, 3.26it/s]\n\n 49%|████▉ | 49/100 [00:18<00:15, 3.26it/s]\u001b[A\n50it [00:19, 3.44it/s]\n\n 50%|█████ | 50/100 [00:19<00:14, 3.44it/s]\u001b[A\n51it [00:19, 2.37it/s]\n\n 51%|█████ | 51/100 [00:19<00:20, 2.37it/s]\u001b[A\n52it [00:20, 2.71it/s]\n\n 52%|█████▏ | 52/100 [00:20<00:17, 2.71it/s]\u001b[A\n53it [00:20, 3.00it/s]\n\n 53%|█████▎ | 53/100 [00:20<00:15, 3.00it/s]\u001b[A\n54it [00:20, 3.24it/s]\n\n 54%|█████▍ | 54/100 [00:20<00:14, 3.24it/s]\u001b[A\n55it [00:20, 3.43it/s]\n\n 55%|█████▌ | 55/100 [00:20<00:13, 3.43it/s]\u001b[A\n56it [00:21, 2.36it/s]\n\n 56%|█████▌ | 56/100 [00:21<00:18, 2.36it/s]\u001b[A\n57it [00:21, 2.71it/s]\n\n 57%|█████▋ | 57/100 [00:21<00:15, 2.71it/s]\u001b[A\n58it [00:22, 3.00it/s]\n\n 58%|█████▊ | 58/100 [00:22<00:13, 3.00it/s]\u001b[A\n59it [00:22, 3.24it/s]\n\n 59%|█████▉ | 59/100 [00:22<00:12, 3.24it/s]\u001b[A\n60it [00:22, 3.42it/s]\n\n 60%|██████ | 60/100 [00:22<00:11, 3.42it/s]\u001b[A\n61it [00:23, 2.36it/s]\n\n 61%|██████ | 61/100 [00:23<00:16, 2.36it/s]\u001b[A\n62it [00:23, 2.71it/s]\n\n 62%|██████▏ | 62/100 [00:23<00:14, 2.71it/s]\u001b[A\n63it [00:23, 3.00it/s]\n\n 63%|██████▎ | 63/100 [00:23<00:12, 3.00it/s]\u001b[A\n64it [00:24, 3.24it/s]\n\n 64%|██████▍ | 64/100 [00:24<00:11, 3.24it/s]\u001b[A\n65it [00:24, 3.42it/s]\n\n 65%|██████▌ | 65/100 [00:24<00:10, 3.42it/s]\u001b[A\n66it [00:25, 2.36it/s]\n\n 66%|██████▌ | 66/100 [00:25<00:14, 2.36it/s]\u001b[A\n67it [00:25, 2.71it/s]\n\n 67%|██████▋ | 67/100 [00:25<00:12, 2.71it/s]\u001b[A\n68it [00:25, 2.99it/s]\n\n 68%|██████▊ | 68/100 [00:25<00:10, 2.99it/s]\u001b[A\n69it [00:25, 3.23it/s]\n\n 69%|██████▉ | 69/100 [00:25<00:09, 3.23it/s]\u001b[A\n70it [00:26, 3.41it/s]\n\n 70%|███████ | 70/100 [00:26<00:08, 3.41it/s]\u001b[A\n71it [00:26, 2.37it/s]\n\n 71%|███████ | 71/100 [00:26<00:12, 2.37it/s]\u001b[A\n72it [00:27, 2.71it/s]\n\n 72%|███████▏ | 72/100 [00:27<00:10, 2.71it/s]\u001b[A\n73it [00:27, 3.00it/s]\n\n 73%|███████▎ | 73/100 [00:27<00:09, 3.00it/s]\u001b[A\n74it [00:27, 3.24it/s]\n\n 74%|███████▍ | 74/100 [00:27<00:08, 3.24it/s]\u001b[A\n75it [00:27, 3.41it/s]\n\n 75%|███████▌ | 75/100 [00:27<00:07, 3.41it/s]\u001b[A\n76it [00:28, 2.37it/s]\n\n 76%|███████▌ | 76/100 [00:28<00:10, 2.37it/s]\u001b[A\n77it [00:28, 2.72it/s]\n\n 77%|███████▋ | 77/100 [00:28<00:08, 2.72it/s]\u001b[A\n78it [00:29, 3.00it/s]\n\n 78%|███████▊ | 78/100 [00:29<00:07, 3.00it/s]\u001b[A\n79it [00:29, 3.25it/s]\n\n 79%|███████▉ | 79/100 [00:29<00:06, 3.24it/s]\u001b[A\n80it [00:29, 3.43it/s]\n\n 80%|████████ | 80/100 [00:29<00:05, 3.43it/s]\u001b[A\n81it [00:30, 2.38it/s]\n\n 81%|████████ | 81/100 [00:30<00:07, 2.38it/s]\u001b[A\n82it [00:30, 2.72it/s]\n\n 82%|████████▏ | 82/100 [00:30<00:06, 2.72it/s]\u001b[A\n83it [00:30, 3.01it/s]\n\n 83%|████████▎ | 83/100 [00:30<00:05, 3.01it/s]\u001b[A\n84it [00:31, 3.24it/s]\n\n 84%|████████▍ | 84/100 [00:31<00:04, 3.24it/s]\u001b[A\n85it [00:31, 3.42it/s]\n\n 85%|████████▌ | 85/100 [00:31<00:04, 3.42it/s]\u001b[A\n86it [00:32, 2.38it/s]\n\n 86%|████████▌ | 86/100 [00:32<00:05, 2.38it/s]\u001b[A\n87it [00:32, 2.73it/s]\n\n 87%|████████▋ | 87/100 [00:32<00:04, 2.73it/s]\u001b[A\n88it [00:32, 3.01it/s]\n\n 88%|████████▊ | 88/100 [00:32<00:03, 3.01it/s]\u001b[A\n89it [00:32, 3.24it/s]\n\n 89%|████████▉ | 89/100 [00:32<00:03, 3.24it/s]\u001b[A\n90it [00:33, 3.43it/s]\n\n 90%|█████████ | 90/100 [00:33<00:02, 3.43it/s]\u001b[A\n91it [00:33, 2.38it/s]\n\n 91%|█████████ | 91/100 [00:33<00:03, 2.38it/s]\u001b[A\n92it [00:33, 2.73it/s]\n\n 92%|█████████▏| 92/100 [00:33<00:02, 2.73it/s]\u001b[A\n93it [00:34, 3.02it/s]\n\n 93%|█████████▎| 93/100 [00:34<00:02, 3.02it/s]\u001b[A\n94it [00:34, 3.26it/s]\n\n 94%|█████████▍| 94/100 [00:34<00:01, 3.26it/s]\u001b[A\n95it [00:34, 3.44it/s]\n\n 95%|█████████▌| 95/100 [00:34<00:01, 3.44it/s]\u001b[A\n96it [00:35, 2.39it/s]\n\n 96%|█████████▌| 96/100 [00:35<00:01, 2.39it/s]\u001b[A\n97it [00:35, 2.74it/s]\n\n 97%|█████████▋| 97/100 [00:35<00:01, 2.74it/s]\u001b[A\n98it [00:35, 3.02it/s]\n\n 98%|█████████▊| 98/100 [00:35<00:00, 3.02it/s]\u001b[A\n99it [00:36, 3.26it/s]\n\n 99%|█████████▉| 99/100 [00:36<00:00, 3.26it/s]\u001b[A\n100it [00:36, 3.44it/s]\n\n100%|██████████| 100/100 [00:36<00:00, 3.44it/s]\u001b[A\n100%|██████████| 100/100 [00:36<00:00, 2.74it/s]\n\n100it [00:36, 2.74it/s]\nFinished generating with seed 1008593075", "metrics": { "predict_time": 37.236819, "total_time": 37.412284 }, "output": [ "https://replicate.delivery/mgxm/8496f468-43c6-441b-b97c-b62e42c1354c/current.png", "https://replicate.delivery/mgxm/dccde2ae-b146-442b-8ac4-3b270a2bd312/current.png", "https://replicate.delivery/mgxm/3ab970c7-7121-40c1-b0df-fe5ec1c89f94/current.png", "https://replicate.delivery/mgxm/2982e4f6-cde1-4acd-97da-618b6469ada0/current.png", "https://replicate.delivery/mgxm/8506d766-fdff-4866-931d-1e6481e229e1/current.png", "https://replicate.delivery/mgxm/11a67ed5-60be-4c73-8fd5-51fd4cf3d7f4/current.png", "https://replicate.delivery/mgxm/7ac835f8-e0c1-4810-ac59-f72c7ba12c7d/current.png", "https://replicate.delivery/mgxm/42dc37e0-ab62-40ce-903a-18405c9e3833/current.png", "https://replicate.delivery/mgxm/a704a7fb-53ee-4c06-bdc1-021e88ddde89/current.png", "https://replicate.delivery/mgxm/f6c02270-cd40-418a-b17c-68e370b37cfd/current.png", "https://replicate.delivery/mgxm/43e8456f-cc80-42a2-a290-c3f7f9327a57/current.png", "https://replicate.delivery/mgxm/bbf50ad0-0d2d-449d-84af-61dfdc52a5bc/current.png", "https://replicate.delivery/mgxm/4a243d05-f9a4-4943-99e5-570c03de6e3a/current.png", "https://replicate.delivery/mgxm/87e7ae54-af46-4ce6-921a-1867b27517d4/current.png", "https://replicate.delivery/mgxm/b83b851e-f303-4cb9-941f-7dfd55d9e226/current.png", "https://replicate.delivery/mgxm/7e87ddf8-8209-407d-b755-abad008cbd84/current.png", "https://replicate.delivery/mgxm/24c34332-68b4-41a9-8748-9b2211bf464e/current.png", "https://replicate.delivery/mgxm/dda1e37b-a022-48f1-928f-271fecf3a4a4/current.png", "https://replicate.delivery/mgxm/c80f8d42-7da2-42e2-91b9-433de68e8d51/current.png", "https://replicate.delivery/mgxm/d6bf6aac-b47f-4cac-bca3-77a042f576b4/current.png" ], "started_at": "2022-06-05T03:19:45.532734Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/e56jbor6ajhhpdoheuhum6egcu", "cancel": "https://api.replicate.com/v1/predictions/e56jbor6ajhhpdoheuhum6egcu/cancel" }, "version": "818c3886693975754e0d8962fa51bd967c8a4a332e123a6099086f08d068c49f" }
Generated inEncoding text with BERT Encoding text with CLIP Using aesthetic embedding 9 with weight 0.5 Loading image Using inpaint model but no image is provided. Initializing with zeros. Packing CLIP and BERT embeddings into kwargs Running diffusion... 0it [00:00, ?it/s] 0%| | 0/100 [00:00<?, ?it/s] 1it [00:01, 1.45s/it] 1%| | 1/100 [00:01<02:23, 1.45s/it] 2it [00:02, 1.17s/it] 2%|▏ | 2/100 [00:02<01:54, 1.17s/it] 3it [00:03, 1.08s/it] 3%|▎ | 3/100 [00:03<01:45, 1.08s/it] 4it [00:03, 1.33it/s] 4%|▍ | 4/100 [00:03<01:12, 1.33it/s] 5it [00:03, 1.76it/s] 5%|▌ | 5/100 [00:03<00:54, 1.76it/s] 6it [00:04, 1.63it/s] 6%|▌ | 6/100 [00:04<00:57, 1.63it/s] 7it [00:04, 2.04it/s] 7%|▋ | 7/100 [00:04<00:45, 2.04it/s] 8it [00:05, 2.42it/s] 8%|▊ | 8/100 [00:05<00:38, 2.42it/s] 9it [00:05, 2.77it/s] 9%|▉ | 9/100 [00:05<00:32, 2.77it/s] 10it [00:05, 3.06it/s] 10%|█ | 10/100 [00:05<00:29, 3.06it/s] 11it [00:06, 2.25it/s] 11%|█ | 11/100 [00:06<00:39, 2.25it/s] 12it [00:06, 2.62it/s] 12%|█▏ | 12/100 [00:06<00:33, 2.62it/s] 13it [00:06, 2.94it/s] 13%|█▎ | 13/100 [00:06<00:29, 2.94it/s] 14it [00:07, 3.20it/s] 14%|█▍ | 14/100 [00:07<00:26, 3.20it/s] 15it [00:07, 3.40it/s] 15%|█▌ | 15/100 [00:07<00:24, 3.40it/s] 16it [00:07, 2.38it/s] 16%|█▌ | 16/100 [00:07<00:35, 2.38it/s] 17it [00:08, 2.73it/s] 17%|█▋ | 17/100 [00:08<00:30, 2.73it/s] 18it [00:08, 3.03it/s] 18%|█▊ | 18/100 [00:08<00:27, 3.03it/s] 19it [00:08, 3.28it/s] 19%|█▉ | 19/100 [00:08<00:24, 3.28it/s] 20it [00:08, 3.47it/s] 20%|██ | 20/100 [00:08<00:23, 3.47it/s] 21it [00:09, 2.40it/s] 21%|██ | 21/100 [00:09<00:32, 2.40it/s] 22it [00:09, 2.75it/s] 22%|██▏ | 22/100 [00:09<00:28, 2.75it/s] 23it [00:10, 3.04it/s] 23%|██▎ | 23/100 [00:10<00:25, 3.04it/s] 24it [00:10, 3.28it/s] 24%|██▍ | 24/100 [00:10<00:23, 3.28it/s] 25it [00:10, 3.47it/s] 25%|██▌ | 25/100 [00:10<00:21, 3.47it/s] 26it [00:11, 2.39it/s] 26%|██▌ | 26/100 [00:11<00:30, 2.39it/s] 27it [00:11, 2.74it/s] 27%|██▋ | 27/100 [00:11<00:26, 2.74it/s] 28it [00:11, 3.03it/s] 28%|██▊ | 28/100 [00:11<00:23, 3.03it/s] 29it [00:12, 3.28it/s] 29%|██▉ | 29/100 [00:12<00:21, 3.28it/s] 30it [00:12, 3.46it/s] 30%|███ | 30/100 [00:12<00:20, 3.46it/s] 31it [00:13, 2.39it/s] 31%|███ | 31/100 [00:13<00:28, 2.39it/s] 32it [00:13, 2.73it/s] 32%|███▏ | 32/100 [00:13<00:24, 2.73it/s] 33it [00:13, 3.02it/s] 33%|███▎ | 33/100 [00:13<00:22, 3.02it/s] 34it [00:13, 3.27it/s] 34%|███▍ | 34/100 [00:13<00:20, 3.27it/s] 35it [00:14, 3.45it/s] 35%|███▌ | 35/100 [00:14<00:18, 3.45it/s] 36it [00:14, 2.38it/s] 36%|███▌ | 36/100 [00:14<00:26, 2.38it/s] 37it [00:15, 2.73it/s] 37%|███▋ | 37/100 [00:15<00:23, 2.73it/s] 38it [00:15, 3.02it/s] 38%|███▊ | 38/100 [00:15<00:20, 3.02it/s] 39it [00:15, 3.27it/s] 39%|███▉ | 39/100 [00:15<00:18, 3.27it/s] 40it [00:15, 3.44it/s] 40%|████ | 40/100 [00:15<00:17, 3.44it/s] 41it [00:16, 2.37it/s] 41%|████ | 41/100 [00:16<00:24, 2.37it/s] 42it [00:16, 2.72it/s] 42%|████▏ | 42/100 [00:16<00:21, 2.72it/s] 43it [00:17, 3.02it/s] 43%|████▎ | 43/100 [00:17<00:18, 3.02it/s] 44it [00:17, 3.26it/s] 44%|████▍ | 44/100 [00:17<00:17, 3.26it/s] 45it [00:17, 3.43it/s] 45%|████▌ | 45/100 [00:17<00:16, 3.43it/s] 46it [00:18, 2.38it/s] 46%|████▌ | 46/100 [00:18<00:22, 2.38it/s] 47it [00:18, 2.73it/s] 47%|████▋ | 47/100 [00:18<00:19, 2.73it/s] 48it [00:18, 3.03it/s] 48%|████▊ | 48/100 [00:18<00:17, 3.03it/s] 49it [00:18, 3.26it/s] 49%|████▉ | 49/100 [00:18<00:15, 3.26it/s] 50it [00:19, 3.44it/s] 50%|█████ | 50/100 [00:19<00:14, 3.44it/s] 51it [00:19, 2.37it/s] 51%|█████ | 51/100 [00:19<00:20, 2.37it/s] 52it [00:20, 2.71it/s] 52%|█████▏ | 52/100 [00:20<00:17, 2.71it/s] 53it [00:20, 3.00it/s] 53%|█████▎ | 53/100 [00:20<00:15, 3.00it/s] 54it [00:20, 3.24it/s] 54%|█████▍ | 54/100 [00:20<00:14, 3.24it/s] 55it [00:20, 3.43it/s] 55%|█████▌ | 55/100 [00:20<00:13, 3.43it/s] 56it [00:21, 2.36it/s] 56%|█████▌ | 56/100 [00:21<00:18, 2.36it/s] 57it [00:21, 2.71it/s] 57%|█████▋ | 57/100 [00:21<00:15, 2.71it/s] 58it [00:22, 3.00it/s] 58%|█████▊ | 58/100 [00:22<00:13, 3.00it/s] 59it [00:22, 3.24it/s] 59%|█████▉ | 59/100 [00:22<00:12, 3.24it/s] 60it [00:22, 3.42it/s] 60%|██████ | 60/100 [00:22<00:11, 3.42it/s] 61it [00:23, 2.36it/s] 61%|██████ | 61/100 [00:23<00:16, 2.36it/s] 62it [00:23, 2.71it/s] 62%|██████▏ | 62/100 [00:23<00:14, 2.71it/s] 63it [00:23, 3.00it/s] 63%|██████▎ | 63/100 [00:23<00:12, 3.00it/s] 64it [00:24, 3.24it/s] 64%|██████▍ | 64/100 [00:24<00:11, 3.24it/s] 65it [00:24, 3.42it/s] 65%|██████▌ | 65/100 [00:24<00:10, 3.42it/s] 66it [00:25, 2.36it/s] 66%|██████▌ | 66/100 [00:25<00:14, 2.36it/s] 67it [00:25, 2.71it/s] 67%|██████▋ | 67/100 [00:25<00:12, 2.71it/s] 68it [00:25, 2.99it/s] 68%|██████▊ | 68/100 [00:25<00:10, 2.99it/s] 69it [00:25, 3.23it/s] 69%|██████▉ | 69/100 [00:25<00:09, 3.23it/s] 70it [00:26, 3.41it/s] 70%|███████ | 70/100 [00:26<00:08, 3.41it/s] 71it [00:26, 2.37it/s] 71%|███████ | 71/100 [00:26<00:12, 2.37it/s] 72it [00:27, 2.71it/s] 72%|███████▏ | 72/100 [00:27<00:10, 2.71it/s] 73it [00:27, 3.00it/s] 73%|███████▎ | 73/100 [00:27<00:09, 3.00it/s] 74it [00:27, 3.24it/s] 74%|███████▍ | 74/100 [00:27<00:08, 3.24it/s] 75it [00:27, 3.41it/s] 75%|███████▌ | 75/100 [00:27<00:07, 3.41it/s] 76it [00:28, 2.37it/s] 76%|███████▌ | 76/100 [00:28<00:10, 2.37it/s] 77it [00:28, 2.72it/s] 77%|███████▋ | 77/100 [00:28<00:08, 2.72it/s] 78it [00:29, 3.00it/s] 78%|███████▊ | 78/100 [00:29<00:07, 3.00it/s] 79it [00:29, 3.25it/s] 79%|███████▉ | 79/100 [00:29<00:06, 3.24it/s] 80it [00:29, 3.43it/s] 80%|████████ | 80/100 [00:29<00:05, 3.43it/s] 81it [00:30, 2.38it/s] 81%|████████ | 81/100 [00:30<00:07, 2.38it/s] 82it [00:30, 2.72it/s] 82%|████████▏ | 82/100 [00:30<00:06, 2.72it/s] 83it [00:30, 3.01it/s] 83%|████████▎ | 83/100 [00:30<00:05, 3.01it/s] 84it [00:31, 3.24it/s] 84%|████████▍ | 84/100 [00:31<00:04, 3.24it/s] 85it [00:31, 3.42it/s] 85%|████████▌ | 85/100 [00:31<00:04, 3.42it/s] 86it [00:32, 2.38it/s] 86%|████████▌ | 86/100 [00:32<00:05, 2.38it/s] 87it [00:32, 2.73it/s] 87%|████████▋ | 87/100 [00:32<00:04, 2.73it/s] 88it [00:32, 3.01it/s] 88%|████████▊ | 88/100 [00:32<00:03, 3.01it/s] 89it [00:32, 3.24it/s] 89%|████████▉ | 89/100 [00:32<00:03, 3.24it/s] 90it [00:33, 3.43it/s] 90%|█████████ | 90/100 [00:33<00:02, 3.43it/s] 91it [00:33, 2.38it/s] 91%|█████████ | 91/100 [00:33<00:03, 2.38it/s] 92it [00:33, 2.73it/s] 92%|█████████▏| 92/100 [00:33<00:02, 2.73it/s] 93it [00:34, 3.02it/s] 93%|█████████▎| 93/100 [00:34<00:02, 3.02it/s] 94it [00:34, 3.26it/s] 94%|█████████▍| 94/100 [00:34<00:01, 3.26it/s] 95it [00:34, 3.44it/s] 95%|█████████▌| 95/100 [00:34<00:01, 3.44it/s] 96it [00:35, 2.39it/s] 96%|█████████▌| 96/100 [00:35<00:01, 2.39it/s] 97it [00:35, 2.74it/s] 97%|█████████▋| 97/100 [00:35<00:01, 2.74it/s] 98it [00:35, 3.02it/s] 98%|█████████▊| 98/100 [00:35<00:00, 3.02it/s] 99it [00:36, 3.26it/s] 99%|█████████▉| 99/100 [00:36<00:00, 3.26it/s] 100it [00:36, 3.44it/s] 100%|██████████| 100/100 [00:36<00:00, 3.44it/s] 100%|██████████| 100/100 [00:36<00:00, 2.74it/s] 100it [00:36, 2.74it/s] Finished generating with seed 1008593075
Prediction
laion-ai/ongo:1b3cd151IDgcgfiw3hrbdc5lqeyxyvttdr3uStatusSucceededSourceWebHardware–Total durationCreatedInput
- seed
- -1
- steps
- "100"
- width
- 256
- height
- 256
- prompt
- a farmhouse surrounded by flowers painting
- batch_size
- "3"
- guidance_scale
- 5
- aesthetic_rating
- 8
- aesthetic_weight
- 0.1
{ "seed": -1, "steps": "100", "width": 256, "height": 256, "prompt": "a farmhouse surrounded by flowers painting", "batch_size": "3", "guidance_scale": 5, "aesthetic_rating": 8, "aesthetic_weight": 0.1 }
Install Replicate’s Node.js client library:npm install replicate
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run laion-ai/ongo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "laion-ai/ongo:1b3cd15121ec450baa71bbbdacddef9217519f12ca12ccfef36eeaa20ad89b9d", { input: { seed: -1, steps: "100", width: 256, height: 256, prompt: "a farmhouse surrounded by flowers painting", batch_size: "3", guidance_scale: 5, aesthetic_rating: 8, aesthetic_weight: 0.1 } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the client:import replicate
Run laion-ai/ongo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "laion-ai/ongo:1b3cd15121ec450baa71bbbdacddef9217519f12ca12ccfef36eeaa20ad89b9d", input={ "seed": -1, "steps": "100", "width": 256, "height": 256, "prompt": "a farmhouse surrounded by flowers painting", "batch_size": "3", "guidance_scale": 5, "aesthetic_rating": 8, "aesthetic_weight": 0.1 } ) # The laion-ai/ongo model can stream output as it's running. # The predict method returns an iterator, and you can iterate over that output. for item in output: # https://replicate.com/laion-ai/ongo/api#output-schema print(item)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run laion-ai/ongo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "1b3cd15121ec450baa71bbbdacddef9217519f12ca12ccfef36eeaa20ad89b9d", "input": { "seed": -1, "steps": "100", "width": 256, "height": 256, "prompt": "a farmhouse surrounded by flowers painting", "batch_size": "3", "guidance_scale": 5, "aesthetic_rating": 8, "aesthetic_weight": 0.1 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2022-06-05T03:21:35.603582Z", "created_at": "2022-06-05T03:20:59.207417Z", "data_removed": false, "error": null, "id": "gcgfiw3hrbdc5lqeyxyvttdr3u", "input": { "seed": -1, "steps": "100", "width": 256, "height": 256, "prompt": "a farmhouse surrounded by flowers painting", "batch_size": "3", "guidance_scale": 5, "aesthetic_rating": 8, "aesthetic_weight": 0.1 }, "logs": "Encoding text with BERT\nEncoding text with CLIP\nUsing aesthetic embedding 8 with weight 0.1\nLoading image\nUsing inpaint model but no image is provided. Initializing with zeros.\nPacking CLIP and BERT embeddings into kwargs\nRunning diffusion...\n\n0it [00:00, ?it/s]\n\n 0%| | 0/100 [00:00<?, ?it/s]\u001b[A\n1it [00:01, 1.41s/it]\n\n 1%| | 1/100 [00:01<02:19, 1.41s/it]\u001b[A\n2it [00:02, 1.15s/it]\n\n 2%|▏ | 2/100 [00:02<01:52, 1.15s/it]\u001b[A\n3it [00:03, 1.07s/it]\n\n 3%|▎ | 3/100 [00:03<01:43, 1.07s/it]\u001b[A\n4it [00:03, 1.35it/s]\n\n 4%|▍ | 4/100 [00:03<01:11, 1.35it/s]\u001b[A\n5it [00:03, 1.78it/s]\n\n 5%|▌ | 5/100 [00:03<00:53, 1.78it/s]\u001b[A\n6it [00:04, 1.68it/s]\n\n 6%|▌ | 6/100 [00:04<00:56, 1.68it/s]\u001b[A\n7it [00:04, 2.09it/s]\n\n 7%|▋ | 7/100 [00:04<00:44, 2.09it/s]\u001b[A\n8it [00:04, 2.48it/s]\n\n 8%|▊ | 8/100 [00:04<00:37, 2.48it/s]\u001b[A\n9it [00:05, 2.82it/s]\n\n 9%|▉ | 9/100 [00:05<00:32, 2.82it/s]\u001b[A\n10it [00:05, 3.12it/s]\n\n 10%|█ | 10/100 [00:05<00:28, 3.12it/s]\u001b[A\n11it [00:06, 2.36it/s]\n\n 11%|█ | 11/100 [00:06<00:37, 2.36it/s]\u001b[A\n12it [00:06, 2.72it/s]\n\n 12%|█▏ | 12/100 [00:06<00:32, 2.72it/s]\u001b[A\n13it [00:06, 3.03it/s]\n\n 13%|█▎ | 13/100 [00:06<00:28, 3.03it/s]\u001b[A\n14it [00:06, 3.28it/s]\n\n 14%|█▍ | 14/100 [00:06<00:26, 3.28it/s]\u001b[A\n15it [00:07, 3.48it/s]\n\n 15%|█▌ | 15/100 [00:07<00:24, 3.48it/s]\u001b[A\n16it [00:07, 2.49it/s]\n\n 16%|█▌ | 16/100 [00:07<00:33, 2.49it/s]\u001b[A\n17it [00:08, 2.83it/s]\n\n 17%|█▋ | 17/100 [00:08<00:29, 2.83it/s]\u001b[A\n18it [00:08, 3.12it/s]\n\n 18%|█▊ | 18/100 [00:08<00:26, 3.12it/s]\u001b[A\n19it [00:08, 3.35it/s]\n\n 19%|█▉ | 19/100 [00:08<00:24, 3.35it/s]\u001b[A\n20it [00:08, 3.53it/s]\n\n 20%|██ | 20/100 [00:08<00:22, 3.53it/s]\u001b[A\n21it [00:09, 2.51it/s]\n\n 21%|██ | 21/100 [00:09<00:31, 2.51it/s]\u001b[A\n22it [00:09, 2.86it/s]\n\n 22%|██▏ | 22/100 [00:09<00:27, 2.86it/s]\u001b[A\n23it [00:09, 3.14it/s]\n\n 23%|██▎ | 23/100 [00:09<00:24, 3.14it/s]\u001b[A\n24it [00:10, 3.36it/s]\n\n 24%|██▍ | 24/100 [00:10<00:22, 3.36it/s]\u001b[A\n25it [00:10, 3.54it/s]\n\n 25%|██▌ | 25/100 [00:10<00:21, 3.54it/s]\u001b[A\n26it [00:11, 2.51it/s]\n\n 26%|██▌ | 26/100 [00:11<00:29, 2.51it/s]\u001b[A\n27it [00:11, 2.85it/s]\n\n 27%|██▋ | 27/100 [00:11<00:25, 2.85it/s]\u001b[A\n28it [00:11, 3.13it/s]\n\n 28%|██▊ | 28/100 [00:11<00:22, 3.13it/s]\u001b[A\n29it [00:11, 3.36it/s]\n\n 29%|██▉ | 29/100 [00:11<00:21, 3.36it/s]\u001b[A\n30it [00:12, 3.53it/s]\n\n 30%|███ | 30/100 [00:12<00:19, 3.53it/s]\u001b[A\n31it [00:12, 2.50it/s]\n\n 31%|███ | 31/100 [00:12<00:27, 2.50it/s]\u001b[A\n32it [00:12, 2.84it/s]\n\n 32%|███▏ | 32/100 [00:12<00:23, 2.84it/s]\u001b[A\n33it [00:13, 3.12it/s]\n\n 33%|███▎ | 33/100 [00:13<00:21, 3.12it/s]\u001b[A\n34it [00:13, 3.35it/s]\n\n 34%|███▍ | 34/100 [00:13<00:19, 3.35it/s]\u001b[A\n35it [00:13, 3.52it/s]\n\n 35%|███▌ | 35/100 [00:13<00:18, 3.52it/s]\u001b[A\n36it [00:14, 2.49it/s]\n\n 36%|███▌ | 36/100 [00:14<00:25, 2.49it/s]\u001b[A\n37it [00:14, 2.83it/s]\n\n 37%|███▋ | 37/100 [00:14<00:22, 2.84it/s]\u001b[A\n38it [00:14, 3.11it/s]\n\n 38%|███▊ | 38/100 [00:14<00:19, 3.11it/s]\u001b[A\n39it [00:15, 3.34it/s]\n\n 39%|███▉ | 39/100 [00:15<00:18, 3.34it/s]\u001b[A\n40it [00:15, 3.51it/s]\n\n 40%|████ | 40/100 [00:15<00:17, 3.51it/s]\u001b[A\n41it [00:16, 2.48it/s]\n\n 41%|████ | 41/100 [00:16<00:23, 2.48it/s]\u001b[A\n42it [00:16, 2.82it/s]\n\n 42%|████▏ | 42/100 [00:16<00:20, 2.82it/s]\u001b[A\n43it [00:16, 3.10it/s]\n\n 43%|████▎ | 43/100 [00:16<00:18, 3.10it/s]\u001b[A\n44it [00:16, 3.33it/s]\n\n 44%|████▍ | 44/100 [00:16<00:16, 3.33it/s]\u001b[A\n45it [00:17, 3.50it/s]\n\n 45%|████▌ | 45/100 [00:17<00:15, 3.50it/s]\u001b[A\n46it [00:17, 2.48it/s]\n\n 46%|████▌ | 46/100 [00:17<00:21, 2.48it/s]\u001b[A\n47it [00:17, 2.82it/s]\n\n 47%|████▋ | 47/100 [00:17<00:18, 2.82it/s]\u001b[A\n48it [00:18, 3.10it/s]\n\n 48%|████▊ | 48/100 [00:18<00:16, 3.10it/s]\u001b[A\n49it [00:18, 3.33it/s]\n\n 49%|████▉ | 49/100 [00:18<00:15, 3.33it/s]\u001b[A\n50it [00:18, 3.50it/s]\n\n 50%|█████ | 50/100 [00:18<00:14, 3.50it/s]\u001b[A\n51it [00:19, 2.48it/s]\n\n 51%|█████ | 51/100 [00:19<00:19, 2.48it/s]\u001b[A\n52it [00:19, 2.83it/s]\n\n 52%|█████▏ | 52/100 [00:19<00:16, 2.83it/s]\u001b[A\n53it [00:19, 3.10it/s]\n\n 53%|█████▎ | 53/100 [00:19<00:15, 3.10it/s]\u001b[A\n54it [00:20, 3.32it/s]\n\n 54%|█████▍ | 54/100 [00:20<00:13, 3.32it/s]\u001b[A\n55it [00:20, 3.49it/s]\n\n 55%|█████▌ | 55/100 [00:20<00:12, 3.49it/s]\u001b[A\n56it [00:21, 2.47it/s]\n\n 56%|█████▌ | 56/100 [00:21<00:17, 2.47it/s]\u001b[A\n57it [00:21, 2.82it/s]\n\n 57%|█████▋ | 57/100 [00:21<00:15, 2.82it/s]\u001b[A\n58it [00:21, 3.09it/s]\n\n 58%|█████▊ | 58/100 [00:21<00:13, 3.09it/s]\u001b[A\n59it [00:21, 3.32it/s]\n\n 59%|█████▉ | 59/100 [00:21<00:12, 3.32it/s]\u001b[A\n60it [00:22, 3.48it/s]\n\n 60%|██████ | 60/100 [00:22<00:11, 3.48it/s]\u001b[A\n61it [00:22, 2.48it/s]\n\n 61%|██████ | 61/100 [00:22<00:15, 2.48it/s]\u001b[A\n62it [00:22, 2.82it/s]\n\n 62%|██████▏ | 62/100 [00:22<00:13, 2.82it/s]\u001b[A\n63it [00:23, 3.08it/s]\n\n 63%|██████▎ | 63/100 [00:23<00:11, 3.08it/s]\u001b[A\n64it [00:23, 3.31it/s]\n\n 64%|██████▍ | 64/100 [00:23<00:10, 3.31it/s]\u001b[A\n65it [00:23, 3.47it/s]\n\n 65%|██████▌ | 65/100 [00:23<00:10, 3.47it/s]\u001b[A\n66it [00:24, 2.47it/s]\n\n 66%|██████▌ | 66/100 [00:24<00:13, 2.47it/s]\u001b[A\n67it [00:24, 2.81it/s]\n\n 67%|██████▋ | 67/100 [00:24<00:11, 2.81it/s]\u001b[A\n68it [00:24, 3.08it/s]\n\n 68%|██████▊ | 68/100 [00:24<00:10, 3.08it/s]\u001b[A\n69it [00:25, 3.31it/s]\n\n 69%|██████▉ | 69/100 [00:25<00:09, 3.31it/s]\u001b[A\n70it [00:25, 3.48it/s]\n\n 70%|███████ | 70/100 [00:25<00:08, 3.48it/s]\u001b[A\n71it [00:26, 2.48it/s]\n\n 71%|███████ | 71/100 [00:26<00:11, 2.48it/s]\u001b[A\n72it [00:26, 2.81it/s]\n\n 72%|███████▏ | 72/100 [00:26<00:09, 2.81it/s]\u001b[A\n73it [00:26, 3.08it/s]\n\n 73%|███████▎ | 73/100 [00:26<00:08, 3.08it/s]\u001b[A\n74it [00:26, 3.30it/s]\n\n 74%|███████▍ | 74/100 [00:26<00:07, 3.30it/s]\u001b[A\n75it [00:27, 3.46it/s]\n\n 75%|███████▌ | 75/100 [00:27<00:07, 3.46it/s]\u001b[A\n76it [00:27, 2.47it/s]\n\n 76%|███████▌ | 76/100 [00:27<00:09, 2.47it/s]\u001b[A\n77it [00:27, 2.80it/s]\n\n 77%|███████▋ | 77/100 [00:27<00:08, 2.80it/s]\u001b[A\n78it [00:28, 3.07it/s]\n\n 78%|███████▊ | 78/100 [00:28<00:07, 3.07it/s]\u001b[A\n79it [00:28, 3.30it/s]\n\n 79%|███████▉ | 79/100 [00:28<00:06, 3.30it/s]\u001b[A\n80it [00:28, 3.47it/s]\n\n 80%|████████ | 80/100 [00:28<00:05, 3.47it/s]\u001b[A\n81it [00:29, 2.48it/s]\n\n 81%|████████ | 81/100 [00:29<00:07, 2.48it/s]\u001b[A\n82it [00:29, 2.81it/s]\n\n 82%|████████▏ | 82/100 [00:29<00:06, 2.81it/s]\u001b[A\n83it [00:29, 3.08it/s]\n\n 83%|████████▎ | 83/100 [00:29<00:05, 3.08it/s]\u001b[A\n84it [00:30, 3.31it/s]\n\n 84%|████████▍ | 84/100 [00:30<00:04, 3.31it/s]\u001b[A\n85it [00:30, 3.47it/s]\n\n 85%|████████▌ | 85/100 [00:30<00:04, 3.47it/s]\u001b[A\n86it [00:31, 2.47it/s]\n\n 86%|████████▌ | 86/100 [00:31<00:05, 2.47it/s]\u001b[A\n87it [00:31, 2.80it/s]\n\n 87%|████████▋ | 87/100 [00:31<00:04, 2.80it/s]\u001b[A\n88it [00:31, 3.07it/s]\n\n 88%|████████▊ | 88/100 [00:31<00:03, 3.07it/s]\u001b[A\n89it [00:31, 3.30it/s]\n\n 89%|████████▉ | 89/100 [00:31<00:03, 3.30it/s]\u001b[A\n90it [00:32, 3.47it/s]\n\n 90%|█████████ | 90/100 [00:32<00:02, 3.47it/s]\u001b[A\n91it [00:32, 2.47it/s]\n\n 91%|█████████ | 91/100 [00:32<00:03, 2.47it/s]\u001b[A\n92it [00:33, 2.81it/s]\n\n 92%|█████████▏| 92/100 [00:33<00:02, 2.81it/s]\u001b[A\n93it [00:33, 3.08it/s]\n\n 93%|█████████▎| 93/100 [00:33<00:02, 3.08it/s]\u001b[A\n94it [00:33, 3.30it/s]\n\n 94%|█████████▍| 94/100 [00:33<00:01, 3.30it/s]\u001b[A\n95it [00:33, 3.46it/s]\n\n 95%|█████████▌| 95/100 [00:33<00:01, 3.46it/s]\u001b[A\n96it [00:34, 2.47it/s]\n\n 96%|█████████▌| 96/100 [00:34<00:01, 2.47it/s]\u001b[A\n97it [00:34, 2.80it/s]\n\n 97%|█████████▋| 97/100 [00:34<00:01, 2.80it/s]\u001b[A\n98it [00:34, 3.08it/s]\n\n 98%|█████████▊| 98/100 [00:34<00:00, 3.08it/s]\u001b[A\n99it [00:35, 3.30it/s]\n\n 99%|█████████▉| 99/100 [00:35<00:00, 3.30it/s]\u001b[A\n100it [00:35, 3.46it/s]\n\n100%|██████████| 100/100 [00:35<00:00, 3.46it/s]\u001b[A\n100%|██████████| 100/100 [00:35<00:00, 2.82it/s]\n\n100it [00:35, 2.82it/s]\nFinished generating with seed 3501501057", "metrics": { "predict_time": 36.233789, "total_time": 36.396165 }, "output": [ "https://replicate.delivery/mgxm/49ae5bd4-7987-46cc-bae3-0390ae9ae1fe/current.png", "https://replicate.delivery/mgxm/b948f863-b56f-4a68-ac77-5291c3ff8d51/current.png", "https://replicate.delivery/mgxm/31236d32-c7c8-446f-bfe2-afbe4eb2a6f5/current.png", "https://replicate.delivery/mgxm/72f1cc7d-d8aa-42c8-8c22-3c3c20e8b11e/current.png", "https://replicate.delivery/mgxm/8874ccd3-af88-471c-912e-eeac0925c06e/current.png", "https://replicate.delivery/mgxm/496bc8fb-083a-4db2-92dd-71f2654b5a53/current.png", "https://replicate.delivery/mgxm/a568edd8-46a1-4daf-b0a0-0f4f9c616a3b/current.png", "https://replicate.delivery/mgxm/f44260ce-f735-400f-82fd-920061fc6a03/current.png", "https://replicate.delivery/mgxm/773bedd4-5b01-4eec-b5f8-61adefd2854d/current.png", "https://replicate.delivery/mgxm/d9ef5f94-8560-4f77-bf48-2e18e2cd702f/current.png", "https://replicate.delivery/mgxm/431e9c84-b6b9-4910-b901-52e7c99f81a0/current.png", "https://replicate.delivery/mgxm/4c13f21f-aae2-4ceb-8299-7d873b87b6e1/current.png", "https://replicate.delivery/mgxm/270a3e41-f5f2-473e-b30c-2af3edafe2c2/current.png", "https://replicate.delivery/mgxm/cc3c2c2c-7de6-452a-91c7-df6058591839/current.png", "https://replicate.delivery/mgxm/f98b7fc9-f3c8-4f69-b75a-b89b5e922b86/current.png", "https://replicate.delivery/mgxm/b945bfa4-cf53-4b27-86fa-bdaaa6ed13c7/current.png", "https://replicate.delivery/mgxm/123f23e3-d7eb-4a03-a3ab-14312be556ca/current.png", "https://replicate.delivery/mgxm/4f2388a9-1b46-4932-b7b8-44e8b9ffce3e/current.png", "https://replicate.delivery/mgxm/16fc9bc6-e700-4cbb-9bcb-9c1b6b0c1e81/current.png", "https://replicate.delivery/mgxm/2e9a0651-83e6-46b6-9204-6e7dc73fa30b/current.png" ], "started_at": "2022-06-05T03:20:59.369793Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/gcgfiw3hrbdc5lqeyxyvttdr3u", "cancel": "https://api.replicate.com/v1/predictions/gcgfiw3hrbdc5lqeyxyvttdr3u/cancel" }, "version": "818c3886693975754e0d8962fa51bd967c8a4a332e123a6099086f08d068c49f" }
Generated inEncoding text with BERT Encoding text with CLIP Using aesthetic embedding 8 with weight 0.1 Loading image Using inpaint model but no image is provided. Initializing with zeros. Packing CLIP and BERT embeddings into kwargs Running diffusion... 0it [00:00, ?it/s] 0%| | 0/100 [00:00<?, ?it/s] 1it [00:01, 1.41s/it] 1%| | 1/100 [00:01<02:19, 1.41s/it] 2it [00:02, 1.15s/it] 2%|▏ | 2/100 [00:02<01:52, 1.15s/it] 3it [00:03, 1.07s/it] 3%|▎ | 3/100 [00:03<01:43, 1.07s/it] 4it [00:03, 1.35it/s] 4%|▍ | 4/100 [00:03<01:11, 1.35it/s] 5it [00:03, 1.78it/s] 5%|▌ | 5/100 [00:03<00:53, 1.78it/s] 6it [00:04, 1.68it/s] 6%|▌ | 6/100 [00:04<00:56, 1.68it/s] 7it [00:04, 2.09it/s] 7%|▋ | 7/100 [00:04<00:44, 2.09it/s] 8it [00:04, 2.48it/s] 8%|▊ | 8/100 [00:04<00:37, 2.48it/s] 9it [00:05, 2.82it/s] 9%|▉ | 9/100 [00:05<00:32, 2.82it/s] 10it [00:05, 3.12it/s] 10%|█ | 10/100 [00:05<00:28, 3.12it/s] 11it [00:06, 2.36it/s] 11%|█ | 11/100 [00:06<00:37, 2.36it/s] 12it [00:06, 2.72it/s] 12%|█▏ | 12/100 [00:06<00:32, 2.72it/s] 13it [00:06, 3.03it/s] 13%|█▎ | 13/100 [00:06<00:28, 3.03it/s] 14it [00:06, 3.28it/s] 14%|█▍ | 14/100 [00:06<00:26, 3.28it/s] 15it [00:07, 3.48it/s] 15%|█▌ | 15/100 [00:07<00:24, 3.48it/s] 16it [00:07, 2.49it/s] 16%|█▌ | 16/100 [00:07<00:33, 2.49it/s] 17it [00:08, 2.83it/s] 17%|█▋ | 17/100 [00:08<00:29, 2.83it/s] 18it [00:08, 3.12it/s] 18%|█▊ | 18/100 [00:08<00:26, 3.12it/s] 19it [00:08, 3.35it/s] 19%|█▉ | 19/100 [00:08<00:24, 3.35it/s] 20it [00:08, 3.53it/s] 20%|██ | 20/100 [00:08<00:22, 3.53it/s] 21it [00:09, 2.51it/s] 21%|██ | 21/100 [00:09<00:31, 2.51it/s] 22it [00:09, 2.86it/s] 22%|██▏ | 22/100 [00:09<00:27, 2.86it/s] 23it [00:09, 3.14it/s] 23%|██▎ | 23/100 [00:09<00:24, 3.14it/s] 24it [00:10, 3.36it/s] 24%|██▍ | 24/100 [00:10<00:22, 3.36it/s] 25it [00:10, 3.54it/s] 25%|██▌ | 25/100 [00:10<00:21, 3.54it/s] 26it [00:11, 2.51it/s] 26%|██▌ | 26/100 [00:11<00:29, 2.51it/s] 27it [00:11, 2.85it/s] 27%|██▋ | 27/100 [00:11<00:25, 2.85it/s] 28it [00:11, 3.13it/s] 28%|██▊ | 28/100 [00:11<00:22, 3.13it/s] 29it [00:11, 3.36it/s] 29%|██▉ | 29/100 [00:11<00:21, 3.36it/s] 30it [00:12, 3.53it/s] 30%|███ | 30/100 [00:12<00:19, 3.53it/s] 31it [00:12, 2.50it/s] 31%|███ | 31/100 [00:12<00:27, 2.50it/s] 32it [00:12, 2.84it/s] 32%|███▏ | 32/100 [00:12<00:23, 2.84it/s] 33it [00:13, 3.12it/s] 33%|███▎ | 33/100 [00:13<00:21, 3.12it/s] 34it [00:13, 3.35it/s] 34%|███▍ | 34/100 [00:13<00:19, 3.35it/s] 35it [00:13, 3.52it/s] 35%|███▌ | 35/100 [00:13<00:18, 3.52it/s] 36it [00:14, 2.49it/s] 36%|███▌ | 36/100 [00:14<00:25, 2.49it/s] 37it [00:14, 2.83it/s] 37%|███▋ | 37/100 [00:14<00:22, 2.84it/s] 38it [00:14, 3.11it/s] 38%|███▊ | 38/100 [00:14<00:19, 3.11it/s] 39it [00:15, 3.34it/s] 39%|███▉ | 39/100 [00:15<00:18, 3.34it/s] 40it [00:15, 3.51it/s] 40%|████ | 40/100 [00:15<00:17, 3.51it/s] 41it [00:16, 2.48it/s] 41%|████ | 41/100 [00:16<00:23, 2.48it/s] 42it [00:16, 2.82it/s] 42%|████▏ | 42/100 [00:16<00:20, 2.82it/s] 43it [00:16, 3.10it/s] 43%|████▎ | 43/100 [00:16<00:18, 3.10it/s] 44it [00:16, 3.33it/s] 44%|████▍ | 44/100 [00:16<00:16, 3.33it/s] 45it [00:17, 3.50it/s] 45%|████▌ | 45/100 [00:17<00:15, 3.50it/s] 46it [00:17, 2.48it/s] 46%|████▌ | 46/100 [00:17<00:21, 2.48it/s] 47it [00:17, 2.82it/s] 47%|████▋ | 47/100 [00:17<00:18, 2.82it/s] 48it [00:18, 3.10it/s] 48%|████▊ | 48/100 [00:18<00:16, 3.10it/s] 49it [00:18, 3.33it/s] 49%|████▉ | 49/100 [00:18<00:15, 3.33it/s] 50it [00:18, 3.50it/s] 50%|█████ | 50/100 [00:18<00:14, 3.50it/s] 51it [00:19, 2.48it/s] 51%|█████ | 51/100 [00:19<00:19, 2.48it/s] 52it [00:19, 2.83it/s] 52%|█████▏ | 52/100 [00:19<00:16, 2.83it/s] 53it [00:19, 3.10it/s] 53%|█████▎ | 53/100 [00:19<00:15, 3.10it/s] 54it [00:20, 3.32it/s] 54%|█████▍ | 54/100 [00:20<00:13, 3.32it/s] 55it [00:20, 3.49it/s] 55%|█████▌ | 55/100 [00:20<00:12, 3.49it/s] 56it [00:21, 2.47it/s] 56%|█████▌ | 56/100 [00:21<00:17, 2.47it/s] 57it [00:21, 2.82it/s] 57%|█████▋ | 57/100 [00:21<00:15, 2.82it/s] 58it [00:21, 3.09it/s] 58%|█████▊ | 58/100 [00:21<00:13, 3.09it/s] 59it [00:21, 3.32it/s] 59%|█████▉ | 59/100 [00:21<00:12, 3.32it/s] 60it [00:22, 3.48it/s] 60%|██████ | 60/100 [00:22<00:11, 3.48it/s] 61it [00:22, 2.48it/s] 61%|██████ | 61/100 [00:22<00:15, 2.48it/s] 62it [00:22, 2.82it/s] 62%|██████▏ | 62/100 [00:22<00:13, 2.82it/s] 63it [00:23, 3.08it/s] 63%|██████▎ | 63/100 [00:23<00:11, 3.08it/s] 64it [00:23, 3.31it/s] 64%|██████▍ | 64/100 [00:23<00:10, 3.31it/s] 65it [00:23, 3.47it/s] 65%|██████▌ | 65/100 [00:23<00:10, 3.47it/s] 66it [00:24, 2.47it/s] 66%|██████▌ | 66/100 [00:24<00:13, 2.47it/s] 67it [00:24, 2.81it/s] 67%|██████▋ | 67/100 [00:24<00:11, 2.81it/s] 68it [00:24, 3.08it/s] 68%|██████▊ | 68/100 [00:24<00:10, 3.08it/s] 69it [00:25, 3.31it/s] 69%|██████▉ | 69/100 [00:25<00:09, 3.31it/s] 70it [00:25, 3.48it/s] 70%|███████ | 70/100 [00:25<00:08, 3.48it/s] 71it [00:26, 2.48it/s] 71%|███████ | 71/100 [00:26<00:11, 2.48it/s] 72it [00:26, 2.81it/s] 72%|███████▏ | 72/100 [00:26<00:09, 2.81it/s] 73it [00:26, 3.08it/s] 73%|███████▎ | 73/100 [00:26<00:08, 3.08it/s] 74it [00:26, 3.30it/s] 74%|███████▍ | 74/100 [00:26<00:07, 3.30it/s] 75it [00:27, 3.46it/s] 75%|███████▌ | 75/100 [00:27<00:07, 3.46it/s] 76it [00:27, 2.47it/s] 76%|███████▌ | 76/100 [00:27<00:09, 2.47it/s] 77it [00:27, 2.80it/s] 77%|███████▋ | 77/100 [00:27<00:08, 2.80it/s] 78it [00:28, 3.07it/s] 78%|███████▊ | 78/100 [00:28<00:07, 3.07it/s] 79it [00:28, 3.30it/s] 79%|███████▉ | 79/100 [00:28<00:06, 3.30it/s] 80it [00:28, 3.47it/s] 80%|████████ | 80/100 [00:28<00:05, 3.47it/s] 81it [00:29, 2.48it/s] 81%|████████ | 81/100 [00:29<00:07, 2.48it/s] 82it [00:29, 2.81it/s] 82%|████████▏ | 82/100 [00:29<00:06, 2.81it/s] 83it [00:29, 3.08it/s] 83%|████████▎ | 83/100 [00:29<00:05, 3.08it/s] 84it [00:30, 3.31it/s] 84%|████████▍ | 84/100 [00:30<00:04, 3.31it/s] 85it [00:30, 3.47it/s] 85%|████████▌ | 85/100 [00:30<00:04, 3.47it/s] 86it [00:31, 2.47it/s] 86%|████████▌ | 86/100 [00:31<00:05, 2.47it/s] 87it [00:31, 2.80it/s] 87%|████████▋ | 87/100 [00:31<00:04, 2.80it/s] 88it [00:31, 3.07it/s] 88%|████████▊ | 88/100 [00:31<00:03, 3.07it/s] 89it [00:31, 3.30it/s] 89%|████████▉ | 89/100 [00:31<00:03, 3.30it/s] 90it [00:32, 3.47it/s] 90%|█████████ | 90/100 [00:32<00:02, 3.47it/s] 91it [00:32, 2.47it/s] 91%|█████████ | 91/100 [00:32<00:03, 2.47it/s] 92it [00:33, 2.81it/s] 92%|█████████▏| 92/100 [00:33<00:02, 2.81it/s] 93it [00:33, 3.08it/s] 93%|█████████▎| 93/100 [00:33<00:02, 3.08it/s] 94it [00:33, 3.30it/s] 94%|█████████▍| 94/100 [00:33<00:01, 3.30it/s] 95it [00:33, 3.46it/s] 95%|█████████▌| 95/100 [00:33<00:01, 3.46it/s] 96it [00:34, 2.47it/s] 96%|█████████▌| 96/100 [00:34<00:01, 2.47it/s] 97it [00:34, 2.80it/s] 97%|█████████▋| 97/100 [00:34<00:01, 2.80it/s] 98it [00:34, 3.08it/s] 98%|█████████▊| 98/100 [00:34<00:00, 3.08it/s] 99it [00:35, 3.30it/s] 99%|█████████▉| 99/100 [00:35<00:00, 3.30it/s] 100it [00:35, 3.46it/s] 100%|██████████| 100/100 [00:35<00:00, 3.46it/s] 100%|██████████| 100/100 [00:35<00:00, 2.82it/s] 100it [00:35, 2.82it/s] Finished generating with seed 3501501057
Prediction
laion-ai/ongo:1b3cd151IDmemxvg44yjecrk6kcpgxhwqvfqStatusSucceededSourceWebHardware–Total durationCreatedInput
- seed
- -1
- steps
- "100"
- width
- 256
- height
- 256
- prompt
- star wars concept art
- batch_size
- "6"
- guidance_scale
- 5
- aesthetic_rating
- 9
- aesthetic_weight
- 0.5
{ "seed": -1, "steps": "100", "width": 256, "height": 256, "prompt": "star wars concept art", "batch_size": "6", "guidance_scale": 5, "aesthetic_rating": 9, "aesthetic_weight": 0.5 }
Install Replicate’s Node.js client library:npm install replicate
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run laion-ai/ongo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "laion-ai/ongo:1b3cd15121ec450baa71bbbdacddef9217519f12ca12ccfef36eeaa20ad89b9d", { input: { seed: -1, steps: "100", width: 256, height: 256, prompt: "star wars concept art", batch_size: "6", guidance_scale: 5, aesthetic_rating: 9, aesthetic_weight: 0.5 } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the client:import replicate
Run laion-ai/ongo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "laion-ai/ongo:1b3cd15121ec450baa71bbbdacddef9217519f12ca12ccfef36eeaa20ad89b9d", input={ "seed": -1, "steps": "100", "width": 256, "height": 256, "prompt": "star wars concept art", "batch_size": "6", "guidance_scale": 5, "aesthetic_rating": 9, "aesthetic_weight": 0.5 } ) # The laion-ai/ongo model can stream output as it's running. # The predict method returns an iterator, and you can iterate over that output. for item in output: # https://replicate.com/laion-ai/ongo/api#output-schema print(item)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run laion-ai/ongo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "1b3cd15121ec450baa71bbbdacddef9217519f12ca12ccfef36eeaa20ad89b9d", "input": { "seed": -1, "steps": "100", "width": 256, "height": 256, "prompt": "star wars concept art", "batch_size": "6", "guidance_scale": 5, "aesthetic_rating": 9, "aesthetic_weight": 0.5 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2022-06-05T03:33:57.873395Z", "created_at": "2022-06-05T03:32:47.310397Z", "data_removed": false, "error": null, "id": "memxvg44yjecrk6kcpgxhwqvfq", "input": { "seed": -1, "steps": "100", "width": 256, "height": 256, "prompt": "star wars concept art", "batch_size": "6", "guidance_scale": 5, "aesthetic_rating": 9, "aesthetic_weight": 0.5 }, "logs": "Encoding text with BERT\nEncoding text with CLIP\nUsing aesthetic embedding 9 with weight 0.5\nLoading image\nUsing inpaint model but no image is provided. Initializing with zeros.\nPacking CLIP and BERT embeddings into kwargs\nRunning diffusion...\n\n0it [00:00, ?it/s]\n\n 0%| | 0/100 [00:00<?, ?it/s]\u001b[A\n1it [00:04, 4.92s/it]\n\n 1%| | 1/100 [00:04<08:06, 4.92s/it]\u001b[A\n2it [00:06, 3.04s/it]\n\n 2%|▏ | 2/100 [00:06<04:58, 3.04s/it]\u001b[A\n3it [00:08, 2.45s/it]\n\n 3%|▎ | 3/100 [00:08<03:57, 2.45s/it]\u001b[A\n4it [00:08, 1.65s/it]\n\n 4%|▍ | 4/100 [00:08<02:38, 1.65s/it]\u001b[A\n5it [00:09, 1.21s/it]\n\n 5%|▌ | 5/100 [00:09<01:55, 1.21s/it]\u001b[A\n6it [00:10, 1.28s/it]\n\n 6%|▌ | 6/100 [00:10<02:00, 1.28s/it]\u001b[A\n7it [00:11, 1.01s/it]\n\n 7%|▋ | 7/100 [00:11<01:33, 1.01s/it]\u001b[A\n8it [00:11, 1.21it/s]\n\n 8%|▊ | 8/100 [00:11<01:15, 1.21it/s]\u001b[A\n9it [00:11, 1.42it/s]\n\n 9%|▉ | 9/100 [00:11<01:04, 1.42it/s]\u001b[A\n10it [00:12, 1.61it/s]\n\n 10%|█ | 10/100 [00:12<00:55, 1.61it/s]\u001b[A\n11it [00:13, 1.16it/s]\n\n 11%|█ | 11/100 [00:13<01:17, 1.16it/s]\u001b[A\n12it [00:14, 1.36it/s]\n\n 12%|█▏ | 12/100 [00:14<01:04, 1.36it/s]\u001b[A\n13it [00:14, 1.55it/s]\n\n 13%|█▎ | 13/100 [00:14<00:56, 1.55it/s]\u001b[A\n14it [00:15, 1.71it/s]\n\n 14%|█▍ | 14/100 [00:15<00:50, 1.71it/s]\u001b[A\n15it [00:15, 1.85it/s]\n\n 15%|█▌ | 15/100 [00:15<00:45, 1.85it/s]\u001b[A\n16it [00:17, 1.25it/s]\n\n 16%|█▌ | 16/100 [00:17<01:07, 1.25it/s]\u001b[A\n17it [00:17, 1.45it/s]\n\n 17%|█▋ | 17/100 [00:17<00:57, 1.45it/s]\u001b[A\n18it [00:17, 1.62it/s]\n\n 18%|█▊ | 18/100 [00:17<00:50, 1.62it/s]\u001b[A\n19it [00:18, 1.78it/s]\n\n 19%|█▉ | 19/100 [00:18<00:45, 1.78it/s]\u001b[A\n20it [00:18, 1.90it/s]\n\n 20%|██ | 20/100 [00:18<00:42, 1.90it/s]\u001b[A\n21it [00:20, 1.26it/s]\n\n 21%|██ | 21/100 [00:20<01:02, 1.26it/s]\u001b[A\n22it [00:20, 1.46it/s]\n\n 22%|██▏ | 22/100 [00:20<00:53, 1.46it/s]\u001b[A\n23it [00:21, 1.63it/s]\n\n 23%|██▎ | 23/100 [00:21<00:47, 1.63it/s]\u001b[A\n24it [00:21, 1.78it/s]\n\n 24%|██▍ | 24/100 [00:21<00:42, 1.78it/s]\u001b[A\n25it [00:21, 1.90it/s]\n\n 25%|██▌ | 25/100 [00:21<00:39, 1.90it/s]\u001b[A\n26it [00:23, 1.26it/s]\n\n 26%|██▌ | 26/100 [00:23<00:58, 1.26it/s]\u001b[A\n27it [00:23, 1.46it/s]\n\n 27%|██▋ | 27/100 [00:23<00:49, 1.46it/s]\u001b[A\n28it [00:24, 1.63it/s]\n\n 28%|██▊ | 28/100 [00:24<00:44, 1.63it/s]\u001b[A\n29it [00:24, 1.78it/s]\n\n 29%|██▉ | 29/100 [00:24<00:39, 1.78it/s]\u001b[A\n30it [00:25, 1.90it/s]\n\n 30%|███ | 30/100 [00:25<00:36, 1.90it/s]\u001b[A\n31it [00:26, 1.26it/s]\n\n 31%|███ | 31/100 [00:26<00:54, 1.26it/s]\u001b[A\n32it [00:26, 1.45it/s]\n\n 32%|███▏ | 32/100 [00:26<00:46, 1.45it/s]\u001b[A\n33it [00:27, 1.63it/s]\n\n 33%|███▎ | 33/100 [00:27<00:41, 1.63it/s]\u001b[A\n34it [00:27, 1.77it/s]\n\n 34%|███▍ | 34/100 [00:27<00:37, 1.77it/s]\u001b[A\n35it [00:28, 1.89it/s]\n\n 35%|███▌ | 35/100 [00:28<00:34, 1.89it/s]\u001b[A\n36it [00:29, 1.26it/s]\n\n 36%|███▌ | 36/100 [00:29<00:50, 1.26it/s]\u001b[A\n37it [00:30, 1.46it/s]\n\n 37%|███▋ | 37/100 [00:30<00:43, 1.46it/s]\u001b[A\n38it [00:30, 1.62it/s]\n\n 38%|███▊ | 38/100 [00:30<00:38, 1.62it/s]\u001b[A\n39it [00:31, 1.76it/s]\n\n 39%|███▉ | 39/100 [00:31<00:34, 1.76it/s]\u001b[A\n40it [00:31, 1.88it/s]\n\n 40%|████ | 40/100 [00:31<00:31, 1.88it/s]\u001b[A\n41it [00:32, 1.25it/s]\n\n 41%|████ | 41/100 [00:32<00:47, 1.25it/s]\u001b[A\n42it [00:33, 1.45it/s]\n\n 42%|████▏ | 42/100 [00:33<00:39, 1.45it/s]\u001b[A\n43it [00:33, 1.62it/s]\n\n 43%|████▎ | 43/100 [00:33<00:35, 1.62it/s]\u001b[A\n44it [00:34, 1.76it/s]\n\n 44%|████▍ | 44/100 [00:34<00:31, 1.76it/s]\u001b[A\n45it [00:34, 1.88it/s]\n\n 45%|████▌ | 45/100 [00:34<00:29, 1.88it/s]\u001b[A\n46it [00:36, 1.26it/s]\n\n 46%|████▌ | 46/100 [00:36<00:42, 1.26it/s]\u001b[A\n47it [00:36, 1.46it/s]\n\n 47%|████▋ | 47/100 [00:36<00:36, 1.46it/s]\u001b[A\n48it [00:37, 1.62it/s]\n\n 48%|████▊ | 48/100 [00:37<00:32, 1.62it/s]\u001b[A\n49it [00:37, 1.76it/s]\n\n 49%|████▉ | 49/100 [00:37<00:28, 1.76it/s]\u001b[A\n50it [00:37, 1.88it/s]\n\n 50%|█████ | 50/100 [00:37<00:26, 1.88it/s]\u001b[A\n51it [00:39, 1.26it/s]\n\n 51%|█████ | 51/100 [00:39<00:38, 1.26it/s]\u001b[A\n52it [00:39, 1.46it/s]\n\n 52%|█████▏ | 52/100 [00:39<00:32, 1.46it/s]\u001b[A\n53it [00:40, 1.62it/s]\n\n 53%|█████▎ | 53/100 [00:40<00:28, 1.62it/s]\u001b[A\n54it [00:40, 1.76it/s]\n\n 54%|█████▍ | 54/100 [00:40<00:26, 1.76it/s]\u001b[A\n55it [00:41, 1.89it/s]\n\n 55%|█████▌ | 55/100 [00:41<00:23, 1.89it/s]\u001b[A\n56it [00:42, 1.27it/s]\n\n 56%|█████▌ | 56/100 [00:42<00:34, 1.27it/s]\u001b[A\n57it [00:42, 1.46it/s]\n\n 57%|█████▋ | 57/100 [00:42<00:29, 1.46it/s]\u001b[A\n58it [00:43, 1.62it/s]\n\n 58%|█████▊ | 58/100 [00:43<00:25, 1.62it/s]\u001b[A\n59it [00:43, 1.76it/s]\n\n 59%|█████▉ | 59/100 [00:43<00:23, 1.76it/s]\u001b[A\n60it [00:44, 1.88it/s]\n\n 60%|██████ | 60/100 [00:44<00:21, 1.88it/s]\u001b[A\n61it [00:45, 1.27it/s]\n\n 61%|██████ | 61/100 [00:45<00:30, 1.27it/s]\u001b[A\n62it [00:46, 1.47it/s]\n\n 62%|██████▏ | 62/100 [00:46<00:25, 1.47it/s]\u001b[A\n63it [00:46, 1.63it/s]\n\n 63%|██████▎ | 63/100 [00:46<00:22, 1.63it/s]\u001b[A\n64it [00:47, 1.77it/s]\n\n 64%|██████▍ | 64/100 [00:47<00:20, 1.77it/s]\u001b[A\n65it [00:47, 1.89it/s]\n\n 65%|██████▌ | 65/100 [00:47<00:18, 1.89it/s]\u001b[A\n66it [00:48, 1.28it/s]\n\n 66%|██████▌ | 66/100 [00:48<00:26, 1.28it/s]\u001b[A\n67it [00:49, 1.48it/s]\n\n 67%|██████▋ | 67/100 [00:49<00:22, 1.48it/s]\u001b[A\n68it [00:49, 1.64it/s]\n\n 68%|██████▊ | 68/100 [00:49<00:19, 1.64it/s]\u001b[A\n69it [00:50, 1.78it/s]\n\n 69%|██████▉ | 69/100 [00:50<00:17, 1.78it/s]\u001b[A\n70it [00:50, 1.90it/s]\n\n 70%|███████ | 70/100 [00:50<00:15, 1.90it/s]\u001b[A\n71it [00:51, 1.28it/s]\n\n 71%|███████ | 71/100 [00:51<00:22, 1.28it/s]\u001b[A\n72it [00:52, 1.48it/s]\n\n 72%|███████▏ | 72/100 [00:52<00:18, 1.48it/s]\u001b[A\n73it [00:52, 1.65it/s]\n\n 73%|███████▎ | 73/100 [00:52<00:16, 1.65it/s]\u001b[A\n74it [00:53, 1.78it/s]\n\n 74%|███████▍ | 74/100 [00:53<00:14, 1.78it/s]\u001b[A\n75it [00:53, 1.90it/s]\n\n 75%|███████▌ | 75/100 [00:53<00:13, 1.90it/s]\u001b[A\n76it [00:55, 1.29it/s]\n\n 76%|███████▌ | 76/100 [00:55<00:18, 1.29it/s]\u001b[A\n77it [00:55, 1.48it/s]\n\n 77%|███████▋ | 77/100 [00:55<00:15, 1.48it/s]\u001b[A\n78it [00:56, 1.65it/s]\n\n 78%|███████▊ | 78/100 [00:56<00:13, 1.65it/s]\u001b[A\n79it [00:56, 1.79it/s]\n\n 79%|███████▉ | 79/100 [00:56<00:11, 1.79it/s]\u001b[A\n80it [00:56, 1.90it/s]\n\n 80%|████████ | 80/100 [00:56<00:10, 1.90it/s]\u001b[A\n81it [00:58, 1.30it/s]\n\n 81%|████████ | 81/100 [00:58<00:14, 1.30it/s]\u001b[A\n82it [00:58, 1.49it/s]\n\n 82%|████████▏ | 82/100 [00:58<00:12, 1.49it/s]\u001b[A\n83it [00:59, 1.66it/s]\n\n 83%|████████▎ | 83/100 [00:59<00:10, 1.66it/s]\u001b[A\n84it [00:59, 1.79it/s]\n\n 84%|████████▍ | 84/100 [00:59<00:08, 1.79it/s]\u001b[A\n85it [01:00, 1.91it/s]\n\n 85%|████████▌ | 85/100 [01:00<00:07, 1.91it/s]\u001b[A\n86it [01:01, 1.30it/s]\n\n 86%|████████▌ | 86/100 [01:01<00:10, 1.30it/s]\u001b[A\n87it [01:01, 1.49it/s]\n\n 87%|████████▋ | 87/100 [01:01<00:08, 1.49it/s]\u001b[A\n88it [01:02, 1.66it/s]\n\n 88%|████████▊ | 88/100 [01:02<00:07, 1.66it/s]\u001b[A\n89it [01:02, 1.81it/s]\n\n 89%|████████▉ | 89/100 [01:02<00:06, 1.81it/s]\u001b[A\n90it [01:03, 1.92it/s]\n\n 90%|█████████ | 90/100 [01:03<00:05, 1.92it/s]\u001b[A\n91it [01:04, 1.30it/s]\n\n 91%|█████████ | 91/100 [01:04<00:06, 1.30it/s]\u001b[A\n92it [01:04, 1.50it/s]\n\n 92%|█████████▏| 92/100 [01:04<00:05, 1.50it/s]\u001b[A\n93it [01:05, 1.66it/s]\n\n 93%|█████████▎| 93/100 [01:05<00:04, 1.66it/s]\u001b[A\n94it [01:05, 1.80it/s]\n\n 94%|█████████▍| 94/100 [01:05<00:03, 1.80it/s]\u001b[A\n95it [01:06, 1.92it/s]\n\n 95%|█████████▌| 95/100 [01:06<00:02, 1.92it/s]\u001b[A\n96it [01:07, 1.31it/s]\n\n 96%|█████████▌| 96/100 [01:07<00:03, 1.31it/s]\u001b[A\n97it [01:08, 1.50it/s]\n\n 97%|█████████▋| 97/100 [01:08<00:01, 1.50it/s]\u001b[A\n98it [01:08, 1.67it/s]\n\n 98%|█████████▊| 98/100 [01:08<00:01, 1.67it/s]\u001b[A\n99it [01:08, 1.81it/s]\n\n 99%|█████████▉| 99/100 [01:08<00:00, 1.81it/s]\u001b[A\n100it [01:09, 1.93it/s]\n\n100%|██████████| 100/100 [01:09<00:00, 1.93it/s]\u001b[A\n100%|██████████| 100/100 [01:09<00:00, 1.44it/s]\n\n100it [01:09, 1.44it/s]\nFinished generating with seed 315760442", "metrics": { "predict_time": 70.412455, "total_time": 70.562998 }, "output": [ "https://replicate.delivery/mgxm/06b6cdea-c75c-46e1-b919-99288bbc9549/current.png", "https://replicate.delivery/mgxm/c1e130da-5edf-458a-9a42-737abc0eb913/current.png", "https://replicate.delivery/mgxm/fc98a203-0e22-48f0-8248-a9467f860ae4/current.png", "https://replicate.delivery/mgxm/8fb678c4-56b1-4d14-9938-99e4998df0d0/current.png", "https://replicate.delivery/mgxm/2adb9f2b-60a8-409f-bc65-1e196253df40/current.png", "https://replicate.delivery/mgxm/c1101c9a-9e2c-45f9-8b70-f98eff23860e/current.png", "https://replicate.delivery/mgxm/a352d686-67c0-4ad7-ade7-bee2a50ddac9/current.png", "https://replicate.delivery/mgxm/d122e760-611c-43b6-bc5c-619f0e87e8eb/current.png", "https://replicate.delivery/mgxm/ba6d6934-dbb7-452e-b7cb-79eedab36c28/current.png", "https://replicate.delivery/mgxm/e6b07409-1f09-4f68-b6a6-5a2b6f502cd9/current.png", "https://replicate.delivery/mgxm/575ac2a4-2160-488d-a67c-1a4b5a1b1d93/current.png", "https://replicate.delivery/mgxm/b0d563e8-f220-4fba-866d-cc65128a1ef4/current.png", "https://replicate.delivery/mgxm/cb0ebe24-af22-4e3f-b462-07c2a420bd82/current.png", "https://replicate.delivery/mgxm/ba0ca5ad-2ea8-4359-8287-bc18b92035f9/current.png", "https://replicate.delivery/mgxm/c9be4118-e0be-42f3-bafa-74a6d65b6527/current.png", "https://replicate.delivery/mgxm/0b4770fc-e513-4eb6-b283-aa07d5dc26e3/current.png", "https://replicate.delivery/mgxm/ed1301cf-9f13-4dff-aba9-b3a61f44dc1d/current.png", "https://replicate.delivery/mgxm/cb255924-d87b-42b1-a779-4c016341fbea/current.png", "https://replicate.delivery/mgxm/70e53929-d01f-4c2d-b611-8dea1d535b9c/current.png", "https://replicate.delivery/mgxm/eb4e1fdf-8f7f-4588-b631-dbf9069c168b/current.png" ], "started_at": "2022-06-05T03:32:47.460940Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/memxvg44yjecrk6kcpgxhwqvfq", "cancel": "https://api.replicate.com/v1/predictions/memxvg44yjecrk6kcpgxhwqvfq/cancel" }, "version": "818c3886693975754e0d8962fa51bd967c8a4a332e123a6099086f08d068c49f" }
Generated inEncoding text with BERT Encoding text with CLIP Using aesthetic embedding 9 with weight 0.5 Loading image Using inpaint model but no image is provided. Initializing with zeros. Packing CLIP and BERT embeddings into kwargs Running diffusion... 0it [00:00, ?it/s] 0%| | 0/100 [00:00<?, ?it/s] 1it [00:04, 4.92s/it] 1%| | 1/100 [00:04<08:06, 4.92s/it] 2it [00:06, 3.04s/it] 2%|▏ | 2/100 [00:06<04:58, 3.04s/it] 3it [00:08, 2.45s/it] 3%|▎ | 3/100 [00:08<03:57, 2.45s/it] 4it [00:08, 1.65s/it] 4%|▍ | 4/100 [00:08<02:38, 1.65s/it] 5it [00:09, 1.21s/it] 5%|▌ | 5/100 [00:09<01:55, 1.21s/it] 6it [00:10, 1.28s/it] 6%|▌ | 6/100 [00:10<02:00, 1.28s/it] 7it [00:11, 1.01s/it] 7%|▋ | 7/100 [00:11<01:33, 1.01s/it] 8it [00:11, 1.21it/s] 8%|▊ | 8/100 [00:11<01:15, 1.21it/s] 9it [00:11, 1.42it/s] 9%|▉ | 9/100 [00:11<01:04, 1.42it/s] 10it [00:12, 1.61it/s] 10%|█ | 10/100 [00:12<00:55, 1.61it/s] 11it [00:13, 1.16it/s] 11%|█ | 11/100 [00:13<01:17, 1.16it/s] 12it [00:14, 1.36it/s] 12%|█▏ | 12/100 [00:14<01:04, 1.36it/s] 13it [00:14, 1.55it/s] 13%|█▎ | 13/100 [00:14<00:56, 1.55it/s] 14it [00:15, 1.71it/s] 14%|█▍ | 14/100 [00:15<00:50, 1.71it/s] 15it [00:15, 1.85it/s] 15%|█▌ | 15/100 [00:15<00:45, 1.85it/s] 16it [00:17, 1.25it/s] 16%|█▌ | 16/100 [00:17<01:07, 1.25it/s] 17it [00:17, 1.45it/s] 17%|█▋ | 17/100 [00:17<00:57, 1.45it/s] 18it [00:17, 1.62it/s] 18%|█▊ | 18/100 [00:17<00:50, 1.62it/s] 19it [00:18, 1.78it/s] 19%|█▉ | 19/100 [00:18<00:45, 1.78it/s] 20it [00:18, 1.90it/s] 20%|██ | 20/100 [00:18<00:42, 1.90it/s] 21it [00:20, 1.26it/s] 21%|██ | 21/100 [00:20<01:02, 1.26it/s] 22it [00:20, 1.46it/s] 22%|██▏ | 22/100 [00:20<00:53, 1.46it/s] 23it [00:21, 1.63it/s] 23%|██▎ | 23/100 [00:21<00:47, 1.63it/s] 24it [00:21, 1.78it/s] 24%|██▍ | 24/100 [00:21<00:42, 1.78it/s] 25it [00:21, 1.90it/s] 25%|██▌ | 25/100 [00:21<00:39, 1.90it/s] 26it [00:23, 1.26it/s] 26%|██▌ | 26/100 [00:23<00:58, 1.26it/s] 27it [00:23, 1.46it/s] 27%|██▋ | 27/100 [00:23<00:49, 1.46it/s] 28it [00:24, 1.63it/s] 28%|██▊ | 28/100 [00:24<00:44, 1.63it/s] 29it [00:24, 1.78it/s] 29%|██▉ | 29/100 [00:24<00:39, 1.78it/s] 30it [00:25, 1.90it/s] 30%|███ | 30/100 [00:25<00:36, 1.90it/s] 31it [00:26, 1.26it/s] 31%|███ | 31/100 [00:26<00:54, 1.26it/s] 32it [00:26, 1.45it/s] 32%|███▏ | 32/100 [00:26<00:46, 1.45it/s] 33it [00:27, 1.63it/s] 33%|███▎ | 33/100 [00:27<00:41, 1.63it/s] 34it [00:27, 1.77it/s] 34%|███▍ | 34/100 [00:27<00:37, 1.77it/s] 35it [00:28, 1.89it/s] 35%|███▌ | 35/100 [00:28<00:34, 1.89it/s] 36it [00:29, 1.26it/s] 36%|███▌ | 36/100 [00:29<00:50, 1.26it/s] 37it [00:30, 1.46it/s] 37%|███▋ | 37/100 [00:30<00:43, 1.46it/s] 38it [00:30, 1.62it/s] 38%|███▊ | 38/100 [00:30<00:38, 1.62it/s] 39it [00:31, 1.76it/s] 39%|███▉ | 39/100 [00:31<00:34, 1.76it/s] 40it [00:31, 1.88it/s] 40%|████ | 40/100 [00:31<00:31, 1.88it/s] 41it [00:32, 1.25it/s] 41%|████ | 41/100 [00:32<00:47, 1.25it/s] 42it [00:33, 1.45it/s] 42%|████▏ | 42/100 [00:33<00:39, 1.45it/s] 43it [00:33, 1.62it/s] 43%|████▎ | 43/100 [00:33<00:35, 1.62it/s] 44it [00:34, 1.76it/s] 44%|████▍ | 44/100 [00:34<00:31, 1.76it/s] 45it [00:34, 1.88it/s] 45%|████▌ | 45/100 [00:34<00:29, 1.88it/s] 46it [00:36, 1.26it/s] 46%|████▌ | 46/100 [00:36<00:42, 1.26it/s] 47it [00:36, 1.46it/s] 47%|████▋ | 47/100 [00:36<00:36, 1.46it/s] 48it [00:37, 1.62it/s] 48%|████▊ | 48/100 [00:37<00:32, 1.62it/s] 49it [00:37, 1.76it/s] 49%|████▉ | 49/100 [00:37<00:28, 1.76it/s] 50it [00:37, 1.88it/s] 50%|█████ | 50/100 [00:37<00:26, 1.88it/s] 51it [00:39, 1.26it/s] 51%|█████ | 51/100 [00:39<00:38, 1.26it/s] 52it [00:39, 1.46it/s] 52%|█████▏ | 52/100 [00:39<00:32, 1.46it/s] 53it [00:40, 1.62it/s] 53%|█████▎ | 53/100 [00:40<00:28, 1.62it/s] 54it [00:40, 1.76it/s] 54%|█████▍ | 54/100 [00:40<00:26, 1.76it/s] 55it [00:41, 1.89it/s] 55%|█████▌ | 55/100 [00:41<00:23, 1.89it/s] 56it [00:42, 1.27it/s] 56%|█████▌ | 56/100 [00:42<00:34, 1.27it/s] 57it [00:42, 1.46it/s] 57%|█████▋ | 57/100 [00:42<00:29, 1.46it/s] 58it [00:43, 1.62it/s] 58%|█████▊ | 58/100 [00:43<00:25, 1.62it/s] 59it [00:43, 1.76it/s] 59%|█████▉ | 59/100 [00:43<00:23, 1.76it/s] 60it [00:44, 1.88it/s] 60%|██████ | 60/100 [00:44<00:21, 1.88it/s] 61it [00:45, 1.27it/s] 61%|██████ | 61/100 [00:45<00:30, 1.27it/s] 62it [00:46, 1.47it/s] 62%|██████▏ | 62/100 [00:46<00:25, 1.47it/s] 63it [00:46, 1.63it/s] 63%|██████▎ | 63/100 [00:46<00:22, 1.63it/s] 64it [00:47, 1.77it/s] 64%|██████▍ | 64/100 [00:47<00:20, 1.77it/s] 65it [00:47, 1.89it/s] 65%|██████▌ | 65/100 [00:47<00:18, 1.89it/s] 66it [00:48, 1.28it/s] 66%|██████▌ | 66/100 [00:48<00:26, 1.28it/s] 67it [00:49, 1.48it/s] 67%|██████▋ | 67/100 [00:49<00:22, 1.48it/s] 68it [00:49, 1.64it/s] 68%|██████▊ | 68/100 [00:49<00:19, 1.64it/s] 69it [00:50, 1.78it/s] 69%|██████▉ | 69/100 [00:50<00:17, 1.78it/s] 70it [00:50, 1.90it/s] 70%|███████ | 70/100 [00:50<00:15, 1.90it/s] 71it [00:51, 1.28it/s] 71%|███████ | 71/100 [00:51<00:22, 1.28it/s] 72it [00:52, 1.48it/s] 72%|███████▏ | 72/100 [00:52<00:18, 1.48it/s] 73it [00:52, 1.65it/s] 73%|███████▎ | 73/100 [00:52<00:16, 1.65it/s] 74it [00:53, 1.78it/s] 74%|███████▍ | 74/100 [00:53<00:14, 1.78it/s] 75it [00:53, 1.90it/s] 75%|███████▌ | 75/100 [00:53<00:13, 1.90it/s] 76it [00:55, 1.29it/s] 76%|███████▌ | 76/100 [00:55<00:18, 1.29it/s] 77it [00:55, 1.48it/s] 77%|███████▋ | 77/100 [00:55<00:15, 1.48it/s] 78it [00:56, 1.65it/s] 78%|███████▊ | 78/100 [00:56<00:13, 1.65it/s] 79it [00:56, 1.79it/s] 79%|███████▉ | 79/100 [00:56<00:11, 1.79it/s] 80it [00:56, 1.90it/s] 80%|████████ | 80/100 [00:56<00:10, 1.90it/s] 81it [00:58, 1.30it/s] 81%|████████ | 81/100 [00:58<00:14, 1.30it/s] 82it [00:58, 1.49it/s] 82%|████████▏ | 82/100 [00:58<00:12, 1.49it/s] 83it [00:59, 1.66it/s] 83%|████████▎ | 83/100 [00:59<00:10, 1.66it/s] 84it [00:59, 1.79it/s] 84%|████████▍ | 84/100 [00:59<00:08, 1.79it/s] 85it [01:00, 1.91it/s] 85%|████████▌ | 85/100 [01:00<00:07, 1.91it/s] 86it [01:01, 1.30it/s] 86%|████████▌ | 86/100 [01:01<00:10, 1.30it/s] 87it [01:01, 1.49it/s] 87%|████████▋ | 87/100 [01:01<00:08, 1.49it/s] 88it [01:02, 1.66it/s] 88%|████████▊ | 88/100 [01:02<00:07, 1.66it/s] 89it [01:02, 1.81it/s] 89%|████████▉ | 89/100 [01:02<00:06, 1.81it/s] 90it [01:03, 1.92it/s] 90%|█████████ | 90/100 [01:03<00:05, 1.92it/s] 91it [01:04, 1.30it/s] 91%|█████████ | 91/100 [01:04<00:06, 1.30it/s] 92it [01:04, 1.50it/s] 92%|█████████▏| 92/100 [01:04<00:05, 1.50it/s] 93it [01:05, 1.66it/s] 93%|█████████▎| 93/100 [01:05<00:04, 1.66it/s] 94it [01:05, 1.80it/s] 94%|█████████▍| 94/100 [01:05<00:03, 1.80it/s] 95it [01:06, 1.92it/s] 95%|█████████▌| 95/100 [01:06<00:02, 1.92it/s] 96it [01:07, 1.31it/s] 96%|█████████▌| 96/100 [01:07<00:03, 1.31it/s] 97it [01:08, 1.50it/s] 97%|█████████▋| 97/100 [01:08<00:01, 1.50it/s] 98it [01:08, 1.67it/s] 98%|█████████▊| 98/100 [01:08<00:01, 1.67it/s] 99it [01:08, 1.81it/s] 99%|█████████▉| 99/100 [01:08<00:00, 1.81it/s] 100it [01:09, 1.93it/s] 100%|██████████| 100/100 [01:09<00:00, 1.93it/s] 100%|██████████| 100/100 [01:09<00:00, 1.44it/s] 100it [01:09, 1.44it/s] Finished generating with seed 315760442
Prediction
laion-ai/ongo:1b3cd151ID6kabc6ksanea7nadevmu26n5uyStatusSucceededSourceWebHardware–Total durationCreatedInput
- seed
- -1
- steps
- "100"
- width
- 256
- height
- 256
- prompt
- concept art of 2001 a space odyssey
- batch_size
- "6"
- guidance_scale
- 5
- aesthetic_rating
- 9
- aesthetic_weight
- 0.5
{ "seed": -1, "steps": "100", "width": 256, "height": 256, "prompt": "concept art of 2001 a space odyssey", "batch_size": "6", "guidance_scale": 5, "aesthetic_rating": 9, "aesthetic_weight": 0.5 }
Install Replicate’s Node.js client library:npm install replicate
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run laion-ai/ongo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "laion-ai/ongo:1b3cd15121ec450baa71bbbdacddef9217519f12ca12ccfef36eeaa20ad89b9d", { input: { seed: -1, steps: "100", width: 256, height: 256, prompt: "concept art of 2001 a space odyssey", batch_size: "6", guidance_scale: 5, aesthetic_rating: 9, aesthetic_weight: 0.5 } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the client:import replicate
Run laion-ai/ongo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "laion-ai/ongo:1b3cd15121ec450baa71bbbdacddef9217519f12ca12ccfef36eeaa20ad89b9d", input={ "seed": -1, "steps": "100", "width": 256, "height": 256, "prompt": "concept art of 2001 a space odyssey", "batch_size": "6", "guidance_scale": 5, "aesthetic_rating": 9, "aesthetic_weight": 0.5 } ) # The laion-ai/ongo model can stream output as it's running. # The predict method returns an iterator, and you can iterate over that output. for item in output: # https://replicate.com/laion-ai/ongo/api#output-schema print(item)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run laion-ai/ongo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "1b3cd15121ec450baa71bbbdacddef9217519f12ca12ccfef36eeaa20ad89b9d", "input": { "seed": -1, "steps": "100", "width": 256, "height": 256, "prompt": "concept art of 2001 a space odyssey", "batch_size": "6", "guidance_scale": 5, "aesthetic_rating": 9, "aesthetic_weight": 0.5 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2022-06-05T03:36:03.637035Z", "created_at": "2022-06-05T03:34:28.572215Z", "data_removed": false, "error": null, "id": "6kabc6ksanea7nadevmu26n5uy", "input": { "seed": -1, "steps": "100", "width": 256, "height": 256, "prompt": "concept art of 2001 a space odyssey", "batch_size": "6", "guidance_scale": 5, "aesthetic_rating": 9, "aesthetic_weight": 0.5 }, "logs": "Encoding text with BERT\nEncoding text with CLIP\nUsing aesthetic embedding 9 with weight 0.5\nLoading image\nUsing inpaint model but no image is provided. Initializing with zeros.\nPacking CLIP and BERT embeddings into kwargs\nRunning diffusion...\n\n0it [00:00, ?it/s]\n\n 0%| | 0/100 [00:00<?, ?it/s]\u001b[A\n1it [00:02, 2.77s/it]\n\n 1%| | 1/100 [00:02<04:34, 2.77s/it]\u001b[A\n2it [00:04, 2.19s/it]\n\n 2%|▏ | 2/100 [00:04<03:34, 2.19s/it]\u001b[A\n3it [00:06, 2.00s/it]\n\n 3%|▎ | 3/100 [00:06<03:14, 2.00s/it]\u001b[A\n4it [00:06, 1.39s/it]\n\n 4%|▍ | 4/100 [00:06<02:13, 1.39s/it]\u001b[A\n5it [00:07, 1.05s/it]\n\n 5%|▌ | 5/100 [00:07<01:39, 1.05s/it]\u001b[A\n6it [00:08, 1.18s/it]\n\n 6%|▌ | 6/100 [00:08<01:50, 1.18s/it]\u001b[A\n7it [00:09, 1.07it/s]\n\n 7%|▋ | 7/100 [00:09<01:26, 1.07it/s]\u001b[A\n8it [00:09, 1.28it/s]\n\n 8%|▊ | 8/100 [00:09<01:11, 1.28it/s]\u001b[A\n9it [00:09, 1.48it/s]\n\n 9%|▉ | 9/100 [00:09<01:01, 1.48it/s]\u001b[A\n10it [00:10, 1.65it/s]\n\n 10%|█ | 10/100 [00:10<00:54, 1.65it/s]\u001b[A\n11it [00:11, 1.17it/s]\n\n 11%|█ | 11/100 [00:11<01:15, 1.17it/s]\u001b[A\n12it [00:12, 1.38it/s]\n\n 12%|█▏ | 12/100 [00:12<01:03, 1.38it/s]\u001b[A\n13it [00:12, 1.56it/s]\n\n 13%|█▎ | 13/100 [00:12<00:55, 1.56it/s]\u001b[A\n14it [00:13, 1.72it/s]\n\n 14%|█▍ | 14/100 [00:13<00:50, 1.72it/s]\u001b[A\n15it [00:13, 1.85it/s]\n\n 15%|█▌ | 15/100 [00:13<00:45, 1.85it/s]\u001b[A\n16it [00:15, 1.25it/s]\n\n 16%|█▌ | 16/100 [00:15<01:07, 1.25it/s]\u001b[A\n17it [00:15, 1.45it/s]\n\n 17%|█▋ | 17/100 [00:15<00:57, 1.45it/s]\u001b[A\n18it [00:15, 1.62it/s]\n\n 18%|█▊ | 18/100 [00:15<00:50, 1.62it/s]\u001b[A\n19it [00:16, 1.77it/s]\n\n 19%|█▉ | 19/100 [00:16<00:45, 1.77it/s]\u001b[A\n20it [00:16, 1.89it/s]\n\n 20%|██ | 20/100 [00:16<00:42, 1.89it/s]\u001b[A\n21it [00:18, 1.26it/s]\n\n 21%|██ | 21/100 [00:18<01:02, 1.26it/s]\u001b[A\n22it [00:18, 1.46it/s]\n\n 22%|██▏ | 22/100 [00:18<00:53, 1.46it/s]\u001b[A\n23it [00:19, 1.64it/s]\n\n 23%|██▎ | 23/100 [00:19<00:47, 1.64it/s]\u001b[A\n24it [00:19, 1.78it/s]\n\n 24%|██▍ | 24/100 [00:19<00:42, 1.78it/s]\u001b[A\n25it [00:19, 1.90it/s]\n\n 25%|██▌ | 25/100 [00:19<00:39, 1.90it/s]\u001b[A\n26it [00:21, 1.27it/s]\n\n 26%|██▌ | 26/100 [00:21<00:58, 1.27it/s]\u001b[A\n27it [00:21, 1.47it/s]\n\n 27%|██▋ | 27/100 [00:21<00:49, 1.47it/s]\u001b[A\n28it [00:22, 1.64it/s]\n\n 28%|██▊ | 28/100 [00:22<00:43, 1.64it/s]\u001b[A\n29it [00:22, 1.79it/s]\n\n 29%|██▉ | 29/100 [00:22<00:39, 1.79it/s]\u001b[A\n30it [00:23, 1.90it/s]\n\n 30%|███ | 30/100 [00:23<00:36, 1.90it/s]\u001b[A\n31it [00:24, 1.27it/s]\n\n 31%|███ | 31/100 [00:24<00:54, 1.27it/s]\u001b[A\n32it [00:24, 1.47it/s]\n\n 32%|███▏ | 32/100 [00:24<00:46, 1.47it/s]\u001b[A\n33it [00:25, 1.65it/s]\n\n 33%|███▎ | 33/100 [00:25<00:40, 1.65it/s]\u001b[A\n34it [00:25, 1.79it/s]\n\n 34%|███▍ | 34/100 [00:25<00:36, 1.79it/s]\u001b[A\n35it [00:26, 1.91it/s]\n\n 35%|███▌ | 35/100 [00:26<00:34, 1.91it/s]\u001b[A\n36it [00:27, 1.28it/s]\n\n 36%|███▌ | 36/100 [00:27<00:49, 1.28it/s]\u001b[A\n37it [00:28, 1.48it/s]\n\n 37%|███▋ | 37/100 [00:28<00:42, 1.48it/s]\u001b[A\n38it [00:28, 1.65it/s]\n\n 38%|███▊ | 38/100 [00:28<00:37, 1.65it/s]\u001b[A\n39it [00:28, 1.79it/s]\n\n 39%|███▉ | 39/100 [00:28<00:34, 1.79it/s]\u001b[A\n40it [00:29, 1.91it/s]\n\n 40%|████ | 40/100 [00:29<00:31, 1.91it/s]\u001b[A\n41it [00:30, 1.28it/s]\n\n 41%|████ | 41/100 [00:30<00:46, 1.28it/s]\u001b[A\n42it [00:31, 1.48it/s]\n\n 42%|████▏ | 42/100 [00:31<00:39, 1.48it/s]\u001b[A\n43it [00:31, 1.65it/s]\n\n 43%|████▎ | 43/100 [00:31<00:34, 1.65it/s]\u001b[A\n44it [00:32, 1.80it/s]\n\n 44%|████▍ | 44/100 [00:32<00:31, 1.80it/s]\u001b[A\n45it [00:32, 1.92it/s]\n\n 45%|████▌ | 45/100 [00:32<00:28, 1.92it/s]\u001b[A\n46it [00:33, 1.29it/s]\n\n 46%|████▌ | 46/100 [00:33<00:41, 1.29it/s]\u001b[A\n47it [00:34, 1.49it/s]\n\n 47%|████▋ | 47/100 [00:34<00:35, 1.49it/s]\u001b[A\n48it [00:34, 1.66it/s]\n\n 48%|████▊ | 48/100 [00:34<00:31, 1.66it/s]\u001b[A\n49it [00:35, 1.80it/s]\n\n 49%|████▉ | 49/100 [00:35<00:28, 1.80it/s]\u001b[A\n50it [00:35, 1.92it/s]\n\n 50%|█████ | 50/100 [00:35<00:26, 1.92it/s]\u001b[A\n51it [00:37, 1.29it/s]\n\n 51%|█████ | 51/100 [00:37<00:37, 1.29it/s]\u001b[A\n52it [00:37, 1.49it/s]\n\n 52%|█████▏ | 52/100 [00:37<00:32, 1.49it/s]\u001b[A\n53it [00:37, 1.66it/s]\n\n 53%|█████▎ | 53/100 [00:37<00:28, 1.66it/s]\u001b[A\n54it [00:38, 1.80it/s]\n\n 54%|█████▍ | 54/100 [00:38<00:25, 1.80it/s]\u001b[A\n55it [00:38, 1.92it/s]\n\n 55%|█████▌ | 55/100 [00:38<00:23, 1.92it/s]\u001b[A\n56it [00:40, 1.29it/s]\n\n 56%|█████▌ | 56/100 [00:40<00:34, 1.29it/s]\u001b[A\n57it [00:40, 1.49it/s]\n\n 57%|█████▋ | 57/100 [00:40<00:28, 1.49it/s]\u001b[A\n58it [00:41, 1.66it/s]\n\n 58%|█████▊ | 58/100 [00:41<00:25, 1.66it/s]\u001b[A\n59it [00:41, 1.80it/s]\n\n 59%|█████▉ | 59/100 [00:41<00:22, 1.80it/s]\u001b[A\n60it [00:41, 1.92it/s]\n\n 60%|██████ | 60/100 [00:41<00:20, 1.92it/s]\u001b[A\n61it [00:43, 1.29it/s]\n\n 61%|██████ | 61/100 [00:43<00:30, 1.29it/s]\u001b[A\n62it [00:43, 1.49it/s]\n\n 62%|██████▏ | 62/100 [00:43<00:25, 1.49it/s]\u001b[A\n63it [00:44, 1.66it/s]\n\n 63%|██████▎ | 63/100 [00:44<00:22, 1.66it/s]\u001b[A\n64it [00:44, 1.80it/s]\n\n 64%|██████▍ | 64/100 [00:44<00:20, 1.80it/s]\u001b[A\n65it [00:45, 1.91it/s]\n\n 65%|██████▌ | 65/100 [00:45<00:18, 1.91it/s]\u001b[A\n66it [00:46, 1.30it/s]\n\n 66%|██████▌ | 66/100 [00:46<00:26, 1.30it/s]\u001b[A\n67it [00:46, 1.50it/s]\n\n 67%|██████▋ | 67/100 [00:46<00:22, 1.50it/s]\u001b[A\n68it [00:47, 1.67it/s]\n\n 68%|██████▊ | 68/100 [00:47<00:19, 1.67it/s]\u001b[A\n69it [00:47, 1.80it/s]\n\n 69%|██████▉ | 69/100 [00:47<00:17, 1.80it/s]\u001b[A\n70it [00:48, 1.92it/s]\n\n 70%|███████ | 70/100 [00:48<00:15, 1.92it/s]\u001b[A\n71it [00:49, 1.31it/s]\n\n 71%|███████ | 71/100 [00:49<00:22, 1.31it/s]\u001b[A\n72it [00:49, 1.50it/s]\n\n 72%|███████▏ | 72/100 [00:49<00:18, 1.50it/s]\u001b[A\n73it [00:50, 1.67it/s]\n\n 73%|███████▎ | 73/100 [00:50<00:16, 1.67it/s]\u001b[A\n74it [00:50, 1.81it/s]\n\n 74%|███████▍ | 74/100 [00:50<00:14, 1.81it/s]\u001b[A\n75it [00:51, 1.92it/s]\n\n 75%|███████▌ | 75/100 [00:51<00:13, 1.92it/s]\u001b[A\n76it [00:52, 1.31it/s]\n\n 76%|███████▌ | 76/100 [00:52<00:18, 1.31it/s]\u001b[A\n77it [00:53, 1.50it/s]\n\n 77%|███████▋ | 77/100 [00:53<00:15, 1.50it/s]\u001b[A\n78it [00:53, 1.67it/s]\n\n 78%|███████▊ | 78/100 [00:53<00:13, 1.67it/s]\u001b[A\n79it [00:53, 1.81it/s]\n\n 79%|███████▉ | 79/100 [00:53<00:11, 1.81it/s]\u001b[A\n80it [00:54, 1.92it/s]\n\n 80%|████████ | 80/100 [00:54<00:10, 1.92it/s]\u001b[A\n81it [00:55, 1.31it/s]\n\n 81%|████████ | 81/100 [00:55<00:14, 1.31it/s]\u001b[A\n82it [00:56, 1.50it/s]\n\n 82%|████████▏ | 82/100 [00:56<00:11, 1.50it/s]\u001b[A\n83it [00:56, 1.67it/s]\n\n 83%|████████▎ | 83/100 [00:56<00:10, 1.67it/s]\u001b[A\n84it [00:57, 1.81it/s]\n\n 84%|████████▍ | 84/100 [00:57<00:08, 1.81it/s]\u001b[A\n85it [00:57, 1.92it/s]\n\n 85%|████████▌ | 85/100 [00:57<00:07, 1.92it/s]\u001b[A\n86it [00:58, 1.31it/s]\n\n 86%|████████▌ | 86/100 [00:58<00:10, 1.31it/s]\u001b[A\n87it [00:59, 1.50it/s]\n\n 87%|████████▋ | 87/100 [00:59<00:08, 1.50it/s]\u001b[A\n88it [00:59, 1.67it/s]\n\n 88%|████████▊ | 88/100 [00:59<00:07, 1.67it/s]\u001b[A\n89it [01:00, 1.81it/s]\n\n 89%|████████▉ | 89/100 [01:00<00:06, 1.81it/s]\u001b[A\n90it [01:00, 1.92it/s]\n\n 90%|█████████ | 90/100 [01:00<00:05, 1.92it/s]\u001b[A\n91it [01:01, 1.31it/s]\n\n 91%|█████████ | 91/100 [01:01<00:06, 1.31it/s]\u001b[A\n92it [01:02, 1.50it/s]\n\n 92%|█████████▏| 92/100 [01:02<00:05, 1.50it/s]\u001b[A\n93it [01:02, 1.67it/s]\n\n 93%|█████████▎| 93/100 [01:02<00:04, 1.67it/s]\u001b[A\n94it [01:03, 1.81it/s]\n\n 94%|█████████▍| 94/100 [01:03<00:03, 1.81it/s]\u001b[A\n95it [01:03, 1.92it/s]\n\n 95%|█████████▌| 95/100 [01:03<00:02, 1.92it/s]\u001b[A\n96it [01:05, 1.31it/s]\n\n 96%|█████████▌| 96/100 [01:05<00:03, 1.31it/s]\u001b[A\n97it [01:05, 1.50it/s]\n\n 97%|█████████▋| 97/100 [01:05<00:01, 1.50it/s]\u001b[A\n98it [01:05, 1.67it/s]\n\n 98%|█████████▊| 98/100 [01:05<00:01, 1.67it/s]\u001b[A\n99it [01:06, 1.81it/s]\n\n 99%|█████████▉| 99/100 [01:06<00:00, 1.81it/s]\u001b[A\n100it [01:06, 1.92it/s]\n\n100%|██████████| 100/100 [01:06<00:00, 1.92it/s]\u001b[A\n100%|██████████| 100/100 [01:06<00:00, 1.50it/s]\n\n100it [01:06, 1.50it/s]\nFinished generating with seed 908426086", "metrics": { "predict_time": 66.684719, "total_time": 95.06482 }, "output": [ "https://replicate.delivery/mgxm/c3b85c9f-2379-452d-9444-360434a46063/current.png", "https://replicate.delivery/mgxm/6d513e79-b821-43bd-b38f-2ef04e553481/current.png", "https://replicate.delivery/mgxm/0508cbd9-faff-49eb-abd2-41f780fc9ed0/current.png", "https://replicate.delivery/mgxm/4515a81a-0f34-42b2-b556-34ad34d39829/current.png", "https://replicate.delivery/mgxm/ca3c00a8-8044-4bc0-9689-cde38208eaf3/current.png", "https://replicate.delivery/mgxm/146f83cc-a695-4f23-ae64-7d4fe2d331af/current.png", "https://replicate.delivery/mgxm/386db86e-62ae-4243-a417-61241d5fc73e/current.png", "https://replicate.delivery/mgxm/94c6bb97-70fd-4204-84a9-1cdf63c08ba4/current.png", "https://replicate.delivery/mgxm/02cd7c03-0cc5-4227-b0c9-57d24da85a45/current.png", "https://replicate.delivery/mgxm/b3df1532-2f9b-407f-8ba7-d6eff10cc130/current.png", "https://replicate.delivery/mgxm/b259525a-e173-4b66-9d54-3e48f4dc38a5/current.png", "https://replicate.delivery/mgxm/6321ce0a-a12d-4af6-b1ee-aa909c18d06a/current.png", "https://replicate.delivery/mgxm/a2e5acd9-d3f3-4dc9-afc4-7d7b60d1afea/current.png", "https://replicate.delivery/mgxm/8c29c99e-3d60-46d4-9a26-80bd0c044370/current.png", "https://replicate.delivery/mgxm/820e410f-8dee-47a0-9d1b-6f55175df408/current.png", "https://replicate.delivery/mgxm/096e0167-6367-44ff-ae40-39f69fe6fdf1/current.png", "https://replicate.delivery/mgxm/d589bde0-815a-4208-85f2-836519230b0e/current.png", "https://replicate.delivery/mgxm/19d247fd-f4d9-4a08-ba0d-940c576df30e/current.png", "https://replicate.delivery/mgxm/602aa48e-28d0-4900-9036-cc3d7f0f6a75/current.png", "https://replicate.delivery/mgxm/8edd85e6-7963-4d20-b282-5030b79e732c/current.png" ], "started_at": "2022-06-05T03:34:56.952316Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/6kabc6ksanea7nadevmu26n5uy", "cancel": "https://api.replicate.com/v1/predictions/6kabc6ksanea7nadevmu26n5uy/cancel" }, "version": "818c3886693975754e0d8962fa51bd967c8a4a332e123a6099086f08d068c49f" }
Generated inEncoding text with BERT Encoding text with CLIP Using aesthetic embedding 9 with weight 0.5 Loading image Using inpaint model but no image is provided. Initializing with zeros. Packing CLIP and BERT embeddings into kwargs Running diffusion... 0it [00:00, ?it/s] 0%| | 0/100 [00:00<?, ?it/s] 1it [00:02, 2.77s/it] 1%| | 1/100 [00:02<04:34, 2.77s/it] 2it [00:04, 2.19s/it] 2%|▏ | 2/100 [00:04<03:34, 2.19s/it] 3it [00:06, 2.00s/it] 3%|▎ | 3/100 [00:06<03:14, 2.00s/it] 4it [00:06, 1.39s/it] 4%|▍ | 4/100 [00:06<02:13, 1.39s/it] 5it [00:07, 1.05s/it] 5%|▌ | 5/100 [00:07<01:39, 1.05s/it] 6it [00:08, 1.18s/it] 6%|▌ | 6/100 [00:08<01:50, 1.18s/it] 7it [00:09, 1.07it/s] 7%|▋ | 7/100 [00:09<01:26, 1.07it/s] 8it [00:09, 1.28it/s] 8%|▊ | 8/100 [00:09<01:11, 1.28it/s] 9it [00:09, 1.48it/s] 9%|▉ | 9/100 [00:09<01:01, 1.48it/s] 10it [00:10, 1.65it/s] 10%|█ | 10/100 [00:10<00:54, 1.65it/s] 11it [00:11, 1.17it/s] 11%|█ | 11/100 [00:11<01:15, 1.17it/s] 12it [00:12, 1.38it/s] 12%|█▏ | 12/100 [00:12<01:03, 1.38it/s] 13it [00:12, 1.56it/s] 13%|█▎ | 13/100 [00:12<00:55, 1.56it/s] 14it [00:13, 1.72it/s] 14%|█▍ | 14/100 [00:13<00:50, 1.72it/s] 15it [00:13, 1.85it/s] 15%|█▌ | 15/100 [00:13<00:45, 1.85it/s] 16it [00:15, 1.25it/s] 16%|█▌ | 16/100 [00:15<01:07, 1.25it/s] 17it [00:15, 1.45it/s] 17%|█▋ | 17/100 [00:15<00:57, 1.45it/s] 18it [00:15, 1.62it/s] 18%|█▊ | 18/100 [00:15<00:50, 1.62it/s] 19it [00:16, 1.77it/s] 19%|█▉ | 19/100 [00:16<00:45, 1.77it/s] 20it [00:16, 1.89it/s] 20%|██ | 20/100 [00:16<00:42, 1.89it/s] 21it [00:18, 1.26it/s] 21%|██ | 21/100 [00:18<01:02, 1.26it/s] 22it [00:18, 1.46it/s] 22%|██▏ | 22/100 [00:18<00:53, 1.46it/s] 23it [00:19, 1.64it/s] 23%|██▎ | 23/100 [00:19<00:47, 1.64it/s] 24it [00:19, 1.78it/s] 24%|██▍ | 24/100 [00:19<00:42, 1.78it/s] 25it [00:19, 1.90it/s] 25%|██▌ | 25/100 [00:19<00:39, 1.90it/s] 26it [00:21, 1.27it/s] 26%|██▌ | 26/100 [00:21<00:58, 1.27it/s] 27it [00:21, 1.47it/s] 27%|██▋ | 27/100 [00:21<00:49, 1.47it/s] 28it [00:22, 1.64it/s] 28%|██▊ | 28/100 [00:22<00:43, 1.64it/s] 29it [00:22, 1.79it/s] 29%|██▉ | 29/100 [00:22<00:39, 1.79it/s] 30it [00:23, 1.90it/s] 30%|███ | 30/100 [00:23<00:36, 1.90it/s] 31it [00:24, 1.27it/s] 31%|███ | 31/100 [00:24<00:54, 1.27it/s] 32it [00:24, 1.47it/s] 32%|███▏ | 32/100 [00:24<00:46, 1.47it/s] 33it [00:25, 1.65it/s] 33%|███▎ | 33/100 [00:25<00:40, 1.65it/s] 34it [00:25, 1.79it/s] 34%|███▍ | 34/100 [00:25<00:36, 1.79it/s] 35it [00:26, 1.91it/s] 35%|███▌ | 35/100 [00:26<00:34, 1.91it/s] 36it [00:27, 1.28it/s] 36%|███▌ | 36/100 [00:27<00:49, 1.28it/s] 37it [00:28, 1.48it/s] 37%|███▋ | 37/100 [00:28<00:42, 1.48it/s] 38it [00:28, 1.65it/s] 38%|███▊ | 38/100 [00:28<00:37, 1.65it/s] 39it [00:28, 1.79it/s] 39%|███▉ | 39/100 [00:28<00:34, 1.79it/s] 40it [00:29, 1.91it/s] 40%|████ | 40/100 [00:29<00:31, 1.91it/s] 41it [00:30, 1.28it/s] 41%|████ | 41/100 [00:30<00:46, 1.28it/s] 42it [00:31, 1.48it/s] 42%|████▏ | 42/100 [00:31<00:39, 1.48it/s] 43it [00:31, 1.65it/s] 43%|████▎ | 43/100 [00:31<00:34, 1.65it/s] 44it [00:32, 1.80it/s] 44%|████▍ | 44/100 [00:32<00:31, 1.80it/s] 45it [00:32, 1.92it/s] 45%|████▌ | 45/100 [00:32<00:28, 1.92it/s] 46it [00:33, 1.29it/s] 46%|████▌ | 46/100 [00:33<00:41, 1.29it/s] 47it [00:34, 1.49it/s] 47%|████▋ | 47/100 [00:34<00:35, 1.49it/s] 48it [00:34, 1.66it/s] 48%|████▊ | 48/100 [00:34<00:31, 1.66it/s] 49it [00:35, 1.80it/s] 49%|████▉ | 49/100 [00:35<00:28, 1.80it/s] 50it [00:35, 1.92it/s] 50%|█████ | 50/100 [00:35<00:26, 1.92it/s] 51it [00:37, 1.29it/s] 51%|█████ | 51/100 [00:37<00:37, 1.29it/s] 52it [00:37, 1.49it/s] 52%|█████▏ | 52/100 [00:37<00:32, 1.49it/s] 53it [00:37, 1.66it/s] 53%|█████▎ | 53/100 [00:37<00:28, 1.66it/s] 54it [00:38, 1.80it/s] 54%|█████▍ | 54/100 [00:38<00:25, 1.80it/s] 55it [00:38, 1.92it/s] 55%|█████▌ | 55/100 [00:38<00:23, 1.92it/s] 56it [00:40, 1.29it/s] 56%|█████▌ | 56/100 [00:40<00:34, 1.29it/s] 57it [00:40, 1.49it/s] 57%|█████▋ | 57/100 [00:40<00:28, 1.49it/s] 58it [00:41, 1.66it/s] 58%|█████▊ | 58/100 [00:41<00:25, 1.66it/s] 59it [00:41, 1.80it/s] 59%|█████▉ | 59/100 [00:41<00:22, 1.80it/s] 60it [00:41, 1.92it/s] 60%|██████ | 60/100 [00:41<00:20, 1.92it/s] 61it [00:43, 1.29it/s] 61%|██████ | 61/100 [00:43<00:30, 1.29it/s] 62it [00:43, 1.49it/s] 62%|██████▏ | 62/100 [00:43<00:25, 1.49it/s] 63it [00:44, 1.66it/s] 63%|██████▎ | 63/100 [00:44<00:22, 1.66it/s] 64it [00:44, 1.80it/s] 64%|██████▍ | 64/100 [00:44<00:20, 1.80it/s] 65it [00:45, 1.91it/s] 65%|██████▌ | 65/100 [00:45<00:18, 1.91it/s] 66it [00:46, 1.30it/s] 66%|██████▌ | 66/100 [00:46<00:26, 1.30it/s] 67it [00:46, 1.50it/s] 67%|██████▋ | 67/100 [00:46<00:22, 1.50it/s] 68it [00:47, 1.67it/s] 68%|██████▊ | 68/100 [00:47<00:19, 1.67it/s] 69it [00:47, 1.80it/s] 69%|██████▉ | 69/100 [00:47<00:17, 1.80it/s] 70it [00:48, 1.92it/s] 70%|███████ | 70/100 [00:48<00:15, 1.92it/s] 71it [00:49, 1.31it/s] 71%|███████ | 71/100 [00:49<00:22, 1.31it/s] 72it [00:49, 1.50it/s] 72%|███████▏ | 72/100 [00:49<00:18, 1.50it/s] 73it [00:50, 1.67it/s] 73%|███████▎ | 73/100 [00:50<00:16, 1.67it/s] 74it [00:50, 1.81it/s] 74%|███████▍ | 74/100 [00:50<00:14, 1.81it/s] 75it [00:51, 1.92it/s] 75%|███████▌ | 75/100 [00:51<00:13, 1.92it/s] 76it [00:52, 1.31it/s] 76%|███████▌ | 76/100 [00:52<00:18, 1.31it/s] 77it [00:53, 1.50it/s] 77%|███████▋ | 77/100 [00:53<00:15, 1.50it/s] 78it [00:53, 1.67it/s] 78%|███████▊ | 78/100 [00:53<00:13, 1.67it/s] 79it [00:53, 1.81it/s] 79%|███████▉ | 79/100 [00:53<00:11, 1.81it/s] 80it [00:54, 1.92it/s] 80%|████████ | 80/100 [00:54<00:10, 1.92it/s] 81it [00:55, 1.31it/s] 81%|████████ | 81/100 [00:55<00:14, 1.31it/s] 82it [00:56, 1.50it/s] 82%|████████▏ | 82/100 [00:56<00:11, 1.50it/s] 83it [00:56, 1.67it/s] 83%|████████▎ | 83/100 [00:56<00:10, 1.67it/s] 84it [00:57, 1.81it/s] 84%|████████▍ | 84/100 [00:57<00:08, 1.81it/s] 85it [00:57, 1.92it/s] 85%|████████▌ | 85/100 [00:57<00:07, 1.92it/s] 86it [00:58, 1.31it/s] 86%|████████▌ | 86/100 [00:58<00:10, 1.31it/s] 87it [00:59, 1.50it/s] 87%|████████▋ | 87/100 [00:59<00:08, 1.50it/s] 88it [00:59, 1.67it/s] 88%|████████▊ | 88/100 [00:59<00:07, 1.67it/s] 89it [01:00, 1.81it/s] 89%|████████▉ | 89/100 [01:00<00:06, 1.81it/s] 90it [01:00, 1.92it/s] 90%|█████████ | 90/100 [01:00<00:05, 1.92it/s] 91it [01:01, 1.31it/s] 91%|█████████ | 91/100 [01:01<00:06, 1.31it/s] 92it [01:02, 1.50it/s] 92%|█████████▏| 92/100 [01:02<00:05, 1.50it/s] 93it [01:02, 1.67it/s] 93%|█████████▎| 93/100 [01:02<00:04, 1.67it/s] 94it [01:03, 1.81it/s] 94%|█████████▍| 94/100 [01:03<00:03, 1.81it/s] 95it [01:03, 1.92it/s] 95%|█████████▌| 95/100 [01:03<00:02, 1.92it/s] 96it [01:05, 1.31it/s] 96%|█████████▌| 96/100 [01:05<00:03, 1.31it/s] 97it [01:05, 1.50it/s] 97%|█████████▋| 97/100 [01:05<00:01, 1.50it/s] 98it [01:05, 1.67it/s] 98%|█████████▊| 98/100 [01:05<00:01, 1.67it/s] 99it [01:06, 1.81it/s] 99%|█████████▉| 99/100 [01:06<00:00, 1.81it/s] 100it [01:06, 1.92it/s] 100%|██████████| 100/100 [01:06<00:00, 1.92it/s] 100%|██████████| 100/100 [01:06<00:00, 1.50it/s] 100it [01:06, 1.50it/s] Finished generating with seed 908426086
Prediction
laion-ai/ongo:1b3cd151IDw4nhvawnjzhe5hylgy45x5dvwyStatusSucceededSourceWebHardware–Total durationCreatedInput
- seed
- -1
- steps
- "100"
- width
- 256
- height
- 256
- prompt
- watercolor painting of a house on a hilltop at midnight with small fireflies flying around trending on artstation;
- batch_size
- "3"
- guidance_scale
- "4.5"
- aesthetic_rating
- 9
- aesthetic_weight
- 0.5
{ "seed": -1, "steps": "100", "width": 256, "height": 256, "prompt": "watercolor painting of a house on a hilltop at midnight with small fireflies flying around trending on artstation;", "batch_size": "3", "guidance_scale": "4.5", "aesthetic_rating": 9, "aesthetic_weight": 0.5 }
Install Replicate’s Node.js client library:npm install replicate
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run laion-ai/ongo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "laion-ai/ongo:1b3cd15121ec450baa71bbbdacddef9217519f12ca12ccfef36eeaa20ad89b9d", { input: { seed: -1, steps: "100", width: 256, height: 256, prompt: "watercolor painting of a house on a hilltop at midnight with small fireflies flying around trending on artstation;", batch_size: "3", guidance_scale: "4.5", aesthetic_rating: 9, aesthetic_weight: 0.5 } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the client:import replicate
Run laion-ai/ongo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "laion-ai/ongo:1b3cd15121ec450baa71bbbdacddef9217519f12ca12ccfef36eeaa20ad89b9d", input={ "seed": -1, "steps": "100", "width": 256, "height": 256, "prompt": "watercolor painting of a house on a hilltop at midnight with small fireflies flying around trending on artstation;", "batch_size": "3", "guidance_scale": "4.5", "aesthetic_rating": 9, "aesthetic_weight": 0.5 } ) # The laion-ai/ongo model can stream output as it's running. # The predict method returns an iterator, and you can iterate over that output. for item in output: # https://replicate.com/laion-ai/ongo/api#output-schema print(item)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run laion-ai/ongo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "1b3cd15121ec450baa71bbbdacddef9217519f12ca12ccfef36eeaa20ad89b9d", "input": { "seed": -1, "steps": "100", "width": 256, "height": 256, "prompt": "watercolor painting of a house on a hilltop at midnight with small fireflies flying around trending on artstation;", "batch_size": "3", "guidance_scale": "4.5", "aesthetic_rating": 9, "aesthetic_weight": 0.5 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2022-06-05T23:59:35.556541Z", "created_at": "2022-06-05T23:57:14.512653Z", "data_removed": false, "error": null, "id": "w4nhvawnjzhe5hylgy45x5dvwy", "input": { "seed": -1, "steps": "100", "width": 256, "height": 256, "prompt": "watercolor painting of a house on a hilltop at midnight with small fireflies flying around trending on artstation;", "batch_size": "3", "guidance_scale": "4.5", "aesthetic_rating": 9, "aesthetic_weight": 0.5 }, "logs": "Encoding text with BERT\nEncoding text with CLIP\nUsing aesthetic embedding 9 with weight 0.5\nLoading image\nUsing inpaint model but no image is provided. Initializing with zeros.\nPacking CLIP and BERT embeddings into kwargs\nRunning diffusion...\n\n0it [00:00, ?it/s]\n\n 0%| | 0/100 [00:00<?, ?it/s]\u001b[A\n1it [00:06, 6.19s/it]\n\n 1%| | 1/100 [00:06<10:12, 6.19s/it]\u001b[A\n2it [00:07, 3.15s/it]\n\n 2%|▏ | 2/100 [00:07<05:08, 3.15s/it]\u001b[A\n3it [00:08, 2.19s/it]\n\n 3%|▎ | 3/100 [00:08<03:31, 2.18s/it]\u001b[A\n4it [00:08, 1.43s/it]\n\n 4%|▍ | 4/100 [00:08<02:16, 1.42s/it]\u001b[A\n5it [00:08, 1.00s/it]\n\n 5%|▌ | 5/100 [00:08<01:35, 1.00s/it]\u001b[A\n6it [00:09, 1.10it/s]\n\n 6%|▌ | 6/100 [00:09<01:25, 1.10it/s]\u001b[A\n7it [00:09, 1.44it/s]\n\n 7%|▋ | 7/100 [00:09<01:04, 1.44it/s]\u001b[A\n8it [00:09, 1.80it/s]\n\n 8%|▊ | 8/100 [00:09<00:51, 1.80it/s]\u001b[A\n9it [00:10, 2.17it/s]\n\n 9%|▉ | 9/100 [00:10<00:41, 2.17it/s]\u001b[A\n10it [00:10, 2.49it/s]\n\n 10%|█ | 10/100 [00:10<00:36, 2.49it/s]\u001b[A\n11it [00:11, 1.99it/s]\n\n 11%|█ | 11/100 [00:11<00:44, 1.99it/s]\u001b[A\n12it [00:11, 2.34it/s]\n\n 12%|█▏ | 12/100 [00:11<00:37, 2.34it/s]\u001b[A\n13it [00:11, 2.66it/s]\n\n 13%|█▎ | 13/100 [00:11<00:32, 2.66it/s]\u001b[A\n14it [00:12, 2.93it/s]\n\n 14%|█▍ | 14/100 [00:12<00:29, 2.93it/s]\u001b[A\n15it [00:12, 3.11it/s]\n\n 15%|█▌ | 15/100 [00:12<00:27, 3.11it/s]\u001b[A\n16it [00:13, 2.21it/s]\n\n 16%|█▌ | 16/100 [00:13<00:37, 2.21it/s]\u001b[A\n17it [00:13, 2.55it/s]\n\n 17%|█▋ | 17/100 [00:13<00:32, 2.55it/s]\u001b[A\n18it [00:13, 2.84it/s]\n\n 18%|█▊ | 18/100 [00:13<00:28, 2.84it/s]\u001b[A\n19it [00:13, 3.08it/s]\n\n 19%|█▉ | 19/100 [00:13<00:26, 3.08it/s]\u001b[A\n20it [00:14, 3.22it/s]\n\n 20%|██ | 20/100 [00:14<00:24, 3.22it/s]\u001b[A\n21it [00:14, 2.26it/s]\n\n 21%|██ | 21/100 [00:14<00:34, 2.26it/s]\u001b[A\n22it [00:15, 2.59it/s]\n\n 22%|██▏ | 22/100 [00:15<00:30, 2.59it/s]\u001b[A\n23it [00:15, 2.87it/s]\n\n 23%|██▎ | 23/100 [00:15<00:26, 2.87it/s]\u001b[A\n24it [00:15, 3.10it/s]\n\n 24%|██▍ | 24/100 [00:15<00:24, 3.10it/s]\u001b[A\n25it [00:15, 3.19it/s]\n\n 25%|██▌ | 25/100 [00:15<00:23, 3.19it/s]\u001b[A\n26it [00:16, 2.25it/s]\n\n 26%|██▌ | 26/100 [00:16<00:32, 2.25it/s]\u001b[A\n27it [00:16, 2.58it/s]\n\n 27%|██▋ | 27/100 [00:16<00:28, 2.58it/s]\u001b[A\n28it [00:17, 2.86it/s]\n\n 28%|██▊ | 28/100 [00:17<00:25, 2.86it/s]\u001b[A\n29it [00:17, 3.08it/s]\n\n 29%|██▉ | 29/100 [00:17<00:23, 3.08it/s]\u001b[A\n30it [00:17, 3.18it/s]\n\n 30%|███ | 30/100 [00:17<00:21, 3.18it/s]\u001b[A\n31it [00:18, 2.24it/s]\n\n 31%|███ | 31/100 [00:18<00:30, 2.24it/s]\u001b[A\n32it [00:18, 2.60it/s]\n\n 32%|███▏ | 32/100 [00:18<00:26, 2.60it/s]\u001b[A\n33it [00:19, 2.87it/s]\n\n 33%|███▎ | 33/100 [00:19<00:23, 2.87it/s]\u001b[A\n34it [00:19, 3.10it/s]\n\n 34%|███▍ | 34/100 [00:19<00:21, 3.10it/s]\u001b[A\n35it [00:19, 3.16it/s]\n\n 35%|███▌ | 35/100 [00:19<00:20, 3.16it/s]\u001b[A\n36it [00:20, 2.22it/s]\n\n 36%|███▌ | 36/100 [00:20<00:28, 2.22it/s]\u001b[A\n37it [00:20, 2.54it/s]\n\n 37%|███▋ | 37/100 [00:20<00:24, 2.54it/s]\u001b[A\n38it [00:20, 2.82it/s]\n\n 38%|███▊ | 38/100 [00:20<00:22, 2.82it/s]\u001b[A\n39it [00:21, 3.04it/s]\n\n 39%|███▉ | 39/100 [00:21<00:20, 3.04it/s]\u001b[A\n40it [00:21, 3.16it/s]\n\n 40%|████ | 40/100 [00:21<00:19, 3.16it/s]\u001b[A\n41it [00:22, 2.22it/s]\n\n 41%|████ | 41/100 [00:22<00:26, 2.22it/s]\u001b[A\n42it [00:22, 2.54it/s]\n\n 42%|████▏ | 42/100 [00:22<00:22, 2.54it/s]\u001b[A\n43it [00:22, 2.82it/s]\n\n 43%|████▎ | 43/100 [00:22<00:20, 2.82it/s]\u001b[A\n44it [00:22, 3.05it/s]\n\n 44%|████▍ | 44/100 [00:22<00:18, 3.05it/s]\u001b[A\n45it [00:23, 3.16it/s]\n\n 45%|████▌ | 45/100 [00:23<00:17, 3.16it/s]\u001b[A\n46it [00:24, 2.21it/s]\n\n 46%|████▌ | 46/100 [00:24<00:24, 2.21it/s]\u001b[A\n47it [00:24, 2.53it/s]\n\n 47%|████▋ | 47/100 [00:24<00:20, 2.53it/s]\u001b[A\n48it [00:24, 2.80it/s]\n\n 48%|████▊ | 48/100 [00:24<00:18, 2.80it/s]\u001b[A\n49it [00:24, 3.02it/s]\n\n 49%|████▉ | 49/100 [00:24<00:16, 3.02it/s]\u001b[A\n50it [00:25, 3.09it/s]\n\n 50%|█████ | 50/100 [00:25<00:16, 3.09it/s]\u001b[A\n51it [00:25, 2.18it/s]\n\n 51%|█████ | 51/100 [00:25<00:22, 2.18it/s]\u001b[A\n52it [00:26, 2.50it/s]\n\n 52%|█████▏ | 52/100 [00:26<00:19, 2.50it/s]\u001b[A\n53it [00:26, 2.78it/s]\n\n 53%|█████▎ | 53/100 [00:26<00:16, 2.78it/s]\u001b[A\n54it [00:26, 3.01it/s]\n\n 54%|█████▍ | 54/100 [00:26<00:15, 3.01it/s]\u001b[A\n55it [00:27, 3.11it/s]\n\n 55%|█████▌ | 55/100 [00:27<00:14, 3.11it/s]\u001b[A\n56it [00:27, 2.20it/s]\n\n 56%|█████▌ | 56/100 [00:27<00:20, 2.20it/s]\u001b[A\n57it [00:28, 2.52it/s]\n\n 57%|█████▋ | 57/100 [00:28<00:17, 2.52it/s]\u001b[A\n58it [00:28, 2.78it/s]\n\n 58%|█████▊ | 58/100 [00:28<00:15, 2.78it/s]\u001b[A\n59it [00:28, 3.01it/s]\n\n 59%|█████▉ | 59/100 [00:28<00:13, 3.01it/s]\u001b[A\n60it [00:28, 3.12it/s]\n\n 60%|██████ | 60/100 [00:28<00:12, 3.12it/s]\u001b[A\n61it [00:29, 2.18it/s]\n\n 61%|██████ | 61/100 [00:29<00:17, 2.18it/s]\u001b[A\n62it [00:29, 2.51it/s]\n\n 62%|██████▏ | 62/100 [00:29<00:15, 2.51it/s]\u001b[A\n63it [00:30, 2.77it/s]\n\n 63%|██████▎ | 63/100 [00:30<00:13, 2.77it/s]\u001b[A\n64it [00:30, 3.00it/s]\n\n 64%|██████▍ | 64/100 [00:30<00:12, 3.00it/s]\u001b[A\n65it [00:30, 3.08it/s]\n\n 65%|██████▌ | 65/100 [00:30<00:11, 3.08it/s]\u001b[A\n66it [00:31, 2.19it/s]\n\n 66%|██████▌ | 66/100 [00:31<00:15, 2.19it/s]\u001b[A\n67it [00:31, 2.50it/s]\n\n 67%|██████▋ | 67/100 [00:31<00:13, 2.50it/s]\u001b[A\n68it [00:32, 2.76it/s]\n\n 68%|██████▊ | 68/100 [00:32<00:11, 2.76it/s]\u001b[A\n69it [00:32, 2.99it/s]\n\n 69%|██████▉ | 69/100 [00:32<00:10, 2.99it/s]\u001b[A\n70it [00:32, 3.08it/s]\n\n 70%|███████ | 70/100 [00:32<00:09, 3.08it/s]\u001b[A\n71it [00:33, 2.20it/s]\n\n 71%|███████ | 71/100 [00:33<00:13, 2.20it/s]\u001b[A\n72it [00:33, 2.52it/s]\n\n 72%|███████▏ | 72/100 [00:33<00:11, 2.52it/s]\u001b[A\n73it [00:33, 2.79it/s]\n\n 73%|███████▎ | 73/100 [00:33<00:09, 2.79it/s]\u001b[A\n74it [00:34, 3.00it/s]\n\n 74%|███████▍ | 74/100 [00:34<00:08, 3.00it/s]\u001b[A\n75it [00:34, 3.09it/s]\n\n 75%|███████▌ | 75/100 [00:34<00:08, 3.09it/s]\u001b[A\n76it [00:35, 2.21it/s]\n\n 76%|███████▌ | 76/100 [00:35<00:10, 2.21it/s]\u001b[A\n77it [00:35, 2.53it/s]\n\n 77%|███████▋ | 77/100 [00:35<00:09, 2.53it/s]\u001b[A\n78it [00:35, 2.80it/s]\n\n 78%|███████▊ | 78/100 [00:35<00:07, 2.80it/s]\u001b[A\n79it [00:36, 3.04it/s]\n\n 79%|███████▉ | 79/100 [00:36<00:06, 3.04it/s]\u001b[A\n80it [00:36, 3.12it/s]\n\n 80%|████████ | 80/100 [00:36<00:06, 3.12it/s]\u001b[A\n81it [00:37, 2.23it/s]\n\n 81%|████████ | 81/100 [00:37<00:08, 2.23it/s]\u001b[A\n82it [00:37, 2.55it/s]\n\n 82%|████████▏ | 82/100 [00:37<00:07, 2.55it/s]\u001b[A\n83it [00:37, 2.82it/s]\n\n 83%|████████▎ | 83/100 [00:37<00:06, 2.82it/s]\u001b[A\n84it [00:37, 3.04it/s]\n\n 84%|████████▍ | 84/100 [00:37<00:05, 3.04it/s]\u001b[A\n85it [00:38, 3.12it/s]\n\n 85%|████████▌ | 85/100 [00:38<00:04, 3.12it/s]\u001b[A\n86it [00:38, 2.23it/s]\n\n 86%|████████▌ | 86/100 [00:38<00:06, 2.23it/s]\u001b[A\n87it [00:39, 2.55it/s]\n\n 87%|████████▋ | 87/100 [00:39<00:05, 2.55it/s]\u001b[A\n88it [00:39, 2.82it/s]\n\n 88%|████████▊ | 88/100 [00:39<00:04, 2.82it/s]\u001b[A\n89it [00:39, 3.05it/s]\n\n 89%|████████▉ | 89/100 [00:39<00:03, 3.05it/s]\u001b[A\n90it [00:40, 3.12it/s]\n\n 90%|█████████ | 90/100 [00:40<00:03, 3.12it/s]\u001b[A\n91it [00:40, 2.25it/s]\n\n 91%|█████████ | 91/100 [00:40<00:04, 2.25it/s]\u001b[A\n92it [00:41, 2.58it/s]\n\n 92%|█████████▏| 92/100 [00:41<00:03, 2.58it/s]\u001b[A\n93it [00:41, 2.85it/s]\n\n 93%|█████████▎| 93/100 [00:41<00:02, 2.85it/s]\u001b[A\n94it [00:41, 3.09it/s]\n\n 94%|█████████▍| 94/100 [00:41<00:01, 3.09it/s]\u001b[A\n95it [00:41, 3.19it/s]\n\n 95%|█████████▌| 95/100 [00:41<00:01, 3.19it/s]\u001b[A\n96it [00:42, 2.27it/s]\n\n 96%|█████████▌| 96/100 [00:42<00:01, 2.27it/s]\u001b[A\n97it [00:42, 2.59it/s]\n\n 97%|█████████▋| 97/100 [00:42<00:01, 2.59it/s]\u001b[A\n98it [00:43, 2.87it/s]\n\n 98%|█████████▊| 98/100 [00:43<00:00, 2.87it/s]\u001b[A\n99it [00:43, 3.10it/s]\n\n 99%|█████████▉| 99/100 [00:43<00:00, 3.10it/s]\u001b[A\n100it [00:43, 3.21it/s]\n\n100%|██████████| 100/100 [00:43<00:00, 3.21it/s]\u001b[A\n100%|██████████| 100/100 [00:43<00:00, 2.29it/s]\n\n100it [00:43, 2.29it/s]\nFinished generating with seed 761263408", "metrics": { "predict_time": 107.639072, "total_time": 141.043888 }, "output": [ "https://replicate.delivery/mgxm/25e01996-ad4e-4cb3-9b46-bf3c9e469585/current.png", "https://replicate.delivery/mgxm/1c762208-cd2e-4ca0-9a5a-ca0b2fad57e0/current.png", "https://replicate.delivery/mgxm/6dbb35f3-cf60-414e-975b-3abb0377dc81/current.png", "https://replicate.delivery/mgxm/20ed0d50-0952-4dac-97ed-2861113e83d6/current.png", "https://replicate.delivery/mgxm/79335281-41c9-4c63-b038-1741323933ec/current.png", "https://replicate.delivery/mgxm/305b6eff-1504-4851-aa07-0eea94165ad4/current.png", "https://replicate.delivery/mgxm/9a7d6510-cfc8-4b16-b281-9ae55f62b283/current.png", "https://replicate.delivery/mgxm/7770af00-1057-4514-b03b-ecdf31a83c71/current.png", "https://replicate.delivery/mgxm/84ac5992-7dd9-4bad-95cf-88c6a220f87e/current.png", "https://replicate.delivery/mgxm/5b0623c8-3dd7-4627-a65f-bf27c01ffcaf/current.png", "https://replicate.delivery/mgxm/d9a3d57c-5658-432b-b9f3-03d3ec9ce7c1/current.png", "https://replicate.delivery/mgxm/cbdc8a3f-9ccf-464d-9d87-69b18e6a4426/current.png", "https://replicate.delivery/mgxm/36dec1f2-b3fc-4b97-87b2-a3431178fba7/current.png", "https://replicate.delivery/mgxm/c0662989-446a-49eb-b5f1-358e2d149d38/current.png", "https://replicate.delivery/mgxm/90f6916b-ceda-4ebb-a50b-a261fbf7a5d0/current.png", "https://replicate.delivery/mgxm/8440f427-68ad-4b37-a168-c85021b2e861/current.png", "https://replicate.delivery/mgxm/5c7cbbff-52d1-430e-a5c3-f250e8559aa2/current.png", "https://replicate.delivery/mgxm/8ed43ddc-5d7b-429b-8913-c209ae0dc091/current.png", "https://replicate.delivery/mgxm/a9f1a262-6108-48ea-88df-8565421c8843/current.png", "https://replicate.delivery/mgxm/a5dde9aa-f633-4f8b-a10d-ea483056c19d/current.png" ], "started_at": "2022-06-05T23:57:47.917469Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/w4nhvawnjzhe5hylgy45x5dvwy", "cancel": "https://api.replicate.com/v1/predictions/w4nhvawnjzhe5hylgy45x5dvwy/cancel" }, "version": "75250c24828cbecce969d755f580bd03d446649efe8635abc29fe4c152c16ed4" }
Generated inEncoding text with BERT Encoding text with CLIP Using aesthetic embedding 9 with weight 0.5 Loading image Using inpaint model but no image is provided. Initializing with zeros. Packing CLIP and BERT embeddings into kwargs Running diffusion... 0it [00:00, ?it/s] 0%| | 0/100 [00:00<?, ?it/s] 1it [00:06, 6.19s/it] 1%| | 1/100 [00:06<10:12, 6.19s/it] 2it [00:07, 3.15s/it] 2%|▏ | 2/100 [00:07<05:08, 3.15s/it] 3it [00:08, 2.19s/it] 3%|▎ | 3/100 [00:08<03:31, 2.18s/it] 4it [00:08, 1.43s/it] 4%|▍ | 4/100 [00:08<02:16, 1.42s/it] 5it [00:08, 1.00s/it] 5%|▌ | 5/100 [00:08<01:35, 1.00s/it] 6it [00:09, 1.10it/s] 6%|▌ | 6/100 [00:09<01:25, 1.10it/s] 7it [00:09, 1.44it/s] 7%|▋ | 7/100 [00:09<01:04, 1.44it/s] 8it [00:09, 1.80it/s] 8%|▊ | 8/100 [00:09<00:51, 1.80it/s] 9it [00:10, 2.17it/s] 9%|▉ | 9/100 [00:10<00:41, 2.17it/s] 10it [00:10, 2.49it/s] 10%|█ | 10/100 [00:10<00:36, 2.49it/s] 11it [00:11, 1.99it/s] 11%|█ | 11/100 [00:11<00:44, 1.99it/s] 12it [00:11, 2.34it/s] 12%|█▏ | 12/100 [00:11<00:37, 2.34it/s] 13it [00:11, 2.66it/s] 13%|█▎ | 13/100 [00:11<00:32, 2.66it/s] 14it [00:12, 2.93it/s] 14%|█▍ | 14/100 [00:12<00:29, 2.93it/s] 15it [00:12, 3.11it/s] 15%|█▌ | 15/100 [00:12<00:27, 3.11it/s] 16it [00:13, 2.21it/s] 16%|█▌ | 16/100 [00:13<00:37, 2.21it/s] 17it [00:13, 2.55it/s] 17%|█▋ | 17/100 [00:13<00:32, 2.55it/s] 18it [00:13, 2.84it/s] 18%|█▊ | 18/100 [00:13<00:28, 2.84it/s] 19it [00:13, 3.08it/s] 19%|█▉ | 19/100 [00:13<00:26, 3.08it/s] 20it [00:14, 3.22it/s] 20%|██ | 20/100 [00:14<00:24, 3.22it/s] 21it [00:14, 2.26it/s] 21%|██ | 21/100 [00:14<00:34, 2.26it/s] 22it [00:15, 2.59it/s] 22%|██▏ | 22/100 [00:15<00:30, 2.59it/s] 23it [00:15, 2.87it/s] 23%|██▎ | 23/100 [00:15<00:26, 2.87it/s] 24it [00:15, 3.10it/s] 24%|██▍ | 24/100 [00:15<00:24, 3.10it/s] 25it [00:15, 3.19it/s] 25%|██▌ | 25/100 [00:15<00:23, 3.19it/s] 26it [00:16, 2.25it/s] 26%|██▌ | 26/100 [00:16<00:32, 2.25it/s] 27it [00:16, 2.58it/s] 27%|██▋ | 27/100 [00:16<00:28, 2.58it/s] 28it [00:17, 2.86it/s] 28%|██▊ | 28/100 [00:17<00:25, 2.86it/s] 29it [00:17, 3.08it/s] 29%|██▉ | 29/100 [00:17<00:23, 3.08it/s] 30it [00:17, 3.18it/s] 30%|███ | 30/100 [00:17<00:21, 3.18it/s] 31it [00:18, 2.24it/s] 31%|███ | 31/100 [00:18<00:30, 2.24it/s] 32it [00:18, 2.60it/s] 32%|███▏ | 32/100 [00:18<00:26, 2.60it/s] 33it [00:19, 2.87it/s] 33%|███▎ | 33/100 [00:19<00:23, 2.87it/s] 34it [00:19, 3.10it/s] 34%|███▍ | 34/100 [00:19<00:21, 3.10it/s] 35it [00:19, 3.16it/s] 35%|███▌ | 35/100 [00:19<00:20, 3.16it/s] 36it [00:20, 2.22it/s] 36%|███▌ | 36/100 [00:20<00:28, 2.22it/s] 37it [00:20, 2.54it/s] 37%|███▋ | 37/100 [00:20<00:24, 2.54it/s] 38it [00:20, 2.82it/s] 38%|███▊ | 38/100 [00:20<00:22, 2.82it/s] 39it [00:21, 3.04it/s] 39%|███▉ | 39/100 [00:21<00:20, 3.04it/s] 40it [00:21, 3.16it/s] 40%|████ | 40/100 [00:21<00:19, 3.16it/s] 41it [00:22, 2.22it/s] 41%|████ | 41/100 [00:22<00:26, 2.22it/s] 42it [00:22, 2.54it/s] 42%|████▏ | 42/100 [00:22<00:22, 2.54it/s] 43it [00:22, 2.82it/s] 43%|████▎ | 43/100 [00:22<00:20, 2.82it/s] 44it [00:22, 3.05it/s] 44%|████▍ | 44/100 [00:22<00:18, 3.05it/s] 45it [00:23, 3.16it/s] 45%|████▌ | 45/100 [00:23<00:17, 3.16it/s] 46it [00:24, 2.21it/s] 46%|████▌ | 46/100 [00:24<00:24, 2.21it/s] 47it [00:24, 2.53it/s] 47%|████▋ | 47/100 [00:24<00:20, 2.53it/s] 48it [00:24, 2.80it/s] 48%|████▊ | 48/100 [00:24<00:18, 2.80it/s] 49it [00:24, 3.02it/s] 49%|████▉ | 49/100 [00:24<00:16, 3.02it/s] 50it [00:25, 3.09it/s] 50%|█████ | 50/100 [00:25<00:16, 3.09it/s] 51it [00:25, 2.18it/s] 51%|█████ | 51/100 [00:25<00:22, 2.18it/s] 52it [00:26, 2.50it/s] 52%|█████▏ | 52/100 [00:26<00:19, 2.50it/s] 53it [00:26, 2.78it/s] 53%|█████▎ | 53/100 [00:26<00:16, 2.78it/s] 54it [00:26, 3.01it/s] 54%|█████▍ | 54/100 [00:26<00:15, 3.01it/s] 55it [00:27, 3.11it/s] 55%|█████▌ | 55/100 [00:27<00:14, 3.11it/s] 56it [00:27, 2.20it/s] 56%|█████▌ | 56/100 [00:27<00:20, 2.20it/s] 57it [00:28, 2.52it/s] 57%|█████▋ | 57/100 [00:28<00:17, 2.52it/s] 58it [00:28, 2.78it/s] 58%|█████▊ | 58/100 [00:28<00:15, 2.78it/s] 59it [00:28, 3.01it/s] 59%|█████▉ | 59/100 [00:28<00:13, 3.01it/s] 60it [00:28, 3.12it/s] 60%|██████ | 60/100 [00:28<00:12, 3.12it/s] 61it [00:29, 2.18it/s] 61%|██████ | 61/100 [00:29<00:17, 2.18it/s] 62it [00:29, 2.51it/s] 62%|██████▏ | 62/100 [00:29<00:15, 2.51it/s] 63it [00:30, 2.77it/s] 63%|██████▎ | 63/100 [00:30<00:13, 2.77it/s] 64it [00:30, 3.00it/s] 64%|██████▍ | 64/100 [00:30<00:12, 3.00it/s] 65it [00:30, 3.08it/s] 65%|██████▌ | 65/100 [00:30<00:11, 3.08it/s] 66it [00:31, 2.19it/s] 66%|██████▌ | 66/100 [00:31<00:15, 2.19it/s] 67it [00:31, 2.50it/s] 67%|██████▋ | 67/100 [00:31<00:13, 2.50it/s] 68it [00:32, 2.76it/s] 68%|██████▊ | 68/100 [00:32<00:11, 2.76it/s] 69it [00:32, 2.99it/s] 69%|██████▉ | 69/100 [00:32<00:10, 2.99it/s] 70it [00:32, 3.08it/s] 70%|███████ | 70/100 [00:32<00:09, 3.08it/s] 71it [00:33, 2.20it/s] 71%|███████ | 71/100 [00:33<00:13, 2.20it/s] 72it [00:33, 2.52it/s] 72%|███████▏ | 72/100 [00:33<00:11, 2.52it/s] 73it [00:33, 2.79it/s] 73%|███████▎ | 73/100 [00:33<00:09, 2.79it/s] 74it [00:34, 3.00it/s] 74%|███████▍ | 74/100 [00:34<00:08, 3.00it/s] 75it [00:34, 3.09it/s] 75%|███████▌ | 75/100 [00:34<00:08, 3.09it/s] 76it [00:35, 2.21it/s] 76%|███████▌ | 76/100 [00:35<00:10, 2.21it/s] 77it [00:35, 2.53it/s] 77%|███████▋ | 77/100 [00:35<00:09, 2.53it/s] 78it [00:35, 2.80it/s] 78%|███████▊ | 78/100 [00:35<00:07, 2.80it/s] 79it [00:36, 3.04it/s] 79%|███████▉ | 79/100 [00:36<00:06, 3.04it/s] 80it [00:36, 3.12it/s] 80%|████████ | 80/100 [00:36<00:06, 3.12it/s] 81it [00:37, 2.23it/s] 81%|████████ | 81/100 [00:37<00:08, 2.23it/s] 82it [00:37, 2.55it/s] 82%|████████▏ | 82/100 [00:37<00:07, 2.55it/s] 83it [00:37, 2.82it/s] 83%|████████▎ | 83/100 [00:37<00:06, 2.82it/s] 84it [00:37, 3.04it/s] 84%|████████▍ | 84/100 [00:37<00:05, 3.04it/s] 85it [00:38, 3.12it/s] 85%|████████▌ | 85/100 [00:38<00:04, 3.12it/s] 86it [00:38, 2.23it/s] 86%|████████▌ | 86/100 [00:38<00:06, 2.23it/s] 87it [00:39, 2.55it/s] 87%|████████▋ | 87/100 [00:39<00:05, 2.55it/s] 88it [00:39, 2.82it/s] 88%|████████▊ | 88/100 [00:39<00:04, 2.82it/s] 89it [00:39, 3.05it/s] 89%|████████▉ | 89/100 [00:39<00:03, 3.05it/s] 90it [00:40, 3.12it/s] 90%|█████████ | 90/100 [00:40<00:03, 3.12it/s] 91it [00:40, 2.25it/s] 91%|█████████ | 91/100 [00:40<00:04, 2.25it/s] 92it [00:41, 2.58it/s] 92%|█████████▏| 92/100 [00:41<00:03, 2.58it/s] 93it [00:41, 2.85it/s] 93%|█████████▎| 93/100 [00:41<00:02, 2.85it/s] 94it [00:41, 3.09it/s] 94%|█████████▍| 94/100 [00:41<00:01, 3.09it/s] 95it [00:41, 3.19it/s] 95%|█████████▌| 95/100 [00:41<00:01, 3.19it/s] 96it [00:42, 2.27it/s] 96%|█████████▌| 96/100 [00:42<00:01, 2.27it/s] 97it [00:42, 2.59it/s] 97%|█████████▋| 97/100 [00:42<00:01, 2.59it/s] 98it [00:43, 2.87it/s] 98%|█████████▊| 98/100 [00:43<00:00, 2.87it/s] 99it [00:43, 3.10it/s] 99%|█████████▉| 99/100 [00:43<00:00, 3.10it/s] 100it [00:43, 3.21it/s] 100%|██████████| 100/100 [00:43<00:00, 3.21it/s] 100%|██████████| 100/100 [00:43<00:00, 2.29it/s] 100it [00:43, 2.29it/s] Finished generating with seed 761263408
Prediction
laion-ai/ongo:1b3cd151IDrb2x665mgnhbhcharj7qghj2hiStatusSucceededSourceWebHardware–Total durationCreatedInput
- seed
- -1
- steps
- "100"
- width
- 256
- height
- 256
- prompt
- a farmhouse surrounded by flowers painting
- batch_size
- "3"
- guidance_scale
- 5
- aesthetic_rating
- 8
- aesthetic_weight
- 0.1
{ "seed": -1, "steps": "100", "width": 256, "height": 256, "prompt": "a farmhouse surrounded by flowers painting", "batch_size": "3", "guidance_scale": 5, "aesthetic_rating": 8, "aesthetic_weight": 0.1 }
Install Replicate’s Node.js client library:npm install replicate
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run laion-ai/ongo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "laion-ai/ongo:1b3cd15121ec450baa71bbbdacddef9217519f12ca12ccfef36eeaa20ad89b9d", { input: { seed: -1, steps: "100", width: 256, height: 256, prompt: "a farmhouse surrounded by flowers painting", batch_size: "3", guidance_scale: 5, aesthetic_rating: 8, aesthetic_weight: 0.1 } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the client:import replicate
Run laion-ai/ongo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "laion-ai/ongo:1b3cd15121ec450baa71bbbdacddef9217519f12ca12ccfef36eeaa20ad89b9d", input={ "seed": -1, "steps": "100", "width": 256, "height": 256, "prompt": "a farmhouse surrounded by flowers painting", "batch_size": "3", "guidance_scale": 5, "aesthetic_rating": 8, "aesthetic_weight": 0.1 } ) # The laion-ai/ongo model can stream output as it's running. # The predict method returns an iterator, and you can iterate over that output. for item in output: # https://replicate.com/laion-ai/ongo/api#output-schema print(item)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run laion-ai/ongo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "1b3cd15121ec450baa71bbbdacddef9217519f12ca12ccfef36eeaa20ad89b9d", "input": { "seed": -1, "steps": "100", "width": 256, "height": 256, "prompt": "a farmhouse surrounded by flowers painting", "batch_size": "3", "guidance_scale": 5, "aesthetic_rating": 8, "aesthetic_weight": 0.1 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2022-06-24T23:03:28.506987Z", "created_at": "2022-06-24T22:58:39.598232Z", "data_removed": false, "error": null, "id": "rb2x665mgnhbhcharj7qghj2hi", "input": { "seed": -1, "steps": "100", "width": 256, "height": 256, "prompt": "a farmhouse surrounded by flowers painting", "batch_size": "3", "guidance_scale": 5, "aesthetic_rating": 8, "aesthetic_weight": 0.1 }, "logs": "Using seed 1707536065\nRunning simulation for a farmhouse surrounded by flowers painting\nEncoding text embeddings with a farmhouse surrounded by flowers painting dimensions\nUsing aesthetic embedding 8 with weight 0.1\nUsing inpaint model but no image is provided. Initializing with zeros.\nRunning diffusion...\n\n0it [00:00, ?it/s]\n\nTimestep 0 - saving sample\n 0%| | 0/100 [00:00<?, ?it/s]\u001b[A\n1it [00:02, 2.14s/it]\n\n 1%| | 1/100 [00:02<03:31, 2.14s/it]\u001b[A\n2it [00:03, 1.83s/it]\n\n 2%|▏ | 2/100 [00:03<02:59, 1.83s/it]\u001b[A\n3it [00:05, 1.74s/it]\n\n 3%|▎ | 3/100 [00:05<02:48, 1.74s/it]\u001b[A\n4it [00:05, 1.21s/it]\n\n 4%|▍ | 4/100 [00:05<01:56, 1.21s/it]\u001b[A\n5it [00:06, 1.08it/s]\n\n 5%|▌ | 5/100 [00:06<01:27, 1.08it/s]\u001b[A\n6it [00:06, 1.34it/s]\n\n 6%|▌ | 6/100 [00:06<01:10, 1.34it/s]\u001b[A\n7it [00:07, 1.57it/s]\n\n 7%|▋ | 7/100 [00:07<00:59, 1.57it/s]\u001b[A\n8it [00:07, 1.77it/s]\n\n 8%|▊ | 8/100 [00:07<00:51, 1.77it/s]\u001b[A\n9it [00:07, 1.94it/s]\n\n 9%|▉ | 9/100 [00:07<00:46, 1.94it/s]\u001b[A\n10it [00:08, 2.07it/s]\n\nTimestep 10 - saving sample\n 10%|█ | 10/100 [00:08<00:43, 2.07it/s]\u001b[A\n11it [00:08, 1.77it/s]\n\n 11%|█ | 11/100 [00:08<00:50, 1.77it/s]\u001b[A\n12it [00:09, 1.94it/s]\n\n 12%|█▏ | 12/100 [00:09<00:45, 1.94it/s]\u001b[A\n13it [00:09, 2.07it/s]\n\n 13%|█▎ | 13/100 [00:09<00:42, 2.07it/s]\u001b[A\n14it [00:10, 2.17it/s]\n\n 14%|█▍ | 14/100 [00:10<00:39, 2.17it/s]\u001b[A\n15it [00:10, 2.24it/s]\n\n 15%|█▌ | 15/100 [00:10<00:37, 2.24it/s]\u001b[A\n16it [00:11, 2.30it/s]\n\n 16%|█▌ | 16/100 [00:11<00:36, 2.30it/s]\u001b[A\n17it [00:11, 2.34it/s]\n\n 17%|█▋ | 17/100 [00:11<00:35, 2.34it/s]\u001b[A\n18it [00:11, 2.37it/s]\n\n 18%|█▊ | 18/100 [00:11<00:34, 2.37it/s]\u001b[A\n19it [00:12, 2.39it/s]\n\n 19%|█▉ | 19/100 [00:12<00:33, 2.39it/s]\u001b[A\n20it [00:12, 2.41it/s]\n\nTimestep 20 - saving sample\n 20%|██ | 20/100 [00:12<00:33, 2.41it/s]\u001b[A\n21it [00:13, 1.92it/s]\n\n 21%|██ | 21/100 [00:13<00:41, 1.93it/s]\u001b[A\n22it [00:13, 2.06it/s]\n\n 22%|██▏ | 22/100 [00:13<00:37, 2.06it/s]\u001b[A\n23it [00:14, 2.16it/s]\n\n 23%|██▎ | 23/100 [00:14<00:35, 2.16it/s]\u001b[A\n24it [00:14, 2.24it/s]\n\n 24%|██▍ | 24/100 [00:14<00:33, 2.24it/s]\u001b[A\n25it [00:15, 2.29it/s]\n\n 25%|██▌ | 25/100 [00:15<00:32, 2.29it/s]\u001b[A\n26it [00:15, 2.33it/s]\n\n 26%|██▌ | 26/100 [00:15<00:31, 2.33it/s]\u001b[A\n27it [00:15, 2.36it/s]\n\n 27%|██▋ | 27/100 [00:15<00:30, 2.36it/s]\u001b[A\n28it [00:16, 2.38it/s]\n\n 28%|██▊ | 28/100 [00:16<00:30, 2.38it/s]\u001b[A\n29it [00:16, 2.39it/s]\n\n 29%|██▉ | 29/100 [00:16<00:29, 2.39it/s]\u001b[A\n30it [00:17, 2.41it/s]\n\nTimestep 30 - saving sample\n 30%|███ | 30/100 [00:17<00:29, 2.41it/s]\u001b[A\n31it [00:17, 1.93it/s]\n\n 31%|███ | 31/100 [00:17<00:35, 1.93it/s]\u001b[A\n32it [00:18, 2.06it/s]\n\n 32%|███▏ | 32/100 [00:18<00:33, 2.06it/s]\u001b[A\n33it [00:18, 2.16it/s]\n\n 33%|███▎ | 33/100 [00:18<00:31, 2.16it/s]\u001b[A\n34it [00:19, 2.22it/s]\n\n 34%|███▍ | 34/100 [00:19<00:29, 2.22it/s]\u001b[A\n35it [00:19, 2.28it/s]\n\n 35%|███▌ | 35/100 [00:19<00:28, 2.28it/s]\u001b[A\n36it [00:19, 2.31it/s]\n\n 36%|███▌ | 36/100 [00:19<00:27, 2.31it/s]\u001b[A\n37it [00:20, 2.34it/s]\n\n 37%|███▋ | 37/100 [00:20<00:26, 2.34it/s]\u001b[A\n38it [00:20, 2.35it/s]\n\n 38%|███▊ | 38/100 [00:20<00:26, 2.35it/s]\u001b[A\n39it [00:21, 2.38it/s]\n\n 39%|███▉ | 39/100 [00:21<00:25, 2.38it/s]\u001b[A\n40it [00:21, 2.38it/s]\n\nTimestep 40 - saving sample\n 40%|████ | 40/100 [00:21<00:25, 2.38it/s]\u001b[A\n41it [00:22, 1.91it/s]\n\n 41%|████ | 41/100 [00:22<00:30, 1.91it/s]\u001b[A\n42it [00:22, 2.04it/s]\n\n 42%|████▏ | 42/100 [00:22<00:28, 2.04it/s]\u001b[A\n43it [00:23, 2.13it/s]\n\n 43%|████▎ | 43/100 [00:23<00:26, 2.13it/s]\u001b[A\n44it [00:23, 2.21it/s]\n\n 44%|████▍ | 44/100 [00:23<00:25, 2.21it/s]\u001b[A\n45it [00:24, 2.26it/s]\n\n 45%|████▌ | 45/100 [00:24<00:24, 2.26it/s]\u001b[A\n46it [00:24, 2.31it/s]\n\n 46%|████▌ | 46/100 [00:24<00:23, 2.31it/s]\u001b[A\n47it [00:24, 2.33it/s]\n\n 47%|████▋ | 47/100 [00:24<00:22, 2.33it/s]\u001b[A\n48it [00:25, 2.35it/s]\n\n 48%|████▊ | 48/100 [00:25<00:22, 2.35it/s]\u001b[A\n49it [00:25, 2.37it/s]\n\n 49%|████▉ | 49/100 [00:25<00:21, 2.37it/s]\u001b[A\n50it [00:26, 2.37it/s]\n\nTimestep 50 - saving sample\n 50%|█████ | 50/100 [00:26<00:21, 2.37it/s]\u001b[A\n51it [00:26, 1.90it/s]\n\n 51%|█████ | 51/100 [00:26<00:25, 1.90it/s]\u001b[A\n52it [00:27, 2.03it/s]\n\n 52%|█████▏ | 52/100 [00:27<00:23, 2.03it/s]\u001b[A\n53it [00:27, 2.12it/s]\n\n 53%|█████▎ | 53/100 [00:27<00:22, 2.12it/s]\u001b[A\n54it [00:28, 2.19it/s]\n\n 54%|█████▍ | 54/100 [00:28<00:21, 2.19it/s]\u001b[A\n55it [00:28, 2.25it/s]\n\n 55%|█████▌ | 55/100 [00:28<00:19, 2.25it/s]\u001b[A\n56it [00:29, 2.29it/s]\n\n 56%|█████▌ | 56/100 [00:28<00:19, 2.29it/s]\u001b[A\n57it [00:29, 2.31it/s]\n\n 57%|█████▋ | 57/100 [00:29<00:18, 2.31it/s]\u001b[A\n58it [00:29, 2.34it/s]\n\n 58%|█████▊ | 58/100 [00:29<00:17, 2.34it/s]\u001b[A\n59it [00:30, 2.35it/s]\n\n 59%|█████▉ | 59/100 [00:30<00:17, 2.35it/s]\u001b[A\n60it [00:30, 2.35it/s]\n\nTimestep 60 - saving sample\n 60%|██████ | 60/100 [00:30<00:16, 2.35it/s]\u001b[A\n61it [00:31, 1.89it/s]\n\n 61%|██████ | 61/100 [00:31<00:20, 1.89it/s]\u001b[A\n62it [00:31, 2.02it/s]\n\n 62%|██████▏ | 62/100 [00:31<00:18, 2.01it/s]\u001b[A\n63it [00:32, 2.11it/s]\n\n 63%|██████▎ | 63/100 [00:32<00:17, 2.11it/s]\u001b[A\n64it [00:32, 2.19it/s]\n\n 64%|██████▍ | 64/100 [00:32<00:16, 2.19it/s]\u001b[A\n65it [00:33, 2.23it/s]\n\n 65%|██████▌ | 65/100 [00:33<00:15, 2.23it/s]\u001b[A\n66it [00:33, 2.27it/s]\n\n 66%|██████▌ | 66/100 [00:33<00:14, 2.27it/s]\u001b[A\n67it [00:33, 2.29it/s]\n\n 67%|██████▋ | 67/100 [00:33<00:14, 2.29it/s]\u001b[A\n68it [00:34, 2.31it/s]\n\n 68%|██████▊ | 68/100 [00:34<00:13, 2.31it/s]\u001b[A\n69it [00:34, 2.32it/s]\n\n 69%|██████▉ | 69/100 [00:34<00:13, 2.32it/s]\u001b[A\n70it [00:35, 2.33it/s]\n\nTimestep 70 - saving sample\n 70%|███████ | 70/100 [00:35<00:12, 2.33it/s]\u001b[A\n71it [00:36, 1.88it/s]\n\n 71%|███████ | 71/100 [00:36<00:15, 1.88it/s]\u001b[A\n72it [00:36, 2.01it/s]\n\n 72%|███████▏ | 72/100 [00:36<00:13, 2.01it/s]\u001b[A\n73it [00:36, 2.10it/s]\n\n 73%|███████▎ | 73/100 [00:36<00:12, 2.10it/s]\u001b[A\n74it [00:37, 2.18it/s]\n\n 74%|███████▍ | 74/100 [00:37<00:11, 2.18it/s]\u001b[A\n75it [00:37, 2.23it/s]\n\n 75%|███████▌ | 75/100 [00:37<00:11, 2.23it/s]\u001b[A\n76it [00:38, 2.27it/s]\n\n 76%|███████▌ | 76/100 [00:38<00:10, 2.27it/s]\u001b[A\n77it [00:38, 2.30it/s]\n\n 77%|███████▋ | 77/100 [00:38<00:09, 2.30it/s]\u001b[A\n78it [00:38, 2.32it/s]\n\n 78%|███████▊ | 78/100 [00:38<00:09, 2.32it/s]\u001b[A\n79it [00:39, 2.33it/s]\n\n 79%|███████▉ | 79/100 [00:39<00:09, 2.33it/s]\u001b[A\n80it [00:39, 2.34it/s]\n\nTimestep 80 - saving sample\n 80%|████████ | 80/100 [00:39<00:08, 2.34it/s]\u001b[A\n81it [00:40, 1.87it/s]\n\n 81%|████████ | 81/100 [00:40<00:10, 1.87it/s]\u001b[A\n82it [00:41, 2.00it/s]\n\n 82%|████████▏ | 82/100 [00:41<00:08, 2.00it/s]\u001b[A\n83it [00:41, 2.10it/s]\n\n 83%|████████▎ | 83/100 [00:41<00:08, 2.10it/s]\u001b[A\n84it [00:41, 2.17it/s]\n\n 84%|████████▍ | 84/100 [00:41<00:07, 2.17it/s]\u001b[A\n85it [00:42, 2.22it/s]\n\n 85%|████████▌ | 85/100 [00:42<00:06, 2.22it/s]\u001b[A\n86it [00:42, 2.26it/s]\n\n 86%|████████▌ | 86/100 [00:42<00:06, 2.26it/s]\u001b[A\n87it [00:43, 2.29it/s]\n\n 87%|████████▋ | 87/100 [00:43<00:05, 2.29it/s]\u001b[A\n88it [00:43, 2.30it/s]\n\n 88%|████████▊ | 88/100 [00:43<00:05, 2.30it/s]\u001b[A\n89it [00:44, 2.32it/s]\n\n 89%|████████▉ | 89/100 [00:44<00:04, 2.32it/s]\u001b[A\n90it [00:44, 2.33it/s]\n\nTimestep 90 - saving sample\n 90%|█████████ | 90/100 [00:44<00:04, 2.33it/s]\u001b[A\n91it [00:45, 1.86it/s]\n\n 91%|█████████ | 91/100 [00:45<00:04, 1.86it/s]\u001b[A\n92it [00:45, 1.98it/s]\n\n 92%|█████████▏| 92/100 [00:45<00:04, 1.98it/s]\u001b[A\n93it [00:46, 2.08it/s]\n\n 93%|█████████▎| 93/100 [00:46<00:03, 2.08it/s]\u001b[A\n94it [00:46, 2.15it/s]\n\n 94%|█████████▍| 94/100 [00:46<00:02, 2.15it/s]\u001b[A\n95it [00:46, 2.21it/s]\n\n 95%|█████████▌| 95/100 [00:46<00:02, 2.21it/s]\u001b[A\n96it [00:47, 2.24it/s]\n\n 96%|█████████▌| 96/100 [00:47<00:01, 2.24it/s]\u001b[A\n97it [00:47, 2.27it/s]\n\n 97%|█████████▋| 97/100 [00:47<00:01, 2.27it/s]\u001b[A\n98it [00:48, 2.28it/s]\n\n 98%|█████████▊| 98/100 [00:48<00:00, 2.28it/s]\u001b[A\n99it [00:48, 2.30it/s]\n\nTimestep 99 - saving final sample\n 99%|█████████▉| 99/100 [00:48<00:00, 2.30it/s]\u001b[A\n100it [00:49, 1.84it/s]\n\n100%|██████████| 100/100 [00:49<00:00, 1.84it/s]\u001b[A\n100%|██████████| 100/100 [00:49<00:00, 2.02it/s]\n\n100it [00:49, 2.02it/s]", "metrics": { "predict_time": 53.279104, "total_time": 288.908755 }, "output": [ [ "https://replicate.delivery/mgxm/77d25ac9-16e8-4d9e-b615-430d1a66da3f/current_0.jpg", "https://replicate.delivery/mgxm/41eda1d3-d8a8-4b5d-b401-d01152ec516a/current_1.jpg", "https://replicate.delivery/mgxm/865418cb-b702-43c1-8804-0eb62e2db870/current_2.jpg" ], [ "https://replicate.delivery/mgxm/4454f98c-665c-43b9-874a-9c3543e0e00c/current_0.jpg", "https://replicate.delivery/mgxm/3d0adec3-5ab7-4cde-84cd-c6f054a774ad/current_1.jpg", "https://replicate.delivery/mgxm/f4dee2b0-0ec3-4b84-9188-fe5912b6b0bd/current_2.jpg" ], [ "https://replicate.delivery/mgxm/466dc877-ea75-44fd-95ef-b03e33e9a1d5/current_0.jpg", "https://replicate.delivery/mgxm/4d04dd88-77e7-4f23-829b-4a160a05efb6/current_1.jpg", "https://replicate.delivery/mgxm/20cb5dcd-309a-48e0-bf20-1c5334d1a796/current_2.jpg" ], [ "https://replicate.delivery/mgxm/456d7c14-207a-41f8-848b-58ce9fbe9b32/current_0.jpg", "https://replicate.delivery/mgxm/206b44cb-9bf2-45c6-9316-e9068c9da4f1/current_1.jpg", "https://replicate.delivery/mgxm/1190cadd-8ba6-4f41-b770-84059294c025/current_2.jpg" ], [ "https://replicate.delivery/mgxm/6e1b5c8d-5025-4a32-a092-637a44d5fb84/current_0.jpg", "https://replicate.delivery/mgxm/babbe018-20c3-49a8-9429-ca4d27d6218b/current_1.jpg", "https://replicate.delivery/mgxm/fadb13a0-f8f6-4c08-b9ad-5a42405367e7/current_2.jpg" ], [ "https://replicate.delivery/mgxm/5abfe9de-7fd4-4da7-9beb-c46860434265/current_0.jpg", "https://replicate.delivery/mgxm/5ab95e17-7ab0-435d-8d64-173095d67950/current_1.jpg", "https://replicate.delivery/mgxm/730deee1-a4f5-44a0-a1b7-0c09063c456f/current_2.jpg" ], [ "https://replicate.delivery/mgxm/f79eca14-d0b2-48e6-a4d6-dad962f9b168/current_0.jpg", "https://replicate.delivery/mgxm/97172e01-8e89-4273-9339-8f5f3cae1df4/current_1.jpg", "https://replicate.delivery/mgxm/1892ea14-3cad-494d-a4c8-81b7a436407d/current_2.jpg" ], [ "https://replicate.delivery/mgxm/a170b9e3-36e1-45ed-b966-35ad9d14b2f4/current_0.jpg", "https://replicate.delivery/mgxm/e64f94a1-3765-4e52-9673-53510282e49c/current_1.jpg", "https://replicate.delivery/mgxm/32e201f0-7d30-4616-902a-e319c7055b8b/current_2.jpg" ], [ "https://replicate.delivery/mgxm/6a8b77c0-38e3-4d0d-8c37-afb22dea6141/current_0.jpg", "https://replicate.delivery/mgxm/83be8526-3f02-4ebc-87b1-ea39134748fb/current_1.jpg", "https://replicate.delivery/mgxm/229172dc-b07d-43f5-95e7-23a6798faa20/current_2.jpg" ], [ "https://replicate.delivery/mgxm/346d6f62-2775-40d2-92e7-74ec87cbda7b/current_0.jpg", "https://replicate.delivery/mgxm/904b820c-5824-4efc-9787-6ca565dc28a6/current_1.jpg", "https://replicate.delivery/mgxm/fffa41c0-1428-4df4-970e-8f6b341a7e71/current_2.jpg" ], [ "https://replicate.delivery/mgxm/92c96915-8ca9-4f5a-bfe1-eccf85675ee4/current_0.jpg", "https://replicate.delivery/mgxm/f3dc9303-6658-4729-b483-fb90ee13cee2/current_1.jpg", "https://replicate.delivery/mgxm/f307c9c7-0b82-4789-a880-cb9245c271ac/current_2.jpg" ] ], "started_at": "2022-06-24T23:02:35.227883Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/rb2x665mgnhbhcharj7qghj2hi", "cancel": "https://api.replicate.com/v1/predictions/rb2x665mgnhbhcharj7qghj2hi/cancel" }, "version": "41ad32228705648d785fc33be19d98dfa058cfd59d1f9a7c2248757e3652cdf6" }
Generated inUsing seed 1707536065 Running simulation for a farmhouse surrounded by flowers painting Encoding text embeddings with a farmhouse surrounded by flowers painting dimensions Using aesthetic embedding 8 with weight 0.1 Using inpaint model but no image is provided. Initializing with zeros. Running diffusion... 0it [00:00, ?it/s] Timestep 0 - saving sample 0%| | 0/100 [00:00<?, ?it/s] 1it [00:02, 2.14s/it] 1%| | 1/100 [00:02<03:31, 2.14s/it] 2it [00:03, 1.83s/it] 2%|▏ | 2/100 [00:03<02:59, 1.83s/it] 3it [00:05, 1.74s/it] 3%|▎ | 3/100 [00:05<02:48, 1.74s/it] 4it [00:05, 1.21s/it] 4%|▍ | 4/100 [00:05<01:56, 1.21s/it] 5it [00:06, 1.08it/s] 5%|▌ | 5/100 [00:06<01:27, 1.08it/s] 6it [00:06, 1.34it/s] 6%|▌ | 6/100 [00:06<01:10, 1.34it/s] 7it [00:07, 1.57it/s] 7%|▋ | 7/100 [00:07<00:59, 1.57it/s] 8it [00:07, 1.77it/s] 8%|▊ | 8/100 [00:07<00:51, 1.77it/s] 9it [00:07, 1.94it/s] 9%|▉ | 9/100 [00:07<00:46, 1.94it/s] 10it [00:08, 2.07it/s] Timestep 10 - saving sample 10%|█ | 10/100 [00:08<00:43, 2.07it/s] 11it [00:08, 1.77it/s] 11%|█ | 11/100 [00:08<00:50, 1.77it/s] 12it [00:09, 1.94it/s] 12%|█▏ | 12/100 [00:09<00:45, 1.94it/s] 13it [00:09, 2.07it/s] 13%|█▎ | 13/100 [00:09<00:42, 2.07it/s] 14it [00:10, 2.17it/s] 14%|█▍ | 14/100 [00:10<00:39, 2.17it/s] 15it [00:10, 2.24it/s] 15%|█▌ | 15/100 [00:10<00:37, 2.24it/s] 16it [00:11, 2.30it/s] 16%|█▌ | 16/100 [00:11<00:36, 2.30it/s] 17it [00:11, 2.34it/s] 17%|█▋ | 17/100 [00:11<00:35, 2.34it/s] 18it [00:11, 2.37it/s] 18%|█▊ | 18/100 [00:11<00:34, 2.37it/s] 19it [00:12, 2.39it/s] 19%|█▉ | 19/100 [00:12<00:33, 2.39it/s] 20it [00:12, 2.41it/s] Timestep 20 - saving sample 20%|██ | 20/100 [00:12<00:33, 2.41it/s] 21it [00:13, 1.92it/s] 21%|██ | 21/100 [00:13<00:41, 1.93it/s] 22it [00:13, 2.06it/s] 22%|██▏ | 22/100 [00:13<00:37, 2.06it/s] 23it [00:14, 2.16it/s] 23%|██▎ | 23/100 [00:14<00:35, 2.16it/s] 24it [00:14, 2.24it/s] 24%|██▍ | 24/100 [00:14<00:33, 2.24it/s] 25it [00:15, 2.29it/s] 25%|██▌ | 25/100 [00:15<00:32, 2.29it/s] 26it [00:15, 2.33it/s] 26%|██▌ | 26/100 [00:15<00:31, 2.33it/s] 27it [00:15, 2.36it/s] 27%|██▋ | 27/100 [00:15<00:30, 2.36it/s] 28it [00:16, 2.38it/s] 28%|██▊ | 28/100 [00:16<00:30, 2.38it/s] 29it [00:16, 2.39it/s] 29%|██▉ | 29/100 [00:16<00:29, 2.39it/s] 30it [00:17, 2.41it/s] Timestep 30 - saving sample 30%|███ | 30/100 [00:17<00:29, 2.41it/s] 31it [00:17, 1.93it/s] 31%|███ | 31/100 [00:17<00:35, 1.93it/s] 32it [00:18, 2.06it/s] 32%|███▏ | 32/100 [00:18<00:33, 2.06it/s] 33it [00:18, 2.16it/s] 33%|███▎ | 33/100 [00:18<00:31, 2.16it/s] 34it [00:19, 2.22it/s] 34%|███▍ | 34/100 [00:19<00:29, 2.22it/s] 35it [00:19, 2.28it/s] 35%|███▌ | 35/100 [00:19<00:28, 2.28it/s] 36it [00:19, 2.31it/s] 36%|███▌ | 36/100 [00:19<00:27, 2.31it/s] 37it [00:20, 2.34it/s] 37%|███▋ | 37/100 [00:20<00:26, 2.34it/s] 38it [00:20, 2.35it/s] 38%|███▊ | 38/100 [00:20<00:26, 2.35it/s] 39it [00:21, 2.38it/s] 39%|███▉ | 39/100 [00:21<00:25, 2.38it/s] 40it [00:21, 2.38it/s] Timestep 40 - saving sample 40%|████ | 40/100 [00:21<00:25, 2.38it/s] 41it [00:22, 1.91it/s] 41%|████ | 41/100 [00:22<00:30, 1.91it/s] 42it [00:22, 2.04it/s] 42%|████▏ | 42/100 [00:22<00:28, 2.04it/s] 43it [00:23, 2.13it/s] 43%|████▎ | 43/100 [00:23<00:26, 2.13it/s] 44it [00:23, 2.21it/s] 44%|████▍ | 44/100 [00:23<00:25, 2.21it/s] 45it [00:24, 2.26it/s] 45%|████▌ | 45/100 [00:24<00:24, 2.26it/s] 46it [00:24, 2.31it/s] 46%|████▌ | 46/100 [00:24<00:23, 2.31it/s] 47it [00:24, 2.33it/s] 47%|████▋ | 47/100 [00:24<00:22, 2.33it/s] 48it [00:25, 2.35it/s] 48%|████▊ | 48/100 [00:25<00:22, 2.35it/s] 49it [00:25, 2.37it/s] 49%|████▉ | 49/100 [00:25<00:21, 2.37it/s] 50it [00:26, 2.37it/s] Timestep 50 - saving sample 50%|█████ | 50/100 [00:26<00:21, 2.37it/s] 51it [00:26, 1.90it/s] 51%|█████ | 51/100 [00:26<00:25, 1.90it/s] 52it [00:27, 2.03it/s] 52%|█████▏ | 52/100 [00:27<00:23, 2.03it/s] 53it [00:27, 2.12it/s] 53%|█████▎ | 53/100 [00:27<00:22, 2.12it/s] 54it [00:28, 2.19it/s] 54%|█████▍ | 54/100 [00:28<00:21, 2.19it/s] 55it [00:28, 2.25it/s] 55%|█████▌ | 55/100 [00:28<00:19, 2.25it/s] 56it [00:29, 2.29it/s] 56%|█████▌ | 56/100 [00:28<00:19, 2.29it/s] 57it [00:29, 2.31it/s] 57%|█████▋ | 57/100 [00:29<00:18, 2.31it/s] 58it [00:29, 2.34it/s] 58%|█████▊ | 58/100 [00:29<00:17, 2.34it/s] 59it [00:30, 2.35it/s] 59%|█████▉ | 59/100 [00:30<00:17, 2.35it/s] 60it [00:30, 2.35it/s] Timestep 60 - saving sample 60%|██████ | 60/100 [00:30<00:16, 2.35it/s] 61it [00:31, 1.89it/s] 61%|██████ | 61/100 [00:31<00:20, 1.89it/s] 62it [00:31, 2.02it/s] 62%|██████▏ | 62/100 [00:31<00:18, 2.01it/s] 63it [00:32, 2.11it/s] 63%|██████▎ | 63/100 [00:32<00:17, 2.11it/s] 64it [00:32, 2.19it/s] 64%|██████▍ | 64/100 [00:32<00:16, 2.19it/s] 65it [00:33, 2.23it/s] 65%|██████▌ | 65/100 [00:33<00:15, 2.23it/s] 66it [00:33, 2.27it/s] 66%|██████▌ | 66/100 [00:33<00:14, 2.27it/s] 67it [00:33, 2.29it/s] 67%|██████▋ | 67/100 [00:33<00:14, 2.29it/s] 68it [00:34, 2.31it/s] 68%|██████▊ | 68/100 [00:34<00:13, 2.31it/s] 69it [00:34, 2.32it/s] 69%|██████▉ | 69/100 [00:34<00:13, 2.32it/s] 70it [00:35, 2.33it/s] Timestep 70 - saving sample 70%|███████ | 70/100 [00:35<00:12, 2.33it/s] 71it [00:36, 1.88it/s] 71%|███████ | 71/100 [00:36<00:15, 1.88it/s] 72it [00:36, 2.01it/s] 72%|███████▏ | 72/100 [00:36<00:13, 2.01it/s] 73it [00:36, 2.10it/s] 73%|███████▎ | 73/100 [00:36<00:12, 2.10it/s] 74it [00:37, 2.18it/s] 74%|███████▍ | 74/100 [00:37<00:11, 2.18it/s] 75it [00:37, 2.23it/s] 75%|███████▌ | 75/100 [00:37<00:11, 2.23it/s] 76it [00:38, 2.27it/s] 76%|███████▌ | 76/100 [00:38<00:10, 2.27it/s] 77it [00:38, 2.30it/s] 77%|███████▋ | 77/100 [00:38<00:09, 2.30it/s] 78it [00:38, 2.32it/s] 78%|███████▊ | 78/100 [00:38<00:09, 2.32it/s] 79it [00:39, 2.33it/s] 79%|███████▉ | 79/100 [00:39<00:09, 2.33it/s] 80it [00:39, 2.34it/s] Timestep 80 - saving sample 80%|████████ | 80/100 [00:39<00:08, 2.34it/s] 81it [00:40, 1.87it/s] 81%|████████ | 81/100 [00:40<00:10, 1.87it/s] 82it [00:41, 2.00it/s] 82%|████████▏ | 82/100 [00:41<00:08, 2.00it/s] 83it [00:41, 2.10it/s] 83%|████████▎ | 83/100 [00:41<00:08, 2.10it/s] 84it [00:41, 2.17it/s] 84%|████████▍ | 84/100 [00:41<00:07, 2.17it/s] 85it [00:42, 2.22it/s] 85%|████████▌ | 85/100 [00:42<00:06, 2.22it/s] 86it [00:42, 2.26it/s] 86%|████████▌ | 86/100 [00:42<00:06, 2.26it/s] 87it [00:43, 2.29it/s] 87%|████████▋ | 87/100 [00:43<00:05, 2.29it/s] 88it [00:43, 2.30it/s] 88%|████████▊ | 88/100 [00:43<00:05, 2.30it/s] 89it [00:44, 2.32it/s] 89%|████████▉ | 89/100 [00:44<00:04, 2.32it/s] 90it [00:44, 2.33it/s] Timestep 90 - saving sample 90%|█████████ | 90/100 [00:44<00:04, 2.33it/s] 91it [00:45, 1.86it/s] 91%|█████████ | 91/100 [00:45<00:04, 1.86it/s] 92it [00:45, 1.98it/s] 92%|█████████▏| 92/100 [00:45<00:04, 1.98it/s] 93it [00:46, 2.08it/s] 93%|█████████▎| 93/100 [00:46<00:03, 2.08it/s] 94it [00:46, 2.15it/s] 94%|█████████▍| 94/100 [00:46<00:02, 2.15it/s] 95it [00:46, 2.21it/s] 95%|█████████▌| 95/100 [00:46<00:02, 2.21it/s] 96it [00:47, 2.24it/s] 96%|█████████▌| 96/100 [00:47<00:01, 2.24it/s] 97it [00:47, 2.27it/s] 97%|█████████▋| 97/100 [00:47<00:01, 2.27it/s] 98it [00:48, 2.28it/s] 98%|█████████▊| 98/100 [00:48<00:00, 2.28it/s] 99it [00:48, 2.30it/s] Timestep 99 - saving final sample 99%|█████████▉| 99/100 [00:48<00:00, 2.30it/s] 100it [00:49, 1.84it/s] 100%|██████████| 100/100 [00:49<00:00, 1.84it/s] 100%|██████████| 100/100 [00:49<00:00, 2.02it/s] 100it [00:49, 2.02it/s]
Prediction
laion-ai/ongo:1b3cd151ID2cdnfiqulffc5ddcgqhlzrw3g4StatusSucceededSourceWebHardware–Total durationCreatedInput
- seed
- -1
- steps
- "100"
- width
- 256
- height
- 256
- prompt
- starry night
- batch_size
- "3"
- guidance_scale
- 5
- aesthetic_rating
- 8
- aesthetic_weight
- 0.1
{ "seed": -1, "steps": "100", "width": 256, "height": 256, "prompt": "starry night", "batch_size": "3", "guidance_scale": 5, "aesthetic_rating": 8, "aesthetic_weight": 0.1 }
Install Replicate’s Node.js client library:npm install replicate
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run laion-ai/ongo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "laion-ai/ongo:1b3cd15121ec450baa71bbbdacddef9217519f12ca12ccfef36eeaa20ad89b9d", { input: { seed: -1, steps: "100", width: 256, height: 256, prompt: "starry night", batch_size: "3", guidance_scale: 5, aesthetic_rating: 8, aesthetic_weight: 0.1 } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the client:import replicate
Run laion-ai/ongo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "laion-ai/ongo:1b3cd15121ec450baa71bbbdacddef9217519f12ca12ccfef36eeaa20ad89b9d", input={ "seed": -1, "steps": "100", "width": 256, "height": 256, "prompt": "starry night", "batch_size": "3", "guidance_scale": 5, "aesthetic_rating": 8, "aesthetic_weight": 0.1 } ) # The laion-ai/ongo model can stream output as it's running. # The predict method returns an iterator, and you can iterate over that output. for item in output: # https://replicate.com/laion-ai/ongo/api#output-schema print(item)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run laion-ai/ongo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "1b3cd15121ec450baa71bbbdacddef9217519f12ca12ccfef36eeaa20ad89b9d", "input": { "seed": -1, "steps": "100", "width": 256, "height": 256, "prompt": "starry night", "batch_size": "3", "guidance_scale": 5, "aesthetic_rating": 8, "aesthetic_weight": 0.1 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2022-06-24T23:05:43.443239Z", "created_at": "2022-06-24T23:04:43.444917Z", "data_removed": false, "error": null, "id": "2cdnfiqulffc5ddcgqhlzrw3g4", "input": { "seed": -1, "steps": "100", "width": 256, "height": 256, "prompt": "starry night", "batch_size": "3", "guidance_scale": 5, "aesthetic_rating": 8, "aesthetic_weight": 0.1 }, "logs": "Using seed 4022895569\nRunning simulation for starry night\nEncoding text embeddings with starry night dimensions\nUsing aesthetic embedding 8 with weight 0.1\nUsing inpaint model but no image is provided. Initializing with zeros.\nRunning diffusion...\n\n0it [00:00, ?it/s]\n\nTimestep 0 - saving sample\n 0%| | 0/100 [00:00<?, ?it/s]\u001b[A\n1it [00:02, 2.26s/it]\n\n 1%| | 1/100 [00:02<03:43, 2.26s/it]\u001b[A\n2it [00:04, 2.00s/it]\n\n 2%|▏ | 2/100 [00:04<03:15, 2.00s/it]\u001b[A\n3it [00:05, 1.92s/it]\n\n 3%|▎ | 3/100 [00:05<03:06, 1.92s/it]\u001b[A\n4it [00:06, 1.35s/it]\n\n 4%|▍ | 4/100 [00:06<02:09, 1.35s/it]\u001b[A\n5it [00:06, 1.03s/it]\n\n 5%|▌ | 5/100 [00:06<01:37, 1.03s/it]\u001b[A\n6it [00:07, 1.19it/s]\n\n 6%|▌ | 6/100 [00:07<01:18, 1.19it/s]\u001b[A\n7it [00:07, 1.40it/s]\n\n 7%|▋ | 7/100 [00:07<01:06, 1.40it/s]\u001b[A\n8it [00:08, 1.57it/s]\n\n 8%|▊ | 8/100 [00:08<00:58, 1.57it/s]\u001b[A\n9it [00:08, 1.72it/s]\n\n 9%|▉ | 9/100 [00:08<00:53, 1.72it/s]\u001b[A\n10it [00:09, 1.83it/s]\n\nTimestep 10 - saving sample\n 10%|█ | 10/100 [00:09<00:49, 1.83it/s]\u001b[A\n11it [00:10, 1.56it/s]\n\n 11%|█ | 11/100 [00:10<00:57, 1.56it/s]\u001b[A\n12it [00:10, 1.70it/s]\n\n 12%|█▏ | 12/100 [00:10<00:51, 1.70it/s]\u001b[A\n13it [00:10, 1.81it/s]\n\n 13%|█▎ | 13/100 [00:10<00:48, 1.81it/s]\u001b[A\n14it [00:11, 1.90it/s]\n\n 14%|█▍ | 14/100 [00:11<00:45, 1.90it/s]\u001b[A\n15it [00:11, 1.96it/s]\n\n 15%|█▌ | 15/100 [00:11<00:43, 1.96it/s]\u001b[A\n16it [00:12, 2.01it/s]\n\n 16%|█▌ | 16/100 [00:12<00:41, 2.01it/s]\u001b[A\n17it [00:12, 2.04it/s]\n\n 17%|█▋ | 17/100 [00:12<00:40, 2.04it/s]\u001b[A\n18it [00:13, 2.06it/s]\n\n 18%|█▊ | 18/100 [00:13<00:39, 2.06it/s]\u001b[A\n19it [00:13, 2.08it/s]\n\n 19%|█▉ | 19/100 [00:13<00:38, 2.08it/s]\u001b[A\n20it [00:14, 2.08it/s]\n\nTimestep 20 - saving sample\n 20%|██ | 20/100 [00:14<00:38, 2.08it/s]\u001b[A\n21it [00:15, 1.67it/s]\n\n 21%|██ | 21/100 [00:15<00:47, 1.67it/s]\u001b[A\n22it [00:15, 1.78it/s]\n\n 22%|██▏ | 22/100 [00:15<00:43, 1.78it/s]\u001b[A\n23it [00:16, 1.86it/s]\n\n 23%|██▎ | 23/100 [00:16<00:41, 1.86it/s]\u001b[A\n24it [00:16, 1.92it/s]\n\n 24%|██▍ | 24/100 [00:16<00:39, 1.92it/s]\u001b[A\n25it [00:17, 1.96it/s]\n\n 25%|██▌ | 25/100 [00:17<00:38, 1.96it/s]\u001b[A\n26it [00:17, 2.00it/s]\n\n 26%|██▌ | 26/100 [00:17<00:37, 2.00it/s]\u001b[A\n27it [00:18, 2.01it/s]\n\n 27%|██▋ | 27/100 [00:18<00:36, 2.01it/s]\u001b[A\n28it [00:18, 2.03it/s]\n\n 28%|██▊ | 28/100 [00:18<00:35, 2.03it/s]\u001b[A\n29it [00:18, 2.03it/s]\n\n 29%|██▉ | 29/100 [00:18<00:34, 2.03it/s]\u001b[A\n30it [00:19, 2.04it/s]\n\nTimestep 30 - saving sample\n 30%|███ | 30/100 [00:19<00:34, 2.04it/s]\u001b[A\n31it [00:20, 1.64it/s]\n\n 31%|███ | 31/100 [00:20<00:42, 1.64it/s]\u001b[A\n32it [00:20, 1.75it/s]\n\n 32%|███▏ | 32/100 [00:20<00:38, 1.75it/s]\u001b[A\n33it [00:21, 1.83it/s]\n\n 33%|███▎ | 33/100 [00:21<00:36, 1.83it/s]\u001b[A\n34it [00:21, 1.89it/s]\n\n 34%|███▍ | 34/100 [00:21<00:35, 1.89it/s]\u001b[A\n35it [00:22, 1.93it/s]\n\n 35%|███▌ | 35/100 [00:22<00:33, 1.93it/s]\u001b[A\n36it [00:22, 1.95it/s]\n\n 36%|███▌ | 36/100 [00:22<00:32, 1.95it/s]\u001b[A\n37it [00:23, 1.97it/s]\n\n 37%|███▋ | 37/100 [00:23<00:31, 1.97it/s]\u001b[A\n38it [00:23, 1.99it/s]\n\n 38%|███▊ | 38/100 [00:23<00:31, 1.99it/s]\u001b[A\n39it [00:24, 2.00it/s]\n\n 39%|███▉ | 39/100 [00:24<00:30, 2.00it/s]\u001b[A\n40it [00:24, 2.00it/s]\n\nTimestep 40 - saving sample\n 40%|████ | 40/100 [00:24<00:30, 2.00it/s]\u001b[A\n41it [00:25, 1.60it/s]\n\n 41%|████ | 41/100 [00:25<00:36, 1.60it/s]\u001b[A\n42it [00:26, 1.71it/s]\n\n 42%|████▏ | 42/100 [00:26<00:33, 1.71it/s]\u001b[A\n43it [00:26, 1.79it/s]\n\n 43%|████▎ | 43/100 [00:26<00:31, 1.79it/s]\u001b[A\n44it [00:27, 1.84it/s]\n\n 44%|████▍ | 44/100 [00:27<00:30, 1.84it/s]\u001b[A\n45it [00:27, 1.88it/s]\n\n 45%|████▌ | 45/100 [00:27<00:29, 1.88it/s]\u001b[A\n46it [00:28, 1.90it/s]\n\n 46%|████▌ | 46/100 [00:28<00:28, 1.90it/s]\u001b[A\n47it [00:28, 1.92it/s]\n\n 47%|████▋ | 47/100 [00:28<00:27, 1.92it/s]\u001b[A\n48it [00:29, 1.94it/s]\n\n 48%|████▊ | 48/100 [00:29<00:26, 1.94it/s]\u001b[A\n49it [00:29, 1.95it/s]\n\n 49%|████▉ | 49/100 [00:29<00:26, 1.95it/s]\u001b[A\n50it [00:30, 1.96it/s]\n\nTimestep 50 - saving sample\n 50%|█████ | 50/100 [00:30<00:25, 1.96it/s]\u001b[A\n51it [00:31, 1.58it/s]\n\n 51%|█████ | 51/100 [00:31<00:31, 1.58it/s]\u001b[A\n52it [00:31, 1.69it/s]\n\n 52%|█████▏ | 52/100 [00:31<00:28, 1.69it/s]\u001b[A\n53it [00:32, 1.77it/s]\n\n 53%|█████▎ | 53/100 [00:32<00:26, 1.77it/s]\u001b[A\n54it [00:32, 1.83it/s]\n\n 54%|█████▍ | 54/100 [00:32<00:25, 1.83it/s]\u001b[A\n55it [00:33, 1.87it/s]\n\n 55%|█████▌ | 55/100 [00:33<00:24, 1.87it/s]\u001b[A\n56it [00:33, 1.90it/s]\n\n 56%|█████▌ | 56/100 [00:33<00:23, 1.90it/s]\u001b[A\n57it [00:34, 1.92it/s]\n\n 57%|█████▋ | 57/100 [00:34<00:22, 1.92it/s]\u001b[A\n58it [00:34, 1.94it/s]\n\n 58%|█████▊ | 58/100 [00:34<00:21, 1.94it/s]\u001b[A\n59it [00:35, 1.95it/s]\n\n 59%|█████▉ | 59/100 [00:35<00:21, 1.95it/s]\u001b[A\n60it [00:35, 1.96it/s]\n\nTimestep 60 - saving sample\n 60%|██████ | 60/100 [00:35<00:20, 1.96it/s]\u001b[A\n61it [00:36, 1.58it/s]\n\n 61%|██████ | 61/100 [00:36<00:24, 1.58it/s]\u001b[A\n62it [00:37, 1.69it/s]\n\n 62%|██████▏ | 62/100 [00:37<00:22, 1.69it/s]\u001b[A\n63it [00:37, 1.77it/s]\n\n 63%|██████▎ | 63/100 [00:37<00:20, 1.77it/s]\u001b[A\n64it [00:38, 1.83it/s]\n\n 64%|██████▍ | 64/100 [00:38<00:19, 1.83it/s]\u001b[A\n65it [00:38, 1.88it/s]\n\n 65%|██████▌ | 65/100 [00:38<00:18, 1.88it/s]\u001b[A\n66it [00:39, 1.92it/s]\n\n 66%|██████▌ | 66/100 [00:39<00:17, 1.92it/s]\u001b[A\n67it [00:39, 1.94it/s]\n\n 67%|██████▋ | 67/100 [00:39<00:17, 1.94it/s]\u001b[A\n68it [00:40, 1.95it/s]\n\n 68%|██████▊ | 68/100 [00:40<00:16, 1.96it/s]\u001b[A\n69it [00:40, 1.98it/s]\n\n 69%|██████▉ | 69/100 [00:40<00:15, 1.98it/s]\u001b[A\n70it [00:41, 1.99it/s]\n\nTimestep 70 - saving sample\n 70%|███████ | 70/100 [00:41<00:15, 1.99it/s]\u001b[A\n71it [00:42, 1.61it/s]\n\n 71%|███████ | 71/100 [00:42<00:18, 1.61it/s]\u001b[A\n72it [00:42, 1.72it/s]\n\n 72%|███████▏ | 72/100 [00:42<00:16, 1.72it/s]\u001b[A\n73it [00:43, 1.80it/s]\n\n 73%|███████▎ | 73/100 [00:43<00:14, 1.80it/s]\u001b[A\n74it [00:43, 1.86it/s]\n\n 74%|███████▍ | 74/100 [00:43<00:13, 1.86it/s]\u001b[A\n75it [00:43, 1.92it/s]\n\n 75%|███████▌ | 75/100 [00:43<00:13, 1.92it/s]\u001b[A\n76it [00:44, 1.95it/s]\n\n 76%|███████▌ | 76/100 [00:44<00:12, 1.95it/s]\u001b[A\n77it [00:44, 1.98it/s]\n\n 77%|███████▋ | 77/100 [00:44<00:11, 1.98it/s]\u001b[A\n78it [00:45, 2.00it/s]\n\n 78%|███████▊ | 78/100 [00:45<00:11, 2.00it/s]\u001b[A\n79it [00:45, 2.01it/s]\n\n 79%|███████▉ | 79/100 [00:45<00:10, 2.01it/s]\u001b[A\n80it [00:46, 2.03it/s]\n\nTimestep 80 - saving sample\n 80%|████████ | 80/100 [00:46<00:09, 2.03it/s]\u001b[A\n81it [00:47, 1.64it/s]\n\n 81%|████████ | 81/100 [00:47<00:11, 1.64it/s]\u001b[A\n82it [00:47, 1.75it/s]\n\n 82%|████████▏ | 82/100 [00:47<00:10, 1.75it/s]\u001b[A\n83it [00:48, 1.83it/s]\n\n 83%|████████▎ | 83/100 [00:48<00:09, 1.83it/s]\u001b[A\n84it [00:48, 1.89it/s]\n\n 84%|████████▍ | 84/100 [00:48<00:08, 1.89it/s]\u001b[A\n85it [00:49, 1.94it/s]\n\n 85%|████████▌ | 85/100 [00:49<00:07, 1.94it/s]\u001b[A\n86it [00:49, 1.98it/s]\n\n 86%|████████▌ | 86/100 [00:49<00:07, 1.98it/s]\u001b[A\n87it [00:50, 2.00it/s]\n\n 87%|████████▋ | 87/100 [00:50<00:06, 2.00it/s]\u001b[A\n88it [00:50, 2.03it/s]\n\n 88%|████████▊ | 88/100 [00:50<00:05, 2.03it/s]\u001b[A\n89it [00:51, 2.04it/s]\n\n 89%|████████▉ | 89/100 [00:51<00:05, 2.04it/s]\u001b[A\n90it [00:51, 2.05it/s]\n\nTimestep 90 - saving sample\n 90%|█████████ | 90/100 [00:51<00:04, 2.05it/s]\u001b[A\n91it [00:52, 1.65it/s]\n\n 91%|█████████ | 91/100 [00:52<00:05, 1.65it/s]\u001b[A\n92it [00:53, 1.77it/s]\n\n 92%|█████████▏| 92/100 [00:53<00:04, 1.77it/s]\u001b[A\n93it [00:53, 1.85it/s]\n\n 93%|█████████▎| 93/100 [00:53<00:03, 1.85it/s]\u001b[A\n94it [00:53, 1.92it/s]\n\n 94%|█████████▍| 94/100 [00:53<00:03, 1.92it/s]\u001b[A\n95it [00:54, 1.97it/s]\n\n 95%|█████████▌| 95/100 [00:54<00:02, 1.97it/s]\u001b[A\n96it [00:54, 2.01it/s]\n\n 96%|█████████▌| 96/100 [00:54<00:01, 2.01it/s]\u001b[A\n97it [00:55, 2.03it/s]\n\n 97%|█████████▋| 97/100 [00:55<00:01, 2.03it/s]\u001b[A\n98it [00:55, 2.06it/s]\n\n 98%|█████████▊| 98/100 [00:55<00:00, 2.06it/s]\u001b[A\n99it [00:56, 2.07it/s]\n\nTimestep 99 - saving final sample\n 99%|█████████▉| 99/100 [00:56<00:00, 2.07it/s]\u001b[A\n100it [00:57, 1.67it/s]\n\n100%|██████████| 100/100 [00:57<00:00, 1.67it/s]\u001b[A\n100%|██████████| 100/100 [00:57<00:00, 1.75it/s]\n\n100it [00:57, 1.75it/s]", "metrics": { "predict_time": 59.867322, "total_time": 59.998322 }, "output": [ [ "https://replicate.delivery/mgxm/e02b10ec-6749-4c4b-b4ef-661a9c78b3f9/current_0.jpg", "https://replicate.delivery/mgxm/a5f37b97-d216-49dc-bd88-c271f0152181/current_1.jpg", "https://replicate.delivery/mgxm/b12db2f6-efa6-4b69-8d3e-6c11950b7885/current_2.jpg" ], [ "https://replicate.delivery/mgxm/116bccdd-0780-4bbf-9256-f07bee5dbc38/current_0.jpg", "https://replicate.delivery/mgxm/8907c0d1-1357-4853-9fab-8c05fa58ed1b/current_1.jpg", "https://replicate.delivery/mgxm/91c8ff5e-0d90-44d7-9f8c-d75a1c459339/current_2.jpg" ], [ "https://replicate.delivery/mgxm/38b01e30-0fd7-445a-b33f-506c2e506077/current_0.jpg", "https://replicate.delivery/mgxm/8f465470-c6cb-474d-802a-cba703d6355e/current_1.jpg", "https://replicate.delivery/mgxm/3ec7ca16-b2dd-4f35-980f-0528218bac0f/current_2.jpg" ], [ "https://replicate.delivery/mgxm/7630b20c-d6ff-4000-925f-7599d1ef335a/current_0.jpg", "https://replicate.delivery/mgxm/f73983c6-9c61-47a1-813e-910f19c67c42/current_1.jpg", "https://replicate.delivery/mgxm/1db73183-c118-4caa-9a31-3a6592cd6e2c/current_2.jpg" ], [ "https://replicate.delivery/mgxm/385b6ed3-56c6-4f6c-bcf6-7e6a04694d9f/current_0.jpg", "https://replicate.delivery/mgxm/d92c5b7c-bafd-4609-bacb-f500cc9b218e/current_1.jpg", "https://replicate.delivery/mgxm/0815aa40-64db-4a98-b920-aeed195d8236/current_2.jpg" ], [ "https://replicate.delivery/mgxm/8a2647e0-ad3b-48fa-be26-4ba84bebfa77/current_0.jpg", "https://replicate.delivery/mgxm/542c580b-b95a-4420-a7f0-c686706b98df/current_1.jpg", "https://replicate.delivery/mgxm/f17dfc20-1479-4929-a73c-c29f8a5a1a14/current_2.jpg" ], [ "https://replicate.delivery/mgxm/21777a72-80c4-4c37-94ee-2c3cc2a9c815/current_0.jpg", "https://replicate.delivery/mgxm/3593b647-3622-4977-8bbd-cb38afca5a5c/current_1.jpg", "https://replicate.delivery/mgxm/b40a752d-18bd-43ca-ba4c-722245adc2c1/current_2.jpg" ], [ "https://replicate.delivery/mgxm/d9c3c28e-8c94-4875-a2a3-e3162ebe990a/current_0.jpg", "https://replicate.delivery/mgxm/5ae8ddf1-e913-468b-af5c-a20bab2d7475/current_1.jpg", "https://replicate.delivery/mgxm/f6718dfd-2849-48ba-bd5b-93269caaf8e4/current_2.jpg" ], [ "https://replicate.delivery/mgxm/1482446c-9b05-460e-8906-f54384021510/current_0.jpg", "https://replicate.delivery/mgxm/192442db-54dc-4794-aebd-b3b9c4374d2c/current_1.jpg", "https://replicate.delivery/mgxm/7a4b77db-91e7-4cae-9712-988a0980851c/current_2.jpg" ], [ "https://replicate.delivery/mgxm/4f66b837-182b-4fb9-8c29-7b9dbbad69a9/current_0.jpg", "https://replicate.delivery/mgxm/51d5e69c-ad2a-4d63-9364-a950ca272bd0/current_1.jpg", "https://replicate.delivery/mgxm/195fb30a-cff0-4c82-a179-a73e3504f3b5/current_2.jpg" ], [ "https://replicate.delivery/mgxm/b1fb52a9-4bbb-41b6-974e-888d0398b500/current_0.jpg", "https://replicate.delivery/mgxm/937ccab8-0f4e-411a-a1a5-0e237e9fde10/current_1.jpg", "https://replicate.delivery/mgxm/a6ce0c1d-91db-4ff9-8b77-1ffa45927265/current_2.jpg" ] ], "started_at": "2022-06-24T23:04:43.575917Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/2cdnfiqulffc5ddcgqhlzrw3g4", "cancel": "https://api.replicate.com/v1/predictions/2cdnfiqulffc5ddcgqhlzrw3g4/cancel" }, "version": "41ad32228705648d785fc33be19d98dfa058cfd59d1f9a7c2248757e3652cdf6" }
Generated inUsing seed 4022895569 Running simulation for starry night Encoding text embeddings with starry night dimensions Using aesthetic embedding 8 with weight 0.1 Using inpaint model but no image is provided. Initializing with zeros. Running diffusion... 0it [00:00, ?it/s] Timestep 0 - saving sample 0%| | 0/100 [00:00<?, ?it/s] 1it [00:02, 2.26s/it] 1%| | 1/100 [00:02<03:43, 2.26s/it] 2it [00:04, 2.00s/it] 2%|▏ | 2/100 [00:04<03:15, 2.00s/it] 3it [00:05, 1.92s/it] 3%|▎ | 3/100 [00:05<03:06, 1.92s/it] 4it [00:06, 1.35s/it] 4%|▍ | 4/100 [00:06<02:09, 1.35s/it] 5it [00:06, 1.03s/it] 5%|▌ | 5/100 [00:06<01:37, 1.03s/it] 6it [00:07, 1.19it/s] 6%|▌ | 6/100 [00:07<01:18, 1.19it/s] 7it [00:07, 1.40it/s] 7%|▋ | 7/100 [00:07<01:06, 1.40it/s] 8it [00:08, 1.57it/s] 8%|▊ | 8/100 [00:08<00:58, 1.57it/s] 9it [00:08, 1.72it/s] 9%|▉ | 9/100 [00:08<00:53, 1.72it/s] 10it [00:09, 1.83it/s] Timestep 10 - saving sample 10%|█ | 10/100 [00:09<00:49, 1.83it/s] 11it [00:10, 1.56it/s] 11%|█ | 11/100 [00:10<00:57, 1.56it/s] 12it [00:10, 1.70it/s] 12%|█▏ | 12/100 [00:10<00:51, 1.70it/s] 13it [00:10, 1.81it/s] 13%|█▎ | 13/100 [00:10<00:48, 1.81it/s] 14it [00:11, 1.90it/s] 14%|█▍ | 14/100 [00:11<00:45, 1.90it/s] 15it [00:11, 1.96it/s] 15%|█▌ | 15/100 [00:11<00:43, 1.96it/s] 16it [00:12, 2.01it/s] 16%|█▌ | 16/100 [00:12<00:41, 2.01it/s] 17it [00:12, 2.04it/s] 17%|█▋ | 17/100 [00:12<00:40, 2.04it/s] 18it [00:13, 2.06it/s] 18%|█▊ | 18/100 [00:13<00:39, 2.06it/s] 19it [00:13, 2.08it/s] 19%|█▉ | 19/100 [00:13<00:38, 2.08it/s] 20it [00:14, 2.08it/s] Timestep 20 - saving sample 20%|██ | 20/100 [00:14<00:38, 2.08it/s] 21it [00:15, 1.67it/s] 21%|██ | 21/100 [00:15<00:47, 1.67it/s] 22it [00:15, 1.78it/s] 22%|██▏ | 22/100 [00:15<00:43, 1.78it/s] 23it [00:16, 1.86it/s] 23%|██▎ | 23/100 [00:16<00:41, 1.86it/s] 24it [00:16, 1.92it/s] 24%|██▍ | 24/100 [00:16<00:39, 1.92it/s] 25it [00:17, 1.96it/s] 25%|██▌ | 25/100 [00:17<00:38, 1.96it/s] 26it [00:17, 2.00it/s] 26%|██▌ | 26/100 [00:17<00:37, 2.00it/s] 27it [00:18, 2.01it/s] 27%|██▋ | 27/100 [00:18<00:36, 2.01it/s] 28it [00:18, 2.03it/s] 28%|██▊ | 28/100 [00:18<00:35, 2.03it/s] 29it [00:18, 2.03it/s] 29%|██▉ | 29/100 [00:18<00:34, 2.03it/s] 30it [00:19, 2.04it/s] Timestep 30 - saving sample 30%|███ | 30/100 [00:19<00:34, 2.04it/s] 31it [00:20, 1.64it/s] 31%|███ | 31/100 [00:20<00:42, 1.64it/s] 32it [00:20, 1.75it/s] 32%|███▏ | 32/100 [00:20<00:38, 1.75it/s] 33it [00:21, 1.83it/s] 33%|███▎ | 33/100 [00:21<00:36, 1.83it/s] 34it [00:21, 1.89it/s] 34%|███▍ | 34/100 [00:21<00:35, 1.89it/s] 35it [00:22, 1.93it/s] 35%|███▌ | 35/100 [00:22<00:33, 1.93it/s] 36it [00:22, 1.95it/s] 36%|███▌ | 36/100 [00:22<00:32, 1.95it/s] 37it [00:23, 1.97it/s] 37%|███▋ | 37/100 [00:23<00:31, 1.97it/s] 38it [00:23, 1.99it/s] 38%|███▊ | 38/100 [00:23<00:31, 1.99it/s] 39it [00:24, 2.00it/s] 39%|███▉ | 39/100 [00:24<00:30, 2.00it/s] 40it [00:24, 2.00it/s] Timestep 40 - saving sample 40%|████ | 40/100 [00:24<00:30, 2.00it/s] 41it [00:25, 1.60it/s] 41%|████ | 41/100 [00:25<00:36, 1.60it/s] 42it [00:26, 1.71it/s] 42%|████▏ | 42/100 [00:26<00:33, 1.71it/s] 43it [00:26, 1.79it/s] 43%|████▎ | 43/100 [00:26<00:31, 1.79it/s] 44it [00:27, 1.84it/s] 44%|████▍ | 44/100 [00:27<00:30, 1.84it/s] 45it [00:27, 1.88it/s] 45%|████▌ | 45/100 [00:27<00:29, 1.88it/s] 46it [00:28, 1.90it/s] 46%|████▌ | 46/100 [00:28<00:28, 1.90it/s] 47it [00:28, 1.92it/s] 47%|████▋ | 47/100 [00:28<00:27, 1.92it/s] 48it [00:29, 1.94it/s] 48%|████▊ | 48/100 [00:29<00:26, 1.94it/s] 49it [00:29, 1.95it/s] 49%|████▉ | 49/100 [00:29<00:26, 1.95it/s] 50it [00:30, 1.96it/s] Timestep 50 - saving sample 50%|█████ | 50/100 [00:30<00:25, 1.96it/s] 51it [00:31, 1.58it/s] 51%|█████ | 51/100 [00:31<00:31, 1.58it/s] 52it [00:31, 1.69it/s] 52%|█████▏ | 52/100 [00:31<00:28, 1.69it/s] 53it [00:32, 1.77it/s] 53%|█████▎ | 53/100 [00:32<00:26, 1.77it/s] 54it [00:32, 1.83it/s] 54%|█████▍ | 54/100 [00:32<00:25, 1.83it/s] 55it [00:33, 1.87it/s] 55%|█████▌ | 55/100 [00:33<00:24, 1.87it/s] 56it [00:33, 1.90it/s] 56%|█████▌ | 56/100 [00:33<00:23, 1.90it/s] 57it [00:34, 1.92it/s] 57%|█████▋ | 57/100 [00:34<00:22, 1.92it/s] 58it [00:34, 1.94it/s] 58%|█████▊ | 58/100 [00:34<00:21, 1.94it/s] 59it [00:35, 1.95it/s] 59%|█████▉ | 59/100 [00:35<00:21, 1.95it/s] 60it [00:35, 1.96it/s] Timestep 60 - saving sample 60%|██████ | 60/100 [00:35<00:20, 1.96it/s] 61it [00:36, 1.58it/s] 61%|██████ | 61/100 [00:36<00:24, 1.58it/s] 62it [00:37, 1.69it/s] 62%|██████▏ | 62/100 [00:37<00:22, 1.69it/s] 63it [00:37, 1.77it/s] 63%|██████▎ | 63/100 [00:37<00:20, 1.77it/s] 64it [00:38, 1.83it/s] 64%|██████▍ | 64/100 [00:38<00:19, 1.83it/s] 65it [00:38, 1.88it/s] 65%|██████▌ | 65/100 [00:38<00:18, 1.88it/s] 66it [00:39, 1.92it/s] 66%|██████▌ | 66/100 [00:39<00:17, 1.92it/s] 67it [00:39, 1.94it/s] 67%|██████▋ | 67/100 [00:39<00:17, 1.94it/s] 68it [00:40, 1.95it/s] 68%|██████▊ | 68/100 [00:40<00:16, 1.96it/s] 69it [00:40, 1.98it/s] 69%|██████▉ | 69/100 [00:40<00:15, 1.98it/s] 70it [00:41, 1.99it/s] Timestep 70 - saving sample 70%|███████ | 70/100 [00:41<00:15, 1.99it/s] 71it [00:42, 1.61it/s] 71%|███████ | 71/100 [00:42<00:18, 1.61it/s] 72it [00:42, 1.72it/s] 72%|███████▏ | 72/100 [00:42<00:16, 1.72it/s] 73it [00:43, 1.80it/s] 73%|███████▎ | 73/100 [00:43<00:14, 1.80it/s] 74it [00:43, 1.86it/s] 74%|███████▍ | 74/100 [00:43<00:13, 1.86it/s] 75it [00:43, 1.92it/s] 75%|███████▌ | 75/100 [00:43<00:13, 1.92it/s] 76it [00:44, 1.95it/s] 76%|███████▌ | 76/100 [00:44<00:12, 1.95it/s] 77it [00:44, 1.98it/s] 77%|███████▋ | 77/100 [00:44<00:11, 1.98it/s] 78it [00:45, 2.00it/s] 78%|███████▊ | 78/100 [00:45<00:11, 2.00it/s] 79it [00:45, 2.01it/s] 79%|███████▉ | 79/100 [00:45<00:10, 2.01it/s] 80it [00:46, 2.03it/s] Timestep 80 - saving sample 80%|████████ | 80/100 [00:46<00:09, 2.03it/s] 81it [00:47, 1.64it/s] 81%|████████ | 81/100 [00:47<00:11, 1.64it/s] 82it [00:47, 1.75it/s] 82%|████████▏ | 82/100 [00:47<00:10, 1.75it/s] 83it [00:48, 1.83it/s] 83%|████████▎ | 83/100 [00:48<00:09, 1.83it/s] 84it [00:48, 1.89it/s] 84%|████████▍ | 84/100 [00:48<00:08, 1.89it/s] 85it [00:49, 1.94it/s] 85%|████████▌ | 85/100 [00:49<00:07, 1.94it/s] 86it [00:49, 1.98it/s] 86%|████████▌ | 86/100 [00:49<00:07, 1.98it/s] 87it [00:50, 2.00it/s] 87%|████████▋ | 87/100 [00:50<00:06, 2.00it/s] 88it [00:50, 2.03it/s] 88%|████████▊ | 88/100 [00:50<00:05, 2.03it/s] 89it [00:51, 2.04it/s] 89%|████████▉ | 89/100 [00:51<00:05, 2.04it/s] 90it [00:51, 2.05it/s] Timestep 90 - saving sample 90%|█████████ | 90/100 [00:51<00:04, 2.05it/s] 91it [00:52, 1.65it/s] 91%|█████████ | 91/100 [00:52<00:05, 1.65it/s] 92it [00:53, 1.77it/s] 92%|█████████▏| 92/100 [00:53<00:04, 1.77it/s] 93it [00:53, 1.85it/s] 93%|█████████▎| 93/100 [00:53<00:03, 1.85it/s] 94it [00:53, 1.92it/s] 94%|█████████▍| 94/100 [00:53<00:03, 1.92it/s] 95it [00:54, 1.97it/s] 95%|█████████▌| 95/100 [00:54<00:02, 1.97it/s] 96it [00:54, 2.01it/s] 96%|█████████▌| 96/100 [00:54<00:01, 2.01it/s] 97it [00:55, 2.03it/s] 97%|█████████▋| 97/100 [00:55<00:01, 2.03it/s] 98it [00:55, 2.06it/s] 98%|█████████▊| 98/100 [00:55<00:00, 2.06it/s] 99it [00:56, 2.07it/s] Timestep 99 - saving final sample 99%|█████████▉| 99/100 [00:56<00:00, 2.07it/s] 100it [00:57, 1.67it/s] 100%|██████████| 100/100 [00:57<00:00, 1.67it/s] 100%|██████████| 100/100 [00:57<00:00, 1.75it/s] 100it [00:57, 1.75it/s]
Prediction
laion-ai/ongo:1b3cd151IDlvc2nt4xu5emlkxffo7hp6f2pyStatusSucceededSourceWebHardware–Total durationCreatedInput
- seed
- -1
- steps
- "100"
- width
- 256
- height
- 256
- prompt
- bunny rabbit in style of van gogh
- batch_size
- "3"
- guidance_scale
- 5
- aesthetic_rating
- 8
- aesthetic_weight
- 0.1
{ "seed": -1, "steps": "100", "width": 256, "height": 256, "prompt": "bunny rabbit in style of van gogh", "batch_size": "3", "guidance_scale": 5, "aesthetic_rating": 8, "aesthetic_weight": 0.1 }
Install Replicate’s Node.js client library:npm install replicate
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run laion-ai/ongo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "laion-ai/ongo:1b3cd15121ec450baa71bbbdacddef9217519f12ca12ccfef36eeaa20ad89b9d", { input: { seed: -1, steps: "100", width: 256, height: 256, prompt: "bunny rabbit in style of van gogh", batch_size: "3", guidance_scale: 5, aesthetic_rating: 8, aesthetic_weight: 0.1 } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the client:import replicate
Run laion-ai/ongo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "laion-ai/ongo:1b3cd15121ec450baa71bbbdacddef9217519f12ca12ccfef36eeaa20ad89b9d", input={ "seed": -1, "steps": "100", "width": 256, "height": 256, "prompt": "bunny rabbit in style of van gogh", "batch_size": "3", "guidance_scale": 5, "aesthetic_rating": 8, "aesthetic_weight": 0.1 } ) # The laion-ai/ongo model can stream output as it's running. # The predict method returns an iterator, and you can iterate over that output. for item in output: # https://replicate.com/laion-ai/ongo/api#output-schema print(item)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run laion-ai/ongo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "1b3cd15121ec450baa71bbbdacddef9217519f12ca12ccfef36eeaa20ad89b9d", "input": { "seed": -1, "steps": "100", "width": 256, "height": 256, "prompt": "bunny rabbit in style of van gogh", "batch_size": "3", "guidance_scale": 5, "aesthetic_rating": 8, "aesthetic_weight": 0.1 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2022-06-24T23:10:08.972024Z", "created_at": "2022-06-24T23:09:08.495722Z", "data_removed": false, "error": null, "id": "lvc2nt4xu5emlkxffo7hp6f2py", "input": { "seed": -1, "steps": "100", "width": 256, "height": 256, "prompt": "bunny rabbit in style of van gogh", "batch_size": "3", "guidance_scale": 5, "aesthetic_rating": 8, "aesthetic_weight": 0.1 }, "logs": "Using seed 3823169816\nRunning simulation for bunny rabbit in style of van gogh\nEncoding text embeddings with bunny rabbit in style of van gogh dimensions\nUsing aesthetic embedding 8 with weight 0.1\nUsing inpaint model but no image is provided. Initializing with zeros.\nRunning diffusion...\n\n0it [00:00, ?it/s]\n\nTimestep 0 - saving sample\n 0%| | 0/100 [00:00<?, ?it/s]\u001b[A\n1it [00:02, 2.33s/it]\n\n 1%| | 1/100 [00:02<03:51, 2.33s/it]\u001b[A\n2it [00:04, 2.09s/it]\n\n 2%|▏ | 2/100 [00:04<03:24, 2.09s/it]\u001b[A\n3it [00:06, 2.02s/it]\n\n 3%|▎ | 3/100 [00:06<03:15, 2.02s/it]\u001b[A\n4it [00:06, 1.42s/it]\n\n 4%|▍ | 4/100 [00:06<02:15, 1.42s/it]\u001b[A\n5it [00:07, 1.08s/it]\n\n 5%|▌ | 5/100 [00:07<01:42, 1.08s/it]\u001b[A\n6it [00:07, 1.14it/s]\n\n 6%|▌ | 6/100 [00:07<01:22, 1.14it/s]\u001b[A\n7it [00:08, 1.33it/s]\n\n 7%|▋ | 7/100 [00:08<01:09, 1.33it/s]\u001b[A\n8it [00:08, 1.49it/s]\n\n 8%|▊ | 8/100 [00:08<01:01, 1.49it/s]\u001b[A\n9it [00:09, 1.63it/s]\n\n 9%|▉ | 9/100 [00:09<00:55, 1.63it/s]\u001b[A\n10it [00:09, 1.73it/s]\n\nTimestep 10 - saving sample\n 10%|█ | 10/100 [00:09<00:51, 1.73it/s]\u001b[A\n11it [00:10, 1.48it/s]\n\n 11%|█ | 11/100 [00:10<01:00, 1.48it/s]\u001b[A\n12it [00:11, 1.61it/s]\n\n 12%|█▏ | 12/100 [00:11<00:54, 1.61it/s]\u001b[A\n13it [00:11, 1.71it/s]\n\n 13%|█▎ | 13/100 [00:11<00:50, 1.71it/s]\u001b[A\n14it [00:12, 1.80it/s]\n\n 14%|█▍ | 14/100 [00:12<00:47, 1.80it/s]\u001b[A\n15it [00:12, 1.85it/s]\n\n 15%|█▌ | 15/100 [00:12<00:45, 1.85it/s]\u001b[A\n16it [00:13, 1.89it/s]\n\n 16%|█▌ | 16/100 [00:13<00:44, 1.89it/s]\u001b[A\n17it [00:13, 1.92it/s]\n\n 17%|█▋ | 17/100 [00:13<00:43, 1.92it/s]\u001b[A\n18it [00:14, 1.93it/s]\n\n 18%|█▊ | 18/100 [00:14<00:42, 1.93it/s]\u001b[A\n19it [00:14, 1.95it/s]\n\n 19%|█▉ | 19/100 [00:14<00:41, 1.95it/s]\u001b[A\n20it [00:15, 1.96it/s]\n\nTimestep 20 - saving sample\n 20%|██ | 20/100 [00:15<00:40, 1.96it/s]\u001b[A\n21it [00:15, 1.58it/s]\n\n 21%|██ | 21/100 [00:15<00:50, 1.58it/s]\u001b[A\n22it [00:16, 1.69it/s]\n\n 22%|██▏ | 22/100 [00:16<00:46, 1.69it/s]\u001b[A\n23it [00:16, 1.77it/s]\n\n 23%|██▎ | 23/100 [00:16<00:43, 1.77it/s]\u001b[A\n24it [00:17, 1.82it/s]\n\n 24%|██▍ | 24/100 [00:17<00:41, 1.82it/s]\u001b[A\n25it [00:17, 1.87it/s]\n\n 25%|██▌ | 25/100 [00:17<00:40, 1.87it/s]\u001b[A\n26it [00:18, 1.90it/s]\n\n 26%|██▌ | 26/100 [00:18<00:39, 1.90it/s]\u001b[A\n27it [00:18, 1.92it/s]\n\n 27%|██▋ | 27/100 [00:18<00:38, 1.92it/s]\u001b[A\n28it [00:19, 1.93it/s]\n\n 28%|██▊ | 28/100 [00:19<00:37, 1.93it/s]\u001b[A\n29it [00:20, 1.93it/s]\n\n 29%|██▉ | 29/100 [00:20<00:36, 1.93it/s]\u001b[A\n30it [00:20, 1.95it/s]\n\nTimestep 30 - saving sample\n 30%|███ | 30/100 [00:20<00:35, 1.95it/s]\u001b[A\n31it [00:21, 1.57it/s]\n\n 31%|███ | 31/100 [00:21<00:43, 1.57it/s]\u001b[A\n32it [00:21, 1.67it/s]\n\n 32%|███▏ | 32/100 [00:21<00:40, 1.67it/s]\u001b[A\n33it [00:22, 1.75it/s]\n\n 33%|███▎ | 33/100 [00:22<00:38, 1.75it/s]\u001b[A\n34it [00:22, 1.81it/s]\n\n 34%|███▍ | 34/100 [00:22<00:36, 1.81it/s]\u001b[A\n35it [00:23, 1.86it/s]\n\n 35%|███▌ | 35/100 [00:23<00:35, 1.86it/s]\u001b[A\n36it [00:23, 1.89it/s]\n\n 36%|███▌ | 36/100 [00:23<00:33, 1.89it/s]\u001b[A\n37it [00:24, 1.92it/s]\n\n 37%|███▋ | 37/100 [00:24<00:32, 1.92it/s]\u001b[A\n38it [00:24, 1.93it/s]\n\n 38%|███▊ | 38/100 [00:24<00:32, 1.93it/s]\u001b[A\n39it [00:25, 1.95it/s]\n\n 39%|███▉ | 39/100 [00:25<00:31, 1.95it/s]\u001b[A\n40it [00:25, 1.96it/s]\n\nTimestep 40 - saving sample\n 40%|████ | 40/100 [00:25<00:30, 1.96it/s]\u001b[A\n41it [00:26, 1.58it/s]\n\n 41%|████ | 41/100 [00:26<00:37, 1.58it/s]\u001b[A\n42it [00:27, 1.70it/s]\n\n 42%|████▏ | 42/100 [00:27<00:34, 1.70it/s]\u001b[A\n43it [00:27, 1.78it/s]\n\n 43%|████▎ | 43/100 [00:27<00:32, 1.78it/s]\u001b[A\n44it [00:28, 1.84it/s]\n\n 44%|████▍ | 44/100 [00:28<00:30, 1.84it/s]\u001b[A\n45it [00:28, 1.89it/s]\n\n 45%|████▌ | 45/100 [00:28<00:29, 1.89it/s]\u001b[A\n46it [00:29, 1.93it/s]\n\n 46%|████▌ | 46/100 [00:29<00:28, 1.93it/s]\u001b[A\n47it [00:29, 1.95it/s]\n\n 47%|████▋ | 47/100 [00:29<00:27, 1.95it/s]\u001b[A\n48it [00:30, 1.97it/s]\n\n 48%|████▊ | 48/100 [00:30<00:26, 1.97it/s]\u001b[A\n49it [00:30, 1.98it/s]\n\n 49%|████▉ | 49/100 [00:30<00:25, 1.98it/s]\u001b[A\n50it [00:31, 2.00it/s]\n\nTimestep 50 - saving sample\n 50%|█████ | 50/100 [00:31<00:25, 2.00it/s]\u001b[A\n51it [00:32, 1.61it/s]\n\n 51%|█████ | 51/100 [00:32<00:30, 1.61it/s]\u001b[A\n52it [00:32, 1.72it/s]\n\n 52%|█████▏ | 52/100 [00:32<00:27, 1.72it/s]\u001b[A\n53it [00:33, 1.81it/s]\n\n 53%|█████▎ | 53/100 [00:33<00:25, 1.81it/s]\u001b[A\n54it [00:33, 1.87it/s]\n\n 54%|█████▍ | 54/100 [00:33<00:24, 1.87it/s]\u001b[A\n55it [00:34, 1.92it/s]\n\n 55%|█████▌ | 55/100 [00:34<00:23, 1.92it/s]\u001b[A\n56it [00:34, 1.96it/s]\n\n 56%|█████▌ | 56/100 [00:34<00:22, 1.96it/s]\u001b[A\n57it [00:35, 1.99it/s]\n\n 57%|█████▋ | 57/100 [00:35<00:21, 1.99it/s]\u001b[A\n58it [00:35, 2.00it/s]\n\n 58%|█████▊ | 58/100 [00:35<00:20, 2.00it/s]\u001b[A\n59it [00:36, 2.02it/s]\n\n 59%|█████▉ | 59/100 [00:36<00:20, 2.02it/s]\u001b[A\n60it [00:36, 2.03it/s]\n\nTimestep 60 - saving sample\n 60%|██████ | 60/100 [00:36<00:19, 2.03it/s]\u001b[A\n61it [00:37, 1.64it/s]\n\n 61%|██████ | 61/100 [00:37<00:23, 1.64it/s]\u001b[A\n62it [00:38, 1.76it/s]\n\n 62%|██████▏ | 62/100 [00:38<00:21, 1.76it/s]\u001b[A\n63it [00:38, 1.84it/s]\n\n 63%|██████▎ | 63/100 [00:38<00:20, 1.84it/s]\u001b[A\n64it [00:38, 1.91it/s]\n\n 64%|██████▍ | 64/100 [00:38<00:18, 1.91it/s]\u001b[A\n65it [00:39, 1.95it/s]\n\n 65%|██████▌ | 65/100 [00:39<00:17, 1.95it/s]\u001b[A\n66it [00:39, 1.99it/s]\n\n 66%|██████▌ | 66/100 [00:39<00:17, 1.99it/s]\u001b[A\n67it [00:40, 2.01it/s]\n\n 67%|██████▋ | 67/100 [00:40<00:16, 2.01it/s]\u001b[A\n68it [00:40, 2.04it/s]\n\n 68%|██████▊ | 68/100 [00:40<00:15, 2.04it/s]\u001b[A\n69it [00:41, 2.05it/s]\n\n 69%|██████▉ | 69/100 [00:41<00:15, 2.05it/s]\u001b[A\n70it [00:41, 2.07it/s]\n\nTimestep 70 - saving sample\n 70%|███████ | 70/100 [00:41<00:14, 2.07it/s]\u001b[A\n71it [00:42, 1.67it/s]\n\n 71%|███████ | 71/100 [00:42<00:17, 1.67it/s]\u001b[A\n72it [00:43, 1.78it/s]\n\n 72%|███████▏ | 72/100 [00:43<00:15, 1.78it/s]\u001b[A\n73it [00:43, 1.87it/s]\n\n 73%|███████▎ | 73/100 [00:43<00:14, 1.87it/s]\u001b[A\n74it [00:44, 1.93it/s]\n\n 74%|███████▍ | 74/100 [00:44<00:13, 1.93it/s]\u001b[A\n75it [00:44, 1.98it/s]\n\n 75%|███████▌ | 75/100 [00:44<00:12, 1.98it/s]\u001b[A\n76it [00:45, 2.01it/s]\n\n 76%|███████▌ | 76/100 [00:45<00:11, 2.01it/s]\u001b[A\n77it [00:45, 2.04it/s]\n\n 77%|███████▋ | 77/100 [00:45<00:11, 2.04it/s]\u001b[A\n78it [00:46, 2.06it/s]\n\n 78%|███████▊ | 78/100 [00:46<00:10, 2.06it/s]\u001b[A\n79it [00:46, 2.08it/s]\n\n 79%|███████▉ | 79/100 [00:46<00:10, 2.08it/s]\u001b[A\n80it [00:46, 2.09it/s]\n\nTimestep 80 - saving sample\n 80%|████████ | 80/100 [00:46<00:09, 2.09it/s]\u001b[A\n81it [00:47, 1.68it/s]\n\n 81%|████████ | 81/100 [00:47<00:11, 1.68it/s]\u001b[A\n82it [00:48, 1.80it/s]\n\n 82%|████████▏ | 82/100 [00:48<00:10, 1.80it/s]\u001b[A\n83it [00:48, 1.88it/s]\n\n 83%|████████▎ | 83/100 [00:48<00:09, 1.88it/s]\u001b[A\n84it [00:49, 1.95it/s]\n\n 84%|████████▍ | 84/100 [00:49<00:08, 1.95it/s]\u001b[A\n85it [00:49, 2.00it/s]\n\n 85%|████████▌ | 85/100 [00:49<00:07, 2.00it/s]\u001b[A\n86it [00:50, 2.03it/s]\n\n 86%|████████▌ | 86/100 [00:50<00:06, 2.03it/s]\u001b[A\n87it [00:50, 2.06it/s]\n\n 87%|████████▋ | 87/100 [00:50<00:06, 2.06it/s]\u001b[A\n88it [00:51, 2.08it/s]\n\n 88%|████████▊ | 88/100 [00:51<00:05, 2.08it/s]\u001b[A\n89it [00:51, 2.10it/s]\n\n 89%|████████▉ | 89/100 [00:51<00:05, 2.10it/s]\u001b[A\n90it [00:52, 2.10it/s]\n\nTimestep 90 - saving sample\n 90%|█████████ | 90/100 [00:52<00:04, 2.10it/s]\u001b[A\n91it [00:52, 1.69it/s]\n\n 91%|█████████ | 91/100 [00:52<00:05, 1.69it/s]\u001b[A\n92it [00:53, 1.81it/s]\n\n 92%|█████████▏| 92/100 [00:53<00:04, 1.81it/s]\u001b[A\n93it [00:53, 1.90it/s]\n\n 93%|█████████▎| 93/100 [00:53<00:03, 1.90it/s]\u001b[A\n94it [00:54, 1.96it/s]\n\n 94%|█████████▍| 94/100 [00:54<00:03, 1.96it/s]\u001b[A\n95it [00:54, 2.01it/s]\n\n 95%|█████████▌| 95/100 [00:54<00:02, 2.01it/s]\u001b[A\n96it [00:55, 2.05it/s]\n\n 96%|█████████▌| 96/100 [00:55<00:01, 2.05it/s]\u001b[A\n97it [00:55, 2.08it/s]\n\n 97%|█████████▋| 97/100 [00:55<00:01, 2.08it/s]\u001b[A\n98it [00:56, 2.10it/s]\n\n 98%|█████████▊| 98/100 [00:56<00:00, 2.10it/s]\u001b[A\n99it [00:56, 2.11it/s]\n\nTimestep 99 - saving final sample\n 99%|█████████▉| 99/100 [00:56<00:00, 2.11it/s]\u001b[A\n100it [00:57, 1.70it/s]\n\n100%|██████████| 100/100 [00:57<00:00, 1.70it/s]\u001b[A\n100%|██████████| 100/100 [00:57<00:00, 1.74it/s]\n\n100it [00:57, 1.74it/s]", "metrics": { "predict_time": 60.32768, "total_time": 60.476302 }, "output": [ [ "https://replicate.delivery/mgxm/9353d053-81a7-45cf-8a74-bb90f4079115/current_0.jpg", "https://replicate.delivery/mgxm/8ed00b10-709e-4e49-88e3-d668997a6981/current_1.jpg", "https://replicate.delivery/mgxm/9b80506b-c375-4e0f-bee8-8443789e4018/current_2.jpg" ], [ "https://replicate.delivery/mgxm/a9b76357-22cc-4c70-b824-517ac86bf469/current_0.jpg", "https://replicate.delivery/mgxm/a37b8810-3420-40f9-8e7f-37d386794cfd/current_1.jpg", "https://replicate.delivery/mgxm/9f7b1277-e14a-402b-bac3-e18ac1d86a00/current_2.jpg" ], [ "https://replicate.delivery/mgxm/fa4c7166-ed00-4d6f-82f3-e7d8387ea59d/current_0.jpg", "https://replicate.delivery/mgxm/94cff6ce-fd73-4b5d-a127-2c1edb6217d7/current_1.jpg", "https://replicate.delivery/mgxm/8783659d-8242-40bf-8317-6cf6fa65c394/current_2.jpg" ], [ "https://replicate.delivery/mgxm/da74c322-b33b-4f76-b837-8a34b2fb0ade/current_0.jpg", "https://replicate.delivery/mgxm/4dd71239-2fe0-4ebe-ba53-6a7d1e6b35a6/current_1.jpg", "https://replicate.delivery/mgxm/a02c25b0-ce30-469a-b822-ce04e6236a93/current_2.jpg" ], [ "https://replicate.delivery/mgxm/025e8f3d-bacb-4d54-88dd-69b5ddb5edbe/current_0.jpg", "https://replicate.delivery/mgxm/b2e8a2a0-ff27-4a47-8a4e-3438f89b131d/current_1.jpg", "https://replicate.delivery/mgxm/31874e33-57cf-43fb-8966-8cf9dee52175/current_2.jpg" ], [ "https://replicate.delivery/mgxm/e0b9fdd6-824d-4eaf-b810-ca8acfba2a29/current_0.jpg", "https://replicate.delivery/mgxm/978aa7b0-b21c-4b1f-9b67-e0e6a57bac60/current_1.jpg", "https://replicate.delivery/mgxm/20eebe0c-bef3-4448-8d9b-1624da68892e/current_2.jpg" ], [ "https://replicate.delivery/mgxm/350e6127-192d-4fdf-92d5-2929c65a3875/current_0.jpg", "https://replicate.delivery/mgxm/a1d3db1f-57e8-4999-b9a6-a42982f2bbad/current_1.jpg", "https://replicate.delivery/mgxm/443f96cb-752e-45c8-b384-5693468ff4de/current_2.jpg" ], [ "https://replicate.delivery/mgxm/f250dc45-3546-4baa-a3cc-7ac453cd7424/current_0.jpg", "https://replicate.delivery/mgxm/44d6c554-93e6-4bfe-b729-38177ef0503f/current_1.jpg", "https://replicate.delivery/mgxm/312561c5-5b6e-4d6c-a11a-8111285cae96/current_2.jpg" ], [ "https://replicate.delivery/mgxm/bcf82116-bab9-45f2-bc20-821c04c74029/current_0.jpg", "https://replicate.delivery/mgxm/13efbc35-99b6-4700-872e-17b16cb4fa9b/current_1.jpg", "https://replicate.delivery/mgxm/b30623f5-1cc3-483d-b358-c0f59bb3a978/current_2.jpg" ], [ "https://replicate.delivery/mgxm/9612dde2-2e28-4e25-95ec-f8bbf98b6e93/current_0.jpg", "https://replicate.delivery/mgxm/880166d2-44db-4e31-aa1a-f3e36f626d3c/current_1.jpg", "https://replicate.delivery/mgxm/d2d3d4c3-a3b7-41f0-be0c-cb03ef9212d2/current_2.jpg" ], [ "https://replicate.delivery/mgxm/641c2320-4d9f-4a7b-bc3f-bcd225f70eee/current_0.jpg", "https://replicate.delivery/mgxm/b46093ec-2abd-49b0-aea5-1e2dc7421ee5/current_1.jpg", "https://replicate.delivery/mgxm/21dfe26e-7782-4242-a33c-142721f40b37/current_2.jpg" ] ], "started_at": "2022-06-24T23:09:08.644344Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/lvc2nt4xu5emlkxffo7hp6f2py", "cancel": "https://api.replicate.com/v1/predictions/lvc2nt4xu5emlkxffo7hp6f2py/cancel" }, "version": "41ad32228705648d785fc33be19d98dfa058cfd59d1f9a7c2248757e3652cdf6" }
Generated inUsing seed 3823169816 Running simulation for bunny rabbit in style of van gogh Encoding text embeddings with bunny rabbit in style of van gogh dimensions Using aesthetic embedding 8 with weight 0.1 Using inpaint model but no image is provided. Initializing with zeros. Running diffusion... 0it [00:00, ?it/s] Timestep 0 - saving sample 0%| | 0/100 [00:00<?, ?it/s] 1it [00:02, 2.33s/it] 1%| | 1/100 [00:02<03:51, 2.33s/it] 2it [00:04, 2.09s/it] 2%|▏ | 2/100 [00:04<03:24, 2.09s/it] 3it [00:06, 2.02s/it] 3%|▎ | 3/100 [00:06<03:15, 2.02s/it] 4it [00:06, 1.42s/it] 4%|▍ | 4/100 [00:06<02:15, 1.42s/it] 5it [00:07, 1.08s/it] 5%|▌ | 5/100 [00:07<01:42, 1.08s/it] 6it [00:07, 1.14it/s] 6%|▌ | 6/100 [00:07<01:22, 1.14it/s] 7it [00:08, 1.33it/s] 7%|▋ | 7/100 [00:08<01:09, 1.33it/s] 8it [00:08, 1.49it/s] 8%|▊ | 8/100 [00:08<01:01, 1.49it/s] 9it [00:09, 1.63it/s] 9%|▉ | 9/100 [00:09<00:55, 1.63it/s] 10it [00:09, 1.73it/s] Timestep 10 - saving sample 10%|█ | 10/100 [00:09<00:51, 1.73it/s] 11it [00:10, 1.48it/s] 11%|█ | 11/100 [00:10<01:00, 1.48it/s] 12it [00:11, 1.61it/s] 12%|█▏ | 12/100 [00:11<00:54, 1.61it/s] 13it [00:11, 1.71it/s] 13%|█▎ | 13/100 [00:11<00:50, 1.71it/s] 14it [00:12, 1.80it/s] 14%|█▍ | 14/100 [00:12<00:47, 1.80it/s] 15it [00:12, 1.85it/s] 15%|█▌ | 15/100 [00:12<00:45, 1.85it/s] 16it [00:13, 1.89it/s] 16%|█▌ | 16/100 [00:13<00:44, 1.89it/s] 17it [00:13, 1.92it/s] 17%|█▋ | 17/100 [00:13<00:43, 1.92it/s] 18it [00:14, 1.93it/s] 18%|█▊ | 18/100 [00:14<00:42, 1.93it/s] 19it [00:14, 1.95it/s] 19%|█▉ | 19/100 [00:14<00:41, 1.95it/s] 20it [00:15, 1.96it/s] Timestep 20 - saving sample 20%|██ | 20/100 [00:15<00:40, 1.96it/s] 21it [00:15, 1.58it/s] 21%|██ | 21/100 [00:15<00:50, 1.58it/s] 22it [00:16, 1.69it/s] 22%|██▏ | 22/100 [00:16<00:46, 1.69it/s] 23it [00:16, 1.77it/s] 23%|██▎ | 23/100 [00:16<00:43, 1.77it/s] 24it [00:17, 1.82it/s] 24%|██▍ | 24/100 [00:17<00:41, 1.82it/s] 25it [00:17, 1.87it/s] 25%|██▌ | 25/100 [00:17<00:40, 1.87it/s] 26it [00:18, 1.90it/s] 26%|██▌ | 26/100 [00:18<00:39, 1.90it/s] 27it [00:18, 1.92it/s] 27%|██▋ | 27/100 [00:18<00:38, 1.92it/s] 28it [00:19, 1.93it/s] 28%|██▊ | 28/100 [00:19<00:37, 1.93it/s] 29it [00:20, 1.93it/s] 29%|██▉ | 29/100 [00:20<00:36, 1.93it/s] 30it [00:20, 1.95it/s] Timestep 30 - saving sample 30%|███ | 30/100 [00:20<00:35, 1.95it/s] 31it [00:21, 1.57it/s] 31%|███ | 31/100 [00:21<00:43, 1.57it/s] 32it [00:21, 1.67it/s] 32%|███▏ | 32/100 [00:21<00:40, 1.67it/s] 33it [00:22, 1.75it/s] 33%|███▎ | 33/100 [00:22<00:38, 1.75it/s] 34it [00:22, 1.81it/s] 34%|███▍ | 34/100 [00:22<00:36, 1.81it/s] 35it [00:23, 1.86it/s] 35%|███▌ | 35/100 [00:23<00:35, 1.86it/s] 36it [00:23, 1.89it/s] 36%|███▌ | 36/100 [00:23<00:33, 1.89it/s] 37it [00:24, 1.92it/s] 37%|███▋ | 37/100 [00:24<00:32, 1.92it/s] 38it [00:24, 1.93it/s] 38%|███▊ | 38/100 [00:24<00:32, 1.93it/s] 39it [00:25, 1.95it/s] 39%|███▉ | 39/100 [00:25<00:31, 1.95it/s] 40it [00:25, 1.96it/s] Timestep 40 - saving sample 40%|████ | 40/100 [00:25<00:30, 1.96it/s] 41it [00:26, 1.58it/s] 41%|████ | 41/100 [00:26<00:37, 1.58it/s] 42it [00:27, 1.70it/s] 42%|████▏ | 42/100 [00:27<00:34, 1.70it/s] 43it [00:27, 1.78it/s] 43%|████▎ | 43/100 [00:27<00:32, 1.78it/s] 44it [00:28, 1.84it/s] 44%|████▍ | 44/100 [00:28<00:30, 1.84it/s] 45it [00:28, 1.89it/s] 45%|████▌ | 45/100 [00:28<00:29, 1.89it/s] 46it [00:29, 1.93it/s] 46%|████▌ | 46/100 [00:29<00:28, 1.93it/s] 47it [00:29, 1.95it/s] 47%|████▋ | 47/100 [00:29<00:27, 1.95it/s] 48it [00:30, 1.97it/s] 48%|████▊ | 48/100 [00:30<00:26, 1.97it/s] 49it [00:30, 1.98it/s] 49%|████▉ | 49/100 [00:30<00:25, 1.98it/s] 50it [00:31, 2.00it/s] Timestep 50 - saving sample 50%|█████ | 50/100 [00:31<00:25, 2.00it/s] 51it [00:32, 1.61it/s] 51%|█████ | 51/100 [00:32<00:30, 1.61it/s] 52it [00:32, 1.72it/s] 52%|█████▏ | 52/100 [00:32<00:27, 1.72it/s] 53it [00:33, 1.81it/s] 53%|█████▎ | 53/100 [00:33<00:25, 1.81it/s] 54it [00:33, 1.87it/s] 54%|█████▍ | 54/100 [00:33<00:24, 1.87it/s] 55it [00:34, 1.92it/s] 55%|█████▌ | 55/100 [00:34<00:23, 1.92it/s] 56it [00:34, 1.96it/s] 56%|█████▌ | 56/100 [00:34<00:22, 1.96it/s] 57it [00:35, 1.99it/s] 57%|█████▋ | 57/100 [00:35<00:21, 1.99it/s] 58it [00:35, 2.00it/s] 58%|█████▊ | 58/100 [00:35<00:20, 2.00it/s] 59it [00:36, 2.02it/s] 59%|█████▉ | 59/100 [00:36<00:20, 2.02it/s] 60it [00:36, 2.03it/s] Timestep 60 - saving sample 60%|██████ | 60/100 [00:36<00:19, 2.03it/s] 61it [00:37, 1.64it/s] 61%|██████ | 61/100 [00:37<00:23, 1.64it/s] 62it [00:38, 1.76it/s] 62%|██████▏ | 62/100 [00:38<00:21, 1.76it/s] 63it [00:38, 1.84it/s] 63%|██████▎ | 63/100 [00:38<00:20, 1.84it/s] 64it [00:38, 1.91it/s] 64%|██████▍ | 64/100 [00:38<00:18, 1.91it/s] 65it [00:39, 1.95it/s] 65%|██████▌ | 65/100 [00:39<00:17, 1.95it/s] 66it [00:39, 1.99it/s] 66%|██████▌ | 66/100 [00:39<00:17, 1.99it/s] 67it [00:40, 2.01it/s] 67%|██████▋ | 67/100 [00:40<00:16, 2.01it/s] 68it [00:40, 2.04it/s] 68%|██████▊ | 68/100 [00:40<00:15, 2.04it/s] 69it [00:41, 2.05it/s] 69%|██████▉ | 69/100 [00:41<00:15, 2.05it/s] 70it [00:41, 2.07it/s] Timestep 70 - saving sample 70%|███████ | 70/100 [00:41<00:14, 2.07it/s] 71it [00:42, 1.67it/s] 71%|███████ | 71/100 [00:42<00:17, 1.67it/s] 72it [00:43, 1.78it/s] 72%|███████▏ | 72/100 [00:43<00:15, 1.78it/s] 73it [00:43, 1.87it/s] 73%|███████▎ | 73/100 [00:43<00:14, 1.87it/s] 74it [00:44, 1.93it/s] 74%|███████▍ | 74/100 [00:44<00:13, 1.93it/s] 75it [00:44, 1.98it/s] 75%|███████▌ | 75/100 [00:44<00:12, 1.98it/s] 76it [00:45, 2.01it/s] 76%|███████▌ | 76/100 [00:45<00:11, 2.01it/s] 77it [00:45, 2.04it/s] 77%|███████▋ | 77/100 [00:45<00:11, 2.04it/s] 78it [00:46, 2.06it/s] 78%|███████▊ | 78/100 [00:46<00:10, 2.06it/s] 79it [00:46, 2.08it/s] 79%|███████▉ | 79/100 [00:46<00:10, 2.08it/s] 80it [00:46, 2.09it/s] Timestep 80 - saving sample 80%|████████ | 80/100 [00:46<00:09, 2.09it/s] 81it [00:47, 1.68it/s] 81%|████████ | 81/100 [00:47<00:11, 1.68it/s] 82it [00:48, 1.80it/s] 82%|████████▏ | 82/100 [00:48<00:10, 1.80it/s] 83it [00:48, 1.88it/s] 83%|████████▎ | 83/100 [00:48<00:09, 1.88it/s] 84it [00:49, 1.95it/s] 84%|████████▍ | 84/100 [00:49<00:08, 1.95it/s] 85it [00:49, 2.00it/s] 85%|████████▌ | 85/100 [00:49<00:07, 2.00it/s] 86it [00:50, 2.03it/s] 86%|████████▌ | 86/100 [00:50<00:06, 2.03it/s] 87it [00:50, 2.06it/s] 87%|████████▋ | 87/100 [00:50<00:06, 2.06it/s] 88it [00:51, 2.08it/s] 88%|████████▊ | 88/100 [00:51<00:05, 2.08it/s] 89it [00:51, 2.10it/s] 89%|████████▉ | 89/100 [00:51<00:05, 2.10it/s] 90it [00:52, 2.10it/s] Timestep 90 - saving sample 90%|█████████ | 90/100 [00:52<00:04, 2.10it/s] 91it [00:52, 1.69it/s] 91%|█████████ | 91/100 [00:52<00:05, 1.69it/s] 92it [00:53, 1.81it/s] 92%|█████████▏| 92/100 [00:53<00:04, 1.81it/s] 93it [00:53, 1.90it/s] 93%|█████████▎| 93/100 [00:53<00:03, 1.90it/s] 94it [00:54, 1.96it/s] 94%|█████████▍| 94/100 [00:54<00:03, 1.96it/s] 95it [00:54, 2.01it/s] 95%|█████████▌| 95/100 [00:54<00:02, 2.01it/s] 96it [00:55, 2.05it/s] 96%|█████████▌| 96/100 [00:55<00:01, 2.05it/s] 97it [00:55, 2.08it/s] 97%|█████████▋| 97/100 [00:55<00:01, 2.08it/s] 98it [00:56, 2.10it/s] 98%|█████████▊| 98/100 [00:56<00:00, 2.10it/s] 99it [00:56, 2.11it/s] Timestep 99 - saving final sample 99%|█████████▉| 99/100 [00:56<00:00, 2.11it/s] 100it [00:57, 1.70it/s] 100%|██████████| 100/100 [00:57<00:00, 1.70it/s] 100%|██████████| 100/100 [00:57<00:00, 1.74it/s] 100it [00:57, 1.74it/s]
Prediction
laion-ai/ongo:1b3cd151IDsn5d222eajgo7piqrsp5arjz3yStatusSucceededSourceWebHardware–Total durationCreatedInput
- seed
- -1
- steps
- "100"
- width
- 256
- height
- 256
- prompt
- a farmhouse surrounded by flowers painting
- batch_size
- "4"
- guidance_scale
- 5
- aesthetic_rating
- 8
- aesthetic_weight
- 0.1
{ "seed": -1, "steps": "100", "width": 256, "height": 256, "prompt": "a farmhouse surrounded by flowers painting", "batch_size": "4", "guidance_scale": 5, "aesthetic_rating": 8, "aesthetic_weight": 0.1 }
Install Replicate’s Node.js client library:npm install replicate
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run laion-ai/ongo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "laion-ai/ongo:1b3cd15121ec450baa71bbbdacddef9217519f12ca12ccfef36eeaa20ad89b9d", { input: { seed: -1, steps: "100", width: 256, height: 256, prompt: "a farmhouse surrounded by flowers painting", batch_size: "4", guidance_scale: 5, aesthetic_rating: 8, aesthetic_weight: 0.1 } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the client:import replicate
Run laion-ai/ongo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "laion-ai/ongo:1b3cd15121ec450baa71bbbdacddef9217519f12ca12ccfef36eeaa20ad89b9d", input={ "seed": -1, "steps": "100", "width": 256, "height": 256, "prompt": "a farmhouse surrounded by flowers painting", "batch_size": "4", "guidance_scale": 5, "aesthetic_rating": 8, "aesthetic_weight": 0.1 } ) # The laion-ai/ongo model can stream output as it's running. # The predict method returns an iterator, and you can iterate over that output. for item in output: # https://replicate.com/laion-ai/ongo/api#output-schema print(item)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run laion-ai/ongo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "1b3cd15121ec450baa71bbbdacddef9217519f12ca12ccfef36eeaa20ad89b9d", "input": { "seed": -1, "steps": "100", "width": 256, "height": 256, "prompt": "a farmhouse surrounded by flowers painting", "batch_size": "4", "guidance_scale": 5, "aesthetic_rating": 8, "aesthetic_weight": 0.1 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2022-06-28T15:15:11.018622Z", "created_at": "2022-06-28T15:14:05.514142Z", "data_removed": false, "error": null, "id": "sn5d222eajgo7piqrsp5arjz3y", "input": { "seed": -1, "steps": "100", "width": 256, "height": 256, "prompt": "a farmhouse surrounded by flowers painting", "batch_size": "4", "guidance_scale": 5, "aesthetic_rating": 8, "aesthetic_weight": 0.1 }, "logs": "Using seed 1629174958\nRunning simulation for a farmhouse surrounded by flowers painting\nEncoding text embeddings with a farmhouse surrounded by flowers painting dimensions\nUsing aesthetic embedding 8 with weight 0.1\nUsing inpaint model but no image is provided. Initializing with zeros.\nRunning diffusion...\n\n 0%| | 0/100 [00:00<?, ?it/s]\n 1%| | 1/100 [00:00<01:33, 1.06it/s]\n 2%|▏ | 2/100 [00:01<01:24, 1.17it/s]\n 3%|▎ | 3/100 [00:02<01:20, 1.20it/s]\n 4%|▍ | 4/100 [00:02<00:56, 1.71it/s]\n 5%|▌ | 5/100 [00:02<00:42, 2.24it/s]\n 6%|▌ | 6/100 [00:03<00:34, 2.76it/s]\n 7%|▋ | 7/100 [00:03<00:28, 3.24it/s]\n 8%|▊ | 8/100 [00:03<00:25, 3.64it/s]\n 9%|▉ | 9/100 [00:03<00:22, 3.98it/s]\n 10%|█ | 10/100 [00:03<00:21, 4.24it/s]\n 11%|█ | 11/100 [00:04<00:20, 4.44it/s]\n 12%|█▏ | 12/100 [00:04<00:19, 4.58it/s]\n 13%|█▎ | 13/100 [00:04<00:18, 4.67it/s]\n 14%|█▍ | 14/100 [00:04<00:18, 4.75it/s]\n 15%|█▌ | 15/100 [00:04<00:17, 4.82it/s]\n 16%|█▌ | 16/100 [00:05<00:17, 4.85it/s]\n 17%|█▋ | 17/100 [00:05<00:17, 4.87it/s]\n 18%|█▊ | 18/100 [00:05<00:16, 4.89it/s]\n 19%|█▉ | 19/100 [00:05<00:16, 4.90it/s]\n 20%|██ | 20/100 [00:05<00:16, 4.93it/s]\n 21%|██ | 21/100 [00:06<00:16, 4.92it/s]\n 22%|██▏ | 22/100 [00:06<00:15, 4.92it/s]\n 23%|██▎ | 23/100 [00:06<00:15, 4.93it/s]\n 24%|██▍ | 24/100 [00:06<00:15, 4.93it/s]\n 25%|██▌ | 25/100 [00:06<00:15, 4.93it/s]\n 26%|██▌ | 26/100 [00:07<00:15, 4.93it/s]\n 27%|██▋ | 27/100 [00:07<00:14, 4.92it/s]\n 28%|██▊ | 28/100 [00:07<00:14, 4.93it/s]\n 29%|██▉ | 29/100 [00:07<00:14, 4.93it/s]\n 30%|███ | 30/100 [00:08<00:14, 4.93it/s]\n 31%|███ | 31/100 [00:08<00:13, 4.93it/s]\n 32%|███▏ | 32/100 [00:08<00:13, 4.93it/s]\n 33%|███▎ | 33/100 [00:08<00:13, 4.93it/s]\n 34%|███▍ | 34/100 [00:08<00:13, 4.93it/s]\n 35%|███▌ | 35/100 [00:09<00:13, 4.93it/s]\n 36%|███▌ | 36/100 [00:09<00:12, 4.94it/s]\n 37%|███▋ | 37/100 [00:09<00:12, 4.94it/s]\n 38%|███▊ | 38/100 [00:09<00:12, 4.93it/s]\n 39%|███▉ | 39/100 [00:09<00:12, 4.94it/s]\n 40%|████ | 40/100 [00:10<00:12, 4.94it/s]\n 41%|████ | 41/100 [00:10<00:11, 4.94it/s]\n 42%|████▏ | 42/100 [00:10<00:11, 4.94it/s]\n 43%|████▎ | 43/100 [00:10<00:11, 4.94it/s]\n 44%|████▍ | 44/100 [00:10<00:11, 4.93it/s]\n 45%|████▌ | 45/100 [00:11<00:11, 4.93it/s]\n 46%|████▌ | 46/100 [00:11<00:10, 4.92it/s]\n 47%|████▋ | 47/100 [00:11<00:10, 4.91it/s]\n 48%|████▊ | 48/100 [00:11<00:10, 4.92it/s]\n 49%|████▉ | 49/100 [00:11<00:10, 4.93it/s]\n 50%|█████ | 50/100 [00:12<00:10, 4.93it/s]\n 51%|█████ | 51/100 [00:12<00:09, 4.93it/s]\n 52%|█████▏ | 52/100 [00:12<00:09, 4.92it/s]\n 53%|█████▎ | 53/100 [00:12<00:09, 4.92it/s]\n 54%|█████▍ | 54/100 [00:12<00:09, 4.94it/s]\n 55%|█████▌ | 55/100 [00:13<00:09, 4.93it/s]\n 56%|█████▌ | 56/100 [00:13<00:08, 4.93it/s]\n 57%|█████▋ | 57/100 [00:13<00:08, 4.92it/s]\n 58%|█████▊ | 58/100 [00:13<00:08, 4.93it/s]\n 59%|█████▉ | 59/100 [00:13<00:08, 4.93it/s]\n 60%|██████ | 60/100 [00:14<00:08, 4.93it/s]\n 61%|██████ | 61/100 [00:14<00:07, 4.92it/s]\n 62%|██████▏ | 62/100 [00:14<00:07, 4.91it/s]\n 63%|██████▎ | 63/100 [00:14<00:07, 4.91it/s]\n 64%|██████▍ | 64/100 [00:14<00:07, 4.90it/s]\n 65%|██████▌ | 65/100 [00:15<00:07, 4.89it/s]\n 66%|██████▌ | 66/100 [00:15<00:06, 4.88it/s]\n 67%|██████▋ | 67/100 [00:15<00:06, 4.88it/s]\n 68%|██████▊ | 68/100 [00:15<00:06, 4.88it/s]\n 69%|██████▉ | 69/100 [00:15<00:06, 4.88it/s]\n 70%|███████ | 70/100 [00:16<00:06, 4.88it/s]\n 71%|███████ | 71/100 [00:16<00:05, 4.89it/s]\n 72%|███████▏ | 72/100 [00:16<00:05, 4.89it/s]\n 73%|███████▎ | 73/100 [00:16<00:05, 4.90it/s]\n 74%|███████▍ | 74/100 [00:16<00:05, 4.89it/s]\n 75%|███████▌ | 75/100 [00:17<00:05, 4.88it/s]\n 76%|███████▌ | 76/100 [00:17<00:04, 4.87it/s]\n 77%|███████▋ | 77/100 [00:17<00:04, 4.86it/s]\n 78%|███████▊ | 78/100 [00:17<00:04, 4.87it/s]\n 79%|███████▉ | 79/100 [00:17<00:04, 4.87it/s]\n 80%|████████ | 80/100 [00:18<00:04, 4.88it/s]\n 81%|████████ | 81/100 [00:18<00:03, 4.89it/s]\n 82%|████████▏ | 82/100 [00:18<00:03, 4.88it/s]\n 83%|████████▎ | 83/100 [00:18<00:03, 4.88it/s]\n 84%|████████▍ | 84/100 [00:19<00:03, 4.87it/s]\n 85%|████████▌ | 85/100 [00:19<00:03, 4.86it/s]\n 86%|████████▌ | 86/100 [00:19<00:02, 4.86it/s]\n 87%|████████▋ | 87/100 [00:19<00:02, 4.86it/s]\n 88%|████████▊ | 88/100 [00:19<00:02, 4.86it/s]\n 89%|████████▉ | 89/100 [00:20<00:02, 4.87it/s]\n 90%|█████████ | 90/100 [00:20<00:02, 4.88it/s]\n 91%|█████████ | 91/100 [00:20<00:01, 4.86it/s]\n 92%|█████████▏| 92/100 [00:20<00:01, 4.86it/s]\n 93%|█████████▎| 93/100 [00:20<00:01, 4.86it/s]\n 94%|█████████▍| 94/100 [00:21<00:01, 4.85it/s]\n 95%|█████████▌| 95/100 [00:21<00:01, 4.86it/s]\n 96%|█████████▌| 96/100 [00:21<00:00, 4.86it/s]\n 97%|█████████▋| 97/100 [00:21<00:00, 4.86it/s]\n 98%|█████████▊| 98/100 [00:21<00:00, 4.86it/s]\nSaving final sample/s\n 99%|█████████▉| 99/100 [00:22<00:00, 4.85it/s]\n100%|██████████| 100/100 [00:22<00:00, 3.24it/s]\n100%|██████████| 100/100 [00:22<00:00, 4.42it/s]", "metrics": { "predict_time": 26.032431, "total_time": 65.50448 }, "output": [ [ "https://replicate.delivery/mgxm/730390c5-9761-44d7-b5d8-eaa7eec9619b/current_0.png", "https://replicate.delivery/mgxm/5d2239c3-acec-492d-9705-1421358f31f5/current_1.png", "https://replicate.delivery/mgxm/d0ab32b5-3e34-48f4-bc02-51c13d554fd2/current_2.png", "https://replicate.delivery/mgxm/02390209-5ec2-4e48-bca8-a3e26ae42e25/current_3.png" ] ], "started_at": "2022-06-28T15:14:44.986191Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/sn5d222eajgo7piqrsp5arjz3y", "cancel": "https://api.replicate.com/v1/predictions/sn5d222eajgo7piqrsp5arjz3y/cancel" }, "version": "13e4da486d56b62616baf8d6233ffd2c09ad534af3e8d55cba4356be2be6ad84" }
Generated inUsing seed 1629174958 Running simulation for a farmhouse surrounded by flowers painting Encoding text embeddings with a farmhouse surrounded by flowers painting dimensions Using aesthetic embedding 8 with weight 0.1 Using inpaint model but no image is provided. Initializing with zeros. Running diffusion... 0%| | 0/100 [00:00<?, ?it/s] 1%| | 1/100 [00:00<01:33, 1.06it/s] 2%|▏ | 2/100 [00:01<01:24, 1.17it/s] 3%|▎ | 3/100 [00:02<01:20, 1.20it/s] 4%|▍ | 4/100 [00:02<00:56, 1.71it/s] 5%|▌ | 5/100 [00:02<00:42, 2.24it/s] 6%|▌ | 6/100 [00:03<00:34, 2.76it/s] 7%|▋ | 7/100 [00:03<00:28, 3.24it/s] 8%|▊ | 8/100 [00:03<00:25, 3.64it/s] 9%|▉ | 9/100 [00:03<00:22, 3.98it/s] 10%|█ | 10/100 [00:03<00:21, 4.24it/s] 11%|█ | 11/100 [00:04<00:20, 4.44it/s] 12%|█▏ | 12/100 [00:04<00:19, 4.58it/s] 13%|█▎ | 13/100 [00:04<00:18, 4.67it/s] 14%|█▍ | 14/100 [00:04<00:18, 4.75it/s] 15%|█▌ | 15/100 [00:04<00:17, 4.82it/s] 16%|█▌ | 16/100 [00:05<00:17, 4.85it/s] 17%|█▋ | 17/100 [00:05<00:17, 4.87it/s] 18%|█▊ | 18/100 [00:05<00:16, 4.89it/s] 19%|█▉ | 19/100 [00:05<00:16, 4.90it/s] 20%|██ | 20/100 [00:05<00:16, 4.93it/s] 21%|██ | 21/100 [00:06<00:16, 4.92it/s] 22%|██▏ | 22/100 [00:06<00:15, 4.92it/s] 23%|██▎ | 23/100 [00:06<00:15, 4.93it/s] 24%|██▍ | 24/100 [00:06<00:15, 4.93it/s] 25%|██▌ | 25/100 [00:06<00:15, 4.93it/s] 26%|██▌ | 26/100 [00:07<00:15, 4.93it/s] 27%|██▋ | 27/100 [00:07<00:14, 4.92it/s] 28%|██▊ | 28/100 [00:07<00:14, 4.93it/s] 29%|██▉ | 29/100 [00:07<00:14, 4.93it/s] 30%|███ | 30/100 [00:08<00:14, 4.93it/s] 31%|███ | 31/100 [00:08<00:13, 4.93it/s] 32%|███▏ | 32/100 [00:08<00:13, 4.93it/s] 33%|███▎ | 33/100 [00:08<00:13, 4.93it/s] 34%|███▍ | 34/100 [00:08<00:13, 4.93it/s] 35%|███▌ | 35/100 [00:09<00:13, 4.93it/s] 36%|███▌ | 36/100 [00:09<00:12, 4.94it/s] 37%|███▋ | 37/100 [00:09<00:12, 4.94it/s] 38%|███▊ | 38/100 [00:09<00:12, 4.93it/s] 39%|███▉ | 39/100 [00:09<00:12, 4.94it/s] 40%|████ | 40/100 [00:10<00:12, 4.94it/s] 41%|████ | 41/100 [00:10<00:11, 4.94it/s] 42%|████▏ | 42/100 [00:10<00:11, 4.94it/s] 43%|████▎ | 43/100 [00:10<00:11, 4.94it/s] 44%|████▍ | 44/100 [00:10<00:11, 4.93it/s] 45%|████▌ | 45/100 [00:11<00:11, 4.93it/s] 46%|████▌ | 46/100 [00:11<00:10, 4.92it/s] 47%|████▋ | 47/100 [00:11<00:10, 4.91it/s] 48%|████▊ | 48/100 [00:11<00:10, 4.92it/s] 49%|████▉ | 49/100 [00:11<00:10, 4.93it/s] 50%|█████ | 50/100 [00:12<00:10, 4.93it/s] 51%|█████ | 51/100 [00:12<00:09, 4.93it/s] 52%|█████▏ | 52/100 [00:12<00:09, 4.92it/s] 53%|█████▎ | 53/100 [00:12<00:09, 4.92it/s] 54%|█████▍ | 54/100 [00:12<00:09, 4.94it/s] 55%|█████▌ | 55/100 [00:13<00:09, 4.93it/s] 56%|█████▌ | 56/100 [00:13<00:08, 4.93it/s] 57%|█████▋ | 57/100 [00:13<00:08, 4.92it/s] 58%|█████▊ | 58/100 [00:13<00:08, 4.93it/s] 59%|█████▉ | 59/100 [00:13<00:08, 4.93it/s] 60%|██████ | 60/100 [00:14<00:08, 4.93it/s] 61%|██████ | 61/100 [00:14<00:07, 4.92it/s] 62%|██████▏ | 62/100 [00:14<00:07, 4.91it/s] 63%|██████▎ | 63/100 [00:14<00:07, 4.91it/s] 64%|██████▍ | 64/100 [00:14<00:07, 4.90it/s] 65%|██████▌ | 65/100 [00:15<00:07, 4.89it/s] 66%|██████▌ | 66/100 [00:15<00:06, 4.88it/s] 67%|██████▋ | 67/100 [00:15<00:06, 4.88it/s] 68%|██████▊ | 68/100 [00:15<00:06, 4.88it/s] 69%|██████▉ | 69/100 [00:15<00:06, 4.88it/s] 70%|███████ | 70/100 [00:16<00:06, 4.88it/s] 71%|███████ | 71/100 [00:16<00:05, 4.89it/s] 72%|███████▏ | 72/100 [00:16<00:05, 4.89it/s] 73%|███████▎ | 73/100 [00:16<00:05, 4.90it/s] 74%|███████▍ | 74/100 [00:16<00:05, 4.89it/s] 75%|███████▌ | 75/100 [00:17<00:05, 4.88it/s] 76%|███████▌ | 76/100 [00:17<00:04, 4.87it/s] 77%|███████▋ | 77/100 [00:17<00:04, 4.86it/s] 78%|███████▊ | 78/100 [00:17<00:04, 4.87it/s] 79%|███████▉ | 79/100 [00:17<00:04, 4.87it/s] 80%|████████ | 80/100 [00:18<00:04, 4.88it/s] 81%|████████ | 81/100 [00:18<00:03, 4.89it/s] 82%|████████▏ | 82/100 [00:18<00:03, 4.88it/s] 83%|████████▎ | 83/100 [00:18<00:03, 4.88it/s] 84%|████████▍ | 84/100 [00:19<00:03, 4.87it/s] 85%|████████▌ | 85/100 [00:19<00:03, 4.86it/s] 86%|████████▌ | 86/100 [00:19<00:02, 4.86it/s] 87%|████████▋ | 87/100 [00:19<00:02, 4.86it/s] 88%|████████▊ | 88/100 [00:19<00:02, 4.86it/s] 89%|████████▉ | 89/100 [00:20<00:02, 4.87it/s] 90%|█████████ | 90/100 [00:20<00:02, 4.88it/s] 91%|█████████ | 91/100 [00:20<00:01, 4.86it/s] 92%|█████████▏| 92/100 [00:20<00:01, 4.86it/s] 93%|█████████▎| 93/100 [00:20<00:01, 4.86it/s] 94%|█████████▍| 94/100 [00:21<00:01, 4.85it/s] 95%|█████████▌| 95/100 [00:21<00:01, 4.86it/s] 96%|█████████▌| 96/100 [00:21<00:00, 4.86it/s] 97%|█████████▋| 97/100 [00:21<00:00, 4.86it/s] 98%|█████████▊| 98/100 [00:21<00:00, 4.86it/s] Saving final sample/s 99%|█████████▉| 99/100 [00:22<00:00, 4.85it/s] 100%|██████████| 100/100 [00:22<00:00, 3.24it/s] 100%|██████████| 100/100 [00:22<00:00, 4.42it/s]
Prediction
laion-ai/ongo:1b3cd151IDjjyhoiplyrc67kvn5ceumuatuqStatusSucceededSourceWebHardware–Total durationCreatedInput
- seed
- -1
- steps
- "100"
- width
- 256
- height
- 256
- prompt
- a farmhouse surrounded by flowers painting
- batch_size
- "4"
- guidance_scale
- 5
- aesthetic_rating
- 8
- aesthetic_weight
- 0.5
{ "seed": -1, "steps": "100", "width": 256, "height": 256, "prompt": "a farmhouse surrounded by flowers painting", "batch_size": "4", "guidance_scale": 5, "aesthetic_rating": 8, "aesthetic_weight": 0.5 }
Install Replicate’s Node.js client library:npm install replicate
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run laion-ai/ongo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "laion-ai/ongo:1b3cd15121ec450baa71bbbdacddef9217519f12ca12ccfef36eeaa20ad89b9d", { input: { seed: -1, steps: "100", width: 256, height: 256, prompt: "a farmhouse surrounded by flowers painting", batch_size: "4", guidance_scale: 5, aesthetic_rating: 8, aesthetic_weight: 0.5 } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the client:import replicate
Run laion-ai/ongo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "laion-ai/ongo:1b3cd15121ec450baa71bbbdacddef9217519f12ca12ccfef36eeaa20ad89b9d", input={ "seed": -1, "steps": "100", "width": 256, "height": 256, "prompt": "a farmhouse surrounded by flowers painting", "batch_size": "4", "guidance_scale": 5, "aesthetic_rating": 8, "aesthetic_weight": 0.5 } ) # The laion-ai/ongo model can stream output as it's running. # The predict method returns an iterator, and you can iterate over that output. for item in output: # https://replicate.com/laion-ai/ongo/api#output-schema print(item)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run laion-ai/ongo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "1b3cd15121ec450baa71bbbdacddef9217519f12ca12ccfef36eeaa20ad89b9d", "input": { "seed": -1, "steps": "100", "width": 256, "height": 256, "prompt": "a farmhouse surrounded by flowers painting", "batch_size": "4", "guidance_scale": 5, "aesthetic_rating": 8, "aesthetic_weight": 0.5 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2022-06-28T15:16:03.473398Z", "created_at": "2022-06-28T15:15:36.528677Z", "data_removed": false, "error": null, "id": "jjyhoiplyrc67kvn5ceumuatuq", "input": { "seed": -1, "steps": "100", "width": 256, "height": 256, "prompt": "a farmhouse surrounded by flowers painting", "batch_size": "4", "guidance_scale": 5, "aesthetic_rating": 8, "aesthetic_weight": 0.5 }, "logs": "Using seed 543616104\nRunning simulation for a farmhouse surrounded by flowers painting\nEncoding text embeddings with a farmhouse surrounded by flowers painting dimensions\nUsing aesthetic embedding 8 with weight 0.5\nUsing inpaint model but no image is provided. Initializing with zeros.\nRunning diffusion...\n\n 0%| | 0/100 [00:00<?, ?it/s]\n 1%| | 1/100 [00:00<01:29, 1.10it/s]\n 2%|▏ | 2/100 [00:01<01:24, 1.16it/s]\n 3%|▎ | 3/100 [00:02<01:21, 1.18it/s]\n 4%|▍ | 4/100 [00:02<00:56, 1.69it/s]\n 5%|▌ | 5/100 [00:02<00:43, 2.20it/s]\n 6%|▌ | 6/100 [00:03<00:34, 2.70it/s]\n 7%|▋ | 7/100 [00:03<00:29, 3.15it/s]\n 8%|▊ | 8/100 [00:03<00:25, 3.54it/s]\n 9%|▉ | 9/100 [00:03<00:23, 3.86it/s]\n 10%|█ | 10/100 [00:04<00:21, 4.13it/s]\n 11%|█ | 11/100 [00:04<00:20, 4.32it/s]\n 12%|█▏ | 12/100 [00:04<00:19, 4.45it/s]\n 13%|█▎ | 13/100 [00:04<00:19, 4.54it/s]\n 14%|█▍ | 14/100 [00:04<00:18, 4.62it/s]\n 15%|█▌ | 15/100 [00:05<00:18, 4.68it/s]\n 16%|█▌ | 16/100 [00:05<00:17, 4.71it/s]\n 17%|█▋ | 17/100 [00:05<00:17, 4.73it/s]\n 18%|█▊ | 18/100 [00:05<00:17, 4.76it/s]\n 19%|█▉ | 19/100 [00:05<00:16, 4.78it/s]\n 20%|██ | 20/100 [00:06<00:16, 4.78it/s]\n 21%|██ | 21/100 [00:06<00:16, 4.79it/s]\n 22%|██▏ | 22/100 [00:06<00:16, 4.79it/s]\n 23%|██▎ | 23/100 [00:06<00:16, 4.80it/s]\n 24%|██▍ | 24/100 [00:06<00:15, 4.80it/s]\n 25%|██▌ | 25/100 [00:07<00:15, 4.79it/s]\n 26%|██▌ | 26/100 [00:07<00:15, 4.79it/s]\n 27%|██▋ | 27/100 [00:07<00:15, 4.78it/s]\n 28%|██▊ | 28/100 [00:07<00:15, 4.77it/s]\n 29%|██▉ | 29/100 [00:07<00:14, 4.79it/s]\n 30%|███ | 30/100 [00:08<00:14, 4.79it/s]\n 31%|███ | 31/100 [00:08<00:14, 4.78it/s]\n 32%|███▏ | 32/100 [00:08<00:14, 4.78it/s]\n 33%|███▎ | 33/100 [00:08<00:14, 4.77it/s]\n 34%|███▍ | 34/100 [00:09<00:13, 4.78it/s]\n 35%|███▌ | 35/100 [00:09<00:13, 4.78it/s]\n 36%|███▌ | 36/100 [00:09<00:13, 4.76it/s]\n 37%|███▋ | 37/100 [00:09<00:13, 4.77it/s]\n 38%|███▊ | 38/100 [00:09<00:13, 4.76it/s]\n 39%|███▉ | 39/100 [00:10<00:12, 4.77it/s]\n 40%|████ | 40/100 [00:10<00:12, 4.76it/s]\n 41%|████ | 41/100 [00:10<00:12, 4.76it/s]\n 42%|████▏ | 42/100 [00:10<00:12, 4.76it/s]\n 43%|████▎ | 43/100 [00:10<00:11, 4.76it/s]\n 44%|████▍ | 44/100 [00:11<00:11, 4.75it/s]\n 45%|████▌ | 45/100 [00:11<00:11, 4.75it/s]\n 46%|████▌ | 46/100 [00:11<00:11, 4.75it/s]\n 47%|████▋ | 47/100 [00:11<00:11, 4.76it/s]\n 48%|████▊ | 48/100 [00:11<00:10, 4.77it/s]\n 49%|████▉ | 49/100 [00:12<00:10, 4.76it/s]\n 50%|█████ | 50/100 [00:12<00:10, 4.75it/s]\n 51%|█████ | 51/100 [00:12<00:10, 4.76it/s]\n 52%|█████▏ | 52/100 [00:12<00:10, 4.75it/s]\n 53%|█████▎ | 53/100 [00:13<00:09, 4.75it/s]\n 54%|█████▍ | 54/100 [00:13<00:09, 4.75it/s]\n 55%|█████▌ | 55/100 [00:13<00:09, 4.74it/s]\n 56%|█████▌ | 56/100 [00:13<00:09, 4.74it/s]\n 57%|█████▋ | 57/100 [00:13<00:09, 4.73it/s]\n 58%|█████▊ | 58/100 [00:14<00:08, 4.74it/s]\n 59%|█████▉ | 59/100 [00:14<00:08, 4.75it/s]\n 60%|██████ | 60/100 [00:14<00:08, 4.74it/s]\n 61%|██████ | 61/100 [00:14<00:08, 4.72it/s]\n 62%|██████▏ | 62/100 [00:14<00:08, 4.73it/s]\n 63%|██████▎ | 63/100 [00:15<00:07, 4.73it/s]\n 64%|██████▍ | 64/100 [00:15<00:07, 4.73it/s]\n 65%|██████▌ | 65/100 [00:15<00:07, 4.71it/s]\n 66%|██████▌ | 66/100 [00:15<00:07, 4.70it/s]\n 67%|██████▋ | 67/100 [00:15<00:06, 4.72it/s]\n 68%|██████▊ | 68/100 [00:16<00:06, 4.72it/s]\n 69%|██████▉ | 69/100 [00:16<00:06, 4.72it/s]\n 70%|███████ | 70/100 [00:16<00:06, 4.71it/s]\n 71%|███████ | 71/100 [00:16<00:06, 4.70it/s]\n 72%|███████▏ | 72/100 [00:17<00:05, 4.71it/s]\n 73%|███████▎ | 73/100 [00:17<00:05, 4.71it/s]\n 74%|███████▍ | 74/100 [00:17<00:05, 4.71it/s]\n 75%|███████▌ | 75/100 [00:17<00:05, 4.71it/s]\n 76%|███████▌ | 76/100 [00:17<00:05, 4.71it/s]\n 77%|███████▋ | 77/100 [00:18<00:04, 4.71it/s]\n 78%|███████▊ | 78/100 [00:18<00:04, 4.71it/s]\n 79%|███████▉ | 79/100 [00:18<00:04, 4.70it/s]\n 80%|████████ | 80/100 [00:18<00:04, 4.70it/s]\n 81%|████████ | 81/100 [00:18<00:04, 4.71it/s]\n 82%|████████▏ | 82/100 [00:19<00:03, 4.71it/s]\n 83%|████████▎ | 83/100 [00:19<00:03, 4.69it/s]\n 84%|████████▍ | 84/100 [00:19<00:03, 4.70it/s]\n 85%|████████▌ | 85/100 [00:19<00:03, 4.69it/s]\n 86%|████████▌ | 86/100 [00:20<00:02, 4.70it/s]\n 87%|████████▋ | 87/100 [00:20<00:02, 4.70it/s]\n 88%|████████▊ | 88/100 [00:20<00:02, 4.69it/s]\n 89%|████████▉ | 89/100 [00:20<00:02, 4.69it/s]\n 90%|█████████ | 90/100 [00:20<00:02, 4.68it/s]\n 91%|█████████ | 91/100 [00:21<00:01, 4.70it/s]\n 92%|█████████▏| 92/100 [00:21<00:01, 4.68it/s]\n 93%|█████████▎| 93/100 [00:21<00:01, 4.68it/s]\n 94%|█████████▍| 94/100 [00:21<00:01, 4.69it/s]\n 95%|█████████▌| 95/100 [00:21<00:01, 4.68it/s]\n 96%|█████████▌| 96/100 [00:22<00:00, 4.68it/s]\n 97%|█████████▋| 97/100 [00:22<00:00, 4.68it/s]\n 98%|█████████▊| 98/100 [00:22<00:00, 4.67it/s]\nSaving final sample/s\n 99%|█████████▉| 99/100 [00:22<00:00, 4.67it/s]\n100%|██████████| 100/100 [00:23<00:00, 3.22it/s]\n100%|██████████| 100/100 [00:23<00:00, 4.29it/s]", "metrics": { "predict_time": 26.790813, "total_time": 26.944721 }, "output": [ [ "https://replicate.delivery/mgxm/2fd95946-7b65-4be9-b57d-993bba097390/current_0.png", "https://replicate.delivery/mgxm/395e8289-9bb5-4f96-becd-d75decfdf069/current_1.png", "https://replicate.delivery/mgxm/c3ae72f7-921d-4408-b7a3-1a8a39536bb3/current_2.png", "https://replicate.delivery/mgxm/0a5eb035-deba-4655-be2c-8305f820883d/current_3.png" ] ], "started_at": "2022-06-28T15:15:36.682585Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/jjyhoiplyrc67kvn5ceumuatuq", "cancel": "https://api.replicate.com/v1/predictions/jjyhoiplyrc67kvn5ceumuatuq/cancel" }, "version": "13e4da486d56b62616baf8d6233ffd2c09ad534af3e8d55cba4356be2be6ad84" }
Generated inUsing seed 543616104 Running simulation for a farmhouse surrounded by flowers painting Encoding text embeddings with a farmhouse surrounded by flowers painting dimensions Using aesthetic embedding 8 with weight 0.5 Using inpaint model but no image is provided. Initializing with zeros. Running diffusion... 0%| | 0/100 [00:00<?, ?it/s] 1%| | 1/100 [00:00<01:29, 1.10it/s] 2%|▏ | 2/100 [00:01<01:24, 1.16it/s] 3%|▎ | 3/100 [00:02<01:21, 1.18it/s] 4%|▍ | 4/100 [00:02<00:56, 1.69it/s] 5%|▌ | 5/100 [00:02<00:43, 2.20it/s] 6%|▌ | 6/100 [00:03<00:34, 2.70it/s] 7%|▋ | 7/100 [00:03<00:29, 3.15it/s] 8%|▊ | 8/100 [00:03<00:25, 3.54it/s] 9%|▉ | 9/100 [00:03<00:23, 3.86it/s] 10%|█ | 10/100 [00:04<00:21, 4.13it/s] 11%|█ | 11/100 [00:04<00:20, 4.32it/s] 12%|█▏ | 12/100 [00:04<00:19, 4.45it/s] 13%|█▎ | 13/100 [00:04<00:19, 4.54it/s] 14%|█▍ | 14/100 [00:04<00:18, 4.62it/s] 15%|█▌ | 15/100 [00:05<00:18, 4.68it/s] 16%|█▌ | 16/100 [00:05<00:17, 4.71it/s] 17%|█▋ | 17/100 [00:05<00:17, 4.73it/s] 18%|█▊ | 18/100 [00:05<00:17, 4.76it/s] 19%|█▉ | 19/100 [00:05<00:16, 4.78it/s] 20%|██ | 20/100 [00:06<00:16, 4.78it/s] 21%|██ | 21/100 [00:06<00:16, 4.79it/s] 22%|██▏ | 22/100 [00:06<00:16, 4.79it/s] 23%|██▎ | 23/100 [00:06<00:16, 4.80it/s] 24%|██▍ | 24/100 [00:06<00:15, 4.80it/s] 25%|██▌ | 25/100 [00:07<00:15, 4.79it/s] 26%|██▌ | 26/100 [00:07<00:15, 4.79it/s] 27%|██▋ | 27/100 [00:07<00:15, 4.78it/s] 28%|██▊ | 28/100 [00:07<00:15, 4.77it/s] 29%|██▉ | 29/100 [00:07<00:14, 4.79it/s] 30%|███ | 30/100 [00:08<00:14, 4.79it/s] 31%|███ | 31/100 [00:08<00:14, 4.78it/s] 32%|███▏ | 32/100 [00:08<00:14, 4.78it/s] 33%|███▎ | 33/100 [00:08<00:14, 4.77it/s] 34%|███▍ | 34/100 [00:09<00:13, 4.78it/s] 35%|███▌ | 35/100 [00:09<00:13, 4.78it/s] 36%|███▌ | 36/100 [00:09<00:13, 4.76it/s] 37%|███▋ | 37/100 [00:09<00:13, 4.77it/s] 38%|███▊ | 38/100 [00:09<00:13, 4.76it/s] 39%|███▉ | 39/100 [00:10<00:12, 4.77it/s] 40%|████ | 40/100 [00:10<00:12, 4.76it/s] 41%|████ | 41/100 [00:10<00:12, 4.76it/s] 42%|████▏ | 42/100 [00:10<00:12, 4.76it/s] 43%|████▎ | 43/100 [00:10<00:11, 4.76it/s] 44%|████▍ | 44/100 [00:11<00:11, 4.75it/s] 45%|████▌ | 45/100 [00:11<00:11, 4.75it/s] 46%|████▌ | 46/100 [00:11<00:11, 4.75it/s] 47%|████▋ | 47/100 [00:11<00:11, 4.76it/s] 48%|████▊ | 48/100 [00:11<00:10, 4.77it/s] 49%|████▉ | 49/100 [00:12<00:10, 4.76it/s] 50%|█████ | 50/100 [00:12<00:10, 4.75it/s] 51%|█████ | 51/100 [00:12<00:10, 4.76it/s] 52%|█████▏ | 52/100 [00:12<00:10, 4.75it/s] 53%|█████▎ | 53/100 [00:13<00:09, 4.75it/s] 54%|█████▍ | 54/100 [00:13<00:09, 4.75it/s] 55%|█████▌ | 55/100 [00:13<00:09, 4.74it/s] 56%|█████▌ | 56/100 [00:13<00:09, 4.74it/s] 57%|█████▋ | 57/100 [00:13<00:09, 4.73it/s] 58%|█████▊ | 58/100 [00:14<00:08, 4.74it/s] 59%|█████▉ | 59/100 [00:14<00:08, 4.75it/s] 60%|██████ | 60/100 [00:14<00:08, 4.74it/s] 61%|██████ | 61/100 [00:14<00:08, 4.72it/s] 62%|██████▏ | 62/100 [00:14<00:08, 4.73it/s] 63%|██████▎ | 63/100 [00:15<00:07, 4.73it/s] 64%|██████▍ | 64/100 [00:15<00:07, 4.73it/s] 65%|██████▌ | 65/100 [00:15<00:07, 4.71it/s] 66%|██████▌ | 66/100 [00:15<00:07, 4.70it/s] 67%|██████▋ | 67/100 [00:15<00:06, 4.72it/s] 68%|██████▊ | 68/100 [00:16<00:06, 4.72it/s] 69%|██████▉ | 69/100 [00:16<00:06, 4.72it/s] 70%|███████ | 70/100 [00:16<00:06, 4.71it/s] 71%|███████ | 71/100 [00:16<00:06, 4.70it/s] 72%|███████▏ | 72/100 [00:17<00:05, 4.71it/s] 73%|███████▎ | 73/100 [00:17<00:05, 4.71it/s] 74%|███████▍ | 74/100 [00:17<00:05, 4.71it/s] 75%|███████▌ | 75/100 [00:17<00:05, 4.71it/s] 76%|███████▌ | 76/100 [00:17<00:05, 4.71it/s] 77%|███████▋ | 77/100 [00:18<00:04, 4.71it/s] 78%|███████▊ | 78/100 [00:18<00:04, 4.71it/s] 79%|███████▉ | 79/100 [00:18<00:04, 4.70it/s] 80%|████████ | 80/100 [00:18<00:04, 4.70it/s] 81%|████████ | 81/100 [00:18<00:04, 4.71it/s] 82%|████████▏ | 82/100 [00:19<00:03, 4.71it/s] 83%|████████▎ | 83/100 [00:19<00:03, 4.69it/s] 84%|████████▍ | 84/100 [00:19<00:03, 4.70it/s] 85%|████████▌ | 85/100 [00:19<00:03, 4.69it/s] 86%|████████▌ | 86/100 [00:20<00:02, 4.70it/s] 87%|████████▋ | 87/100 [00:20<00:02, 4.70it/s] 88%|████████▊ | 88/100 [00:20<00:02, 4.69it/s] 89%|████████▉ | 89/100 [00:20<00:02, 4.69it/s] 90%|█████████ | 90/100 [00:20<00:02, 4.68it/s] 91%|█████████ | 91/100 [00:21<00:01, 4.70it/s] 92%|█████████▏| 92/100 [00:21<00:01, 4.68it/s] 93%|█████████▎| 93/100 [00:21<00:01, 4.68it/s] 94%|█████████▍| 94/100 [00:21<00:01, 4.69it/s] 95%|█████████▌| 95/100 [00:21<00:01, 4.68it/s] 96%|█████████▌| 96/100 [00:22<00:00, 4.68it/s] 97%|█████████▋| 97/100 [00:22<00:00, 4.68it/s] 98%|█████████▊| 98/100 [00:22<00:00, 4.67it/s] Saving final sample/s 99%|█████████▉| 99/100 [00:22<00:00, 4.67it/s] 100%|██████████| 100/100 [00:23<00:00, 3.22it/s] 100%|██████████| 100/100 [00:23<00:00, 4.29it/s]
Prediction
laion-ai/ongo:1b3cd151ID2i2mkiammfcutniml3h5mxew6eStatusSucceededSourceWebHardware–Total durationCreatedInput
- seed
- "-1"
- steps
- "50"
- width
- 256
- height
- 256
- prompt
- a painting of a bunny rabbit
- batch_size
- "4"
- guidance_scale
- "10"
- aesthetic_rating
- 8
- aesthetic_weight
- 0
- intermediate_outputs
{ "mask": "https://replicate.delivery/mgxm/ec781cf6-a641-4d14-a106-7afb9c25694a/circle_mask.png", "seed": "-1", "steps": "50", "width": 256, "height": 256, "prompt": "a painting of a bunny rabbit", "batch_size": "4", "init_image": "https://replicate.delivery/mgxm/c7cfc078-03c0-4d68-adc4-64d5f7247592/current_3.png", "guidance_scale": "10", "aesthetic_rating": 8, "aesthetic_weight": 0, "intermediate_outputs": false }
Install Replicate’s Node.js client library:npm install replicate
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run laion-ai/ongo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "laion-ai/ongo:1b3cd15121ec450baa71bbbdacddef9217519f12ca12ccfef36eeaa20ad89b9d", { input: { mask: "https://replicate.delivery/mgxm/ec781cf6-a641-4d14-a106-7afb9c25694a/circle_mask.png", seed: "-1", steps: "50", width: 256, height: 256, prompt: "a painting of a bunny rabbit", batch_size: "4", init_image: "https://replicate.delivery/mgxm/c7cfc078-03c0-4d68-adc4-64d5f7247592/current_3.png", guidance_scale: "10", aesthetic_rating: 8, aesthetic_weight: 0, intermediate_outputs: false } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the client:import replicate
Run laion-ai/ongo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "laion-ai/ongo:1b3cd15121ec450baa71bbbdacddef9217519f12ca12ccfef36eeaa20ad89b9d", input={ "mask": "https://replicate.delivery/mgxm/ec781cf6-a641-4d14-a106-7afb9c25694a/circle_mask.png", "seed": "-1", "steps": "50", "width": 256, "height": 256, "prompt": "a painting of a bunny rabbit", "batch_size": "4", "init_image": "https://replicate.delivery/mgxm/c7cfc078-03c0-4d68-adc4-64d5f7247592/current_3.png", "guidance_scale": "10", "aesthetic_rating": 8, "aesthetic_weight": 0, "intermediate_outputs": False } ) # The laion-ai/ongo model can stream output as it's running. # The predict method returns an iterator, and you can iterate over that output. for item in output: # https://replicate.com/laion-ai/ongo/api#output-schema print(item)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run laion-ai/ongo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "1b3cd15121ec450baa71bbbdacddef9217519f12ca12ccfef36eeaa20ad89b9d", "input": { "mask": "https://replicate.delivery/mgxm/ec781cf6-a641-4d14-a106-7afb9c25694a/circle_mask.png", "seed": "-1", "steps": "50", "width": 256, "height": 256, "prompt": "a painting of a bunny rabbit", "batch_size": "4", "init_image": "https://replicate.delivery/mgxm/c7cfc078-03c0-4d68-adc4-64d5f7247592/current_3.png", "guidance_scale": "10", "aesthetic_rating": 8, "aesthetic_weight": 0, "intermediate_outputs": false } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2022-06-30T05:23:35.229925Z", "created_at": "2022-06-30T05:23:18.629757Z", "data_removed": false, "error": null, "id": "2i2mkiammfcutniml3h5mxew6e", "input": { "mask": "https://replicate.delivery/mgxm/ec781cf6-a641-4d14-a106-7afb9c25694a/circle_mask.png", "seed": "-1", "steps": "50", "width": 256, "height": 256, "prompt": "a painting of a bunny rabbit", "batch_size": "4", "init_image": "https://replicate.delivery/mgxm/c7cfc078-03c0-4d68-adc4-64d5f7247592/current_3.png", "guidance_scale": "10", "aesthetic_rating": 8, "aesthetic_weight": 0, "intermediate_outputs": false }, "logs": "Using seed 1657459453\nRunning simulation for a painting of a bunny rabbit\nEncoding text embeddings with a painting of a bunny rabbit dimensions\nUsing aesthetic embedding 8 with weight 0.0\nUsing inpaint model with image: /tmp/tmpuop9k19gcurrent_3.png\nRunning diffusion...\n\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:43, 1.12it/s]\n 4%|▍ | 2/50 [00:01<00:41, 1.15it/s]\n 6%|▌ | 3/50 [00:02<00:40, 1.16it/s]\n 8%|▊ | 4/50 [00:02<00:27, 1.65it/s]\n 10%|█ | 5/50 [00:03<00:20, 2.14it/s]\n 12%|█▏ | 6/50 [00:03<00:16, 2.62it/s]\n 14%|█▍ | 7/50 [00:03<00:14, 3.06it/s]\n 16%|█▌ | 8/50 [00:03<00:12, 3.44it/s]\n 18%|█▊ | 9/50 [00:03<00:10, 3.76it/s]\n 20%|██ | 10/50 [00:04<00:10, 3.99it/s]\n 22%|██▏ | 11/50 [00:04<00:09, 4.18it/s]\n 24%|██▍ | 12/50 [00:04<00:08, 4.29it/s]\n 26%|██▌ | 13/50 [00:04<00:08, 4.40it/s]\n 28%|██▊ | 14/50 [00:04<00:08, 4.48it/s]\n 30%|███ | 15/50 [00:05<00:07, 4.53it/s]\n 32%|███▏ | 16/50 [00:05<00:07, 4.57it/s]\n 34%|███▍ | 17/50 [00:05<00:07, 4.59it/s]\n 36%|███▌ | 18/50 [00:05<00:06, 4.61it/s]\n 38%|███▊ | 19/50 [00:06<00:06, 4.62it/s]\n 40%|████ | 20/50 [00:06<00:06, 4.64it/s]\n 42%|████▏ | 21/50 [00:06<00:06, 4.64it/s]\n 44%|████▍ | 22/50 [00:06<00:06, 4.64it/s]\n 46%|████▌ | 23/50 [00:06<00:05, 4.65it/s]\n 48%|████▊ | 24/50 [00:07<00:05, 4.65it/s]\n 50%|█████ | 25/50 [00:07<00:05, 4.64it/s]\n 52%|█████▏ | 26/50 [00:07<00:05, 4.64it/s]\n 54%|█████▍ | 27/50 [00:07<00:04, 4.63it/s]\n 56%|█████▌ | 28/50 [00:07<00:04, 4.63it/s]\n 58%|█████▊ | 29/50 [00:08<00:04, 4.63it/s]\n 60%|██████ | 30/50 [00:08<00:04, 4.64it/s]\n 62%|██████▏ | 31/50 [00:08<00:04, 4.63it/s]\n 64%|██████▍ | 32/50 [00:08<00:03, 4.63it/s]\n 66%|██████▌ | 33/50 [00:09<00:03, 4.63it/s]\n 68%|██████▊ | 34/50 [00:09<00:03, 4.63it/s]\n 70%|███████ | 35/50 [00:09<00:03, 4.63it/s]\n 72%|███████▏ | 36/50 [00:09<00:03, 4.63it/s]\n 74%|███████▍ | 37/50 [00:09<00:02, 4.63it/s]\n 76%|███████▌ | 38/50 [00:10<00:02, 4.63it/s]\n 78%|███████▊ | 39/50 [00:10<00:02, 4.63it/s]\n 80%|████████ | 40/50 [00:10<00:02, 4.64it/s]\n 82%|████████▏ | 41/50 [00:10<00:01, 4.63it/s]\n 84%|████████▍ | 42/50 [00:11<00:01, 4.63it/s]\n 86%|████████▌ | 43/50 [00:11<00:01, 4.63it/s]\n 88%|████████▊ | 44/50 [00:11<00:01, 4.63it/s]\n 90%|█████████ | 45/50 [00:11<00:01, 4.63it/s]\n 92%|█████████▏| 46/50 [00:11<00:00, 4.63it/s]\n 94%|█████████▍| 47/50 [00:12<00:00, 4.62it/s]\n 96%|█████████▌| 48/50 [00:12<00:00, 4.61it/s]\n 98%|█████████▊| 49/50 [00:12<00:00, 4.62it/s]\n100%|██████████| 50/50 [00:12<00:00, 4.63it/s]\n100%|██████████| 50/50 [00:12<00:00, 3.93it/s]\nSaving final sample/s", "metrics": { "predict_time": 16.39406, "total_time": 16.600168 }, "output": [ [ "https://replicate.delivery/mgxm/a74e945b-b463-4390-966f-066f6785333a/current_0.png", "https://replicate.delivery/mgxm/a7871fdc-b8d4-45ea-b242-de516d3fd1a8/current_1.png", "https://replicate.delivery/mgxm/15f91604-d8d8-4a2c-a032-0ebb72448d55/current_2.png", "https://replicate.delivery/mgxm/f2b2669e-b3f7-4651-aee7-2277c408b6e2/current_3.png" ] ], "started_at": "2022-06-30T05:23:18.835865Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/2i2mkiammfcutniml3h5mxew6e", "cancel": "https://api.replicate.com/v1/predictions/2i2mkiammfcutniml3h5mxew6e/cancel" }, "version": "9ef304ed2499cfddc1ec4ff3bc1b657c03db722ac1e52577e3c42b97d176c040" }
Generated inUsing seed 1657459453 Running simulation for a painting of a bunny rabbit Encoding text embeddings with a painting of a bunny rabbit dimensions Using aesthetic embedding 8 with weight 0.0 Using inpaint model with image: /tmp/tmpuop9k19gcurrent_3.png Running diffusion... 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:43, 1.12it/s] 4%|▍ | 2/50 [00:01<00:41, 1.15it/s] 6%|▌ | 3/50 [00:02<00:40, 1.16it/s] 8%|▊ | 4/50 [00:02<00:27, 1.65it/s] 10%|█ | 5/50 [00:03<00:20, 2.14it/s] 12%|█▏ | 6/50 [00:03<00:16, 2.62it/s] 14%|█▍ | 7/50 [00:03<00:14, 3.06it/s] 16%|█▌ | 8/50 [00:03<00:12, 3.44it/s] 18%|█▊ | 9/50 [00:03<00:10, 3.76it/s] 20%|██ | 10/50 [00:04<00:10, 3.99it/s] 22%|██▏ | 11/50 [00:04<00:09, 4.18it/s] 24%|██▍ | 12/50 [00:04<00:08, 4.29it/s] 26%|██▌ | 13/50 [00:04<00:08, 4.40it/s] 28%|██▊ | 14/50 [00:04<00:08, 4.48it/s] 30%|███ | 15/50 [00:05<00:07, 4.53it/s] 32%|███▏ | 16/50 [00:05<00:07, 4.57it/s] 34%|███▍ | 17/50 [00:05<00:07, 4.59it/s] 36%|███▌ | 18/50 [00:05<00:06, 4.61it/s] 38%|███▊ | 19/50 [00:06<00:06, 4.62it/s] 40%|████ | 20/50 [00:06<00:06, 4.64it/s] 42%|████▏ | 21/50 [00:06<00:06, 4.64it/s] 44%|████▍ | 22/50 [00:06<00:06, 4.64it/s] 46%|████▌ | 23/50 [00:06<00:05, 4.65it/s] 48%|████▊ | 24/50 [00:07<00:05, 4.65it/s] 50%|█████ | 25/50 [00:07<00:05, 4.64it/s] 52%|█████▏ | 26/50 [00:07<00:05, 4.64it/s] 54%|█████▍ | 27/50 [00:07<00:04, 4.63it/s] 56%|█████▌ | 28/50 [00:07<00:04, 4.63it/s] 58%|█████▊ | 29/50 [00:08<00:04, 4.63it/s] 60%|██████ | 30/50 [00:08<00:04, 4.64it/s] 62%|██████▏ | 31/50 [00:08<00:04, 4.63it/s] 64%|██████▍ | 32/50 [00:08<00:03, 4.63it/s] 66%|██████▌ | 33/50 [00:09<00:03, 4.63it/s] 68%|██████▊ | 34/50 [00:09<00:03, 4.63it/s] 70%|███████ | 35/50 [00:09<00:03, 4.63it/s] 72%|███████▏ | 36/50 [00:09<00:03, 4.63it/s] 74%|███████▍ | 37/50 [00:09<00:02, 4.63it/s] 76%|███████▌ | 38/50 [00:10<00:02, 4.63it/s] 78%|███████▊ | 39/50 [00:10<00:02, 4.63it/s] 80%|████████ | 40/50 [00:10<00:02, 4.64it/s] 82%|████████▏ | 41/50 [00:10<00:01, 4.63it/s] 84%|████████▍ | 42/50 [00:11<00:01, 4.63it/s] 86%|████████▌ | 43/50 [00:11<00:01, 4.63it/s] 88%|████████▊ | 44/50 [00:11<00:01, 4.63it/s] 90%|█████████ | 45/50 [00:11<00:01, 4.63it/s] 92%|█████████▏| 46/50 [00:11<00:00, 4.63it/s] 94%|█████████▍| 47/50 [00:12<00:00, 4.62it/s] 96%|█████████▌| 48/50 [00:12<00:00, 4.61it/s] 98%|█████████▊| 49/50 [00:12<00:00, 4.62it/s] 100%|██████████| 50/50 [00:12<00:00, 4.63it/s] 100%|██████████| 50/50 [00:12<00:00, 3.93it/s] Saving final sample/s
Prediction
laion-ai/ongo:1b3cd151IDjuxcjpeddzf23nxwhdcypwyd54StatusSucceededSourceWebHardware–Total durationCreatedInput
- seed
- -1
- steps
- "100"
- width
- "384"
- height
- "384"
- prompt
- bunny rabbit in style of van gogh
- batch_size
- "3"
- guidance_scale
- 5
- aesthetic_rating
- 8
- aesthetic_weight
- 0.1
{ "seed": -1, "steps": "100", "width": "384", "height": "384", "prompt": "bunny rabbit in style of van gogh", "batch_size": "3", "guidance_scale": 5, "aesthetic_rating": 8, "aesthetic_weight": 0.1 }
Install Replicate’s Node.js client library:npm install replicate
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run laion-ai/ongo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "laion-ai/ongo:1b3cd15121ec450baa71bbbdacddef9217519f12ca12ccfef36eeaa20ad89b9d", { input: { seed: -1, steps: "100", width: "384", height: "384", prompt: "bunny rabbit in style of van gogh", batch_size: "3", guidance_scale: 5, aesthetic_rating: 8, aesthetic_weight: 0.1 } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the client:import replicate
Run laion-ai/ongo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "laion-ai/ongo:1b3cd15121ec450baa71bbbdacddef9217519f12ca12ccfef36eeaa20ad89b9d", input={ "seed": -1, "steps": "100", "width": "384", "height": "384", "prompt": "bunny rabbit in style of van gogh", "batch_size": "3", "guidance_scale": 5, "aesthetic_rating": 8, "aesthetic_weight": 0.1 } ) # The laion-ai/ongo model can stream output as it's running. # The predict method returns an iterator, and you can iterate over that output. for item in output: # https://replicate.com/laion-ai/ongo/api#output-schema print(item)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run laion-ai/ongo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "1b3cd15121ec450baa71bbbdacddef9217519f12ca12ccfef36eeaa20ad89b9d", "input": { "seed": -1, "steps": "100", "width": "384", "height": "384", "prompt": "bunny rabbit in style of van gogh", "batch_size": "3", "guidance_scale": 5, "aesthetic_rating": 8, "aesthetic_weight": 0.1 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2022-07-17T07:44:30.683816Z", "created_at": "2022-07-17T07:43:35.219634Z", "data_removed": false, "error": null, "id": "juxcjpeddzf23nxwhdcypwyd54", "input": { "seed": -1, "steps": "100", "width": "384", "height": "384", "prompt": "bunny rabbit in style of van gogh", "batch_size": "3", "guidance_scale": 5, "aesthetic_rating": 8, "aesthetic_weight": 0.1 }, "logs": "Using seed 3741438641\nRunning simulation for bunny rabbit in style of van gogh\nEncoding text embeddings with bunny rabbit in style of van gogh dimensions\nUsing aesthetic embedding 8 with weight 0.1\nRunning diffusion...\n\n 0%| | 0/100 [00:00<?, ?it/s]\n 1%| | 1/100 [00:01<02:40, 1.62s/it]\n 2%|▏ | 2/100 [00:03<02:39, 1.63s/it]\n 3%|▎ | 3/100 [00:04<02:38, 1.63s/it]\n 4%|▍ | 4/100 [00:05<01:50, 1.15s/it]\n 5%|▌ | 5/100 [00:05<01:23, 1.14it/s]\n 6%|▌ | 6/100 [00:06<01:07, 1.39it/s]\n 7%|▋ | 7/100 [00:06<00:57, 1.62it/s]\n 8%|▊ | 8/100 [00:06<00:50, 1.82it/s]\n 9%|▉ | 9/100 [00:07<00:45, 1.98it/s]\n 10%|█ | 10/100 [00:07<00:42, 2.11it/s]\n 11%|█ | 11/100 [00:08<00:40, 2.20it/s]\n 12%|█▏ | 12/100 [00:08<00:38, 2.27it/s]\n 13%|█▎ | 13/100 [00:08<00:37, 2.32it/s]\n 14%|█▍ | 14/100 [00:09<00:36, 2.36it/s]\n 15%|█▌ | 15/100 [00:09<00:35, 2.39it/s]\n 16%|█▌ | 16/100 [00:10<00:34, 2.41it/s]\n 17%|█▋ | 17/100 [00:10<00:34, 2.42it/s]\n 18%|█▊ | 18/100 [00:10<00:33, 2.43it/s]\n 19%|█▉ | 19/100 [00:11<00:33, 2.44it/s]\n 20%|██ | 20/100 [00:11<00:32, 2.45it/s]\n 21%|██ | 21/100 [00:12<00:32, 2.45it/s]\n 22%|██▏ | 22/100 [00:12<00:31, 2.46it/s]\n 23%|██▎ | 23/100 [00:13<00:31, 2.46it/s]\n 24%|██▍ | 24/100 [00:13<00:30, 2.46it/s]\n 25%|██▌ | 25/100 [00:13<00:30, 2.46it/s]\n 26%|██▌ | 26/100 [00:14<00:30, 2.46it/s]\n 27%|██▋ | 27/100 [00:14<00:29, 2.46it/s]\n 28%|██▊ | 28/100 [00:15<00:29, 2.46it/s]\n 29%|██▉ | 29/100 [00:15<00:28, 2.46it/s]\n 30%|███ | 30/100 [00:15<00:28, 2.46it/s]\n 31%|███ | 31/100 [00:16<00:28, 2.46it/s]\n 32%|███▏ | 32/100 [00:16<00:27, 2.46it/s]\n 33%|███▎ | 33/100 [00:17<00:27, 2.47it/s]\n 34%|███▍ | 34/100 [00:17<00:26, 2.47it/s]\n 35%|███▌ | 35/100 [00:17<00:26, 2.47it/s]\n 36%|███▌ | 36/100 [00:18<00:25, 2.47it/s]\n 37%|███▋ | 37/100 [00:18<00:25, 2.47it/s]\n 38%|███▊ | 38/100 [00:19<00:25, 2.47it/s]\n 39%|███▉ | 39/100 [00:19<00:24, 2.46it/s]\n 40%|████ | 40/100 [00:19<00:24, 2.47it/s]\n 41%|████ | 41/100 [00:20<00:23, 2.46it/s]\n 42%|████▏ | 42/100 [00:20<00:23, 2.47it/s]\n 43%|████▎ | 43/100 [00:21<00:23, 2.47it/s]\n 44%|████▍ | 44/100 [00:21<00:22, 2.47it/s]\n 45%|████▌ | 45/100 [00:21<00:22, 2.47it/s]\n 46%|████▌ | 46/100 [00:22<00:21, 2.47it/s]\n 47%|████▋ | 47/100 [00:22<00:21, 2.47it/s]\n 48%|████▊ | 48/100 [00:23<00:21, 2.47it/s]\n 49%|████▉ | 49/100 [00:23<00:20, 2.47it/s]\n 50%|█████ | 50/100 [00:23<00:20, 2.47it/s]\n 51%|█████ | 51/100 [00:24<00:19, 2.47it/s]\n 52%|█████▏ | 52/100 [00:24<00:19, 2.47it/s]\n 53%|█████▎ | 53/100 [00:25<00:19, 2.47it/s]\n 54%|█████▍ | 54/100 [00:25<00:18, 2.47it/s]\n 55%|█████▌ | 55/100 [00:25<00:18, 2.47it/s]\n 56%|█████▌ | 56/100 [00:26<00:17, 2.48it/s]\n 57%|█████▋ | 57/100 [00:26<00:17, 2.48it/s]\n 58%|█████▊ | 58/100 [00:27<00:16, 2.48it/s]\n 59%|█████▉ | 59/100 [00:27<00:16, 2.48it/s]\n 60%|██████ | 60/100 [00:28<00:16, 2.48it/s]\n 61%|██████ | 61/100 [00:28<00:15, 2.48it/s]\n 62%|██████▏ | 62/100 [00:28<00:15, 2.48it/s]\n 63%|██████▎ | 63/100 [00:29<00:14, 2.48it/s]\n 64%|██████▍ | 64/100 [00:29<00:14, 2.49it/s]\n 65%|██████▌ | 65/100 [00:30<00:14, 2.49it/s]\n 66%|██████▌ | 66/100 [00:30<00:13, 2.48it/s]\n 67%|██████▋ | 67/100 [00:30<00:13, 2.49it/s]\n 68%|██████▊ | 68/100 [00:31<00:12, 2.49it/s]\n 69%|██████▉ | 69/100 [00:31<00:12, 2.49it/s]\n 70%|███████ | 70/100 [00:32<00:12, 2.49it/s]\n 71%|███████ | 71/100 [00:32<00:11, 2.48it/s]\n 72%|███████▏ | 72/100 [00:32<00:11, 2.49it/s]\n 73%|███████▎ | 73/100 [00:33<00:10, 2.49it/s]\n 74%|███████▍ | 74/100 [00:33<00:10, 2.50it/s]\n 75%|███████▌ | 75/100 [00:34<00:10, 2.49it/s]\n 76%|███████▌ | 76/100 [00:34<00:09, 2.49it/s]\n 77%|███████▋ | 77/100 [00:34<00:09, 2.49it/s]\n 78%|███████▊ | 78/100 [00:35<00:08, 2.49it/s]\n 79%|███████▉ | 79/100 [00:35<00:08, 2.49it/s]\n 80%|████████ | 80/100 [00:36<00:08, 2.49it/s]\n 81%|████████ | 81/100 [00:36<00:07, 2.48it/s]\n 82%|████████▏ | 82/100 [00:36<00:07, 2.49it/s]\n 83%|████████▎ | 83/100 [00:37<00:06, 2.49it/s]\n 84%|████████▍ | 84/100 [00:37<00:06, 2.49it/s]\n 85%|████████▌ | 85/100 [00:38<00:06, 2.49it/s]\n 86%|████████▌ | 86/100 [00:38<00:05, 2.49it/s]\n 87%|████████▋ | 87/100 [00:38<00:05, 2.49it/s]\n 88%|████████▊ | 88/100 [00:39<00:04, 2.50it/s]\n 89%|████████▉ | 89/100 [00:39<00:04, 2.49it/s]\n 90%|█████████ | 90/100 [00:40<00:04, 2.49it/s]\n 91%|█████████ | 91/100 [00:40<00:03, 2.49it/s]\n 92%|█████████▏| 92/100 [00:40<00:03, 2.49it/s]\n 93%|█████████▎| 93/100 [00:41<00:02, 2.49it/s]\n 94%|█████████▍| 94/100 [00:41<00:02, 2.49it/s]\n 95%|█████████▌| 95/100 [00:42<00:02, 2.50it/s]\n 96%|█████████▌| 96/100 [00:42<00:01, 2.50it/s]\n 97%|█████████▋| 97/100 [00:42<00:01, 2.49it/s]\n 98%|█████████▊| 98/100 [00:43<00:00, 2.50it/s]\n 99%|█████████▉| 99/100 [00:43<00:00, 2.50it/s]\n100%|██████████| 100/100 [00:44<00:00, 2.50it/s]\n100%|██████████| 100/100 [00:44<00:00, 2.27it/s]\nSaving final sample/s", "metrics": { "predict_time": 46.807893, "total_time": 55.464182 }, "output": [ [ "https://replicate.delivery/mgxm/a33510a3-92b2-432e-a778-92753c78d936/current_0.png", "https://replicate.delivery/mgxm/9ef7669c-4c7d-483d-b818-be78e5aa08ec/current_1.png", "https://replicate.delivery/mgxm/9696c825-c8b3-4940-ab70-0717af035d9d/current_2.png" ] ], "started_at": "2022-07-17T07:43:43.875923Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/juxcjpeddzf23nxwhdcypwyd54", "cancel": "https://api.replicate.com/v1/predictions/juxcjpeddzf23nxwhdcypwyd54/cancel" }, "version": "9ef304ed2499cfddc1ec4ff3bc1b657c03db722ac1e52577e3c42b97d176c040" }
Generated inUsing seed 3741438641 Running simulation for bunny rabbit in style of van gogh Encoding text embeddings with bunny rabbit in style of van gogh dimensions Using aesthetic embedding 8 with weight 0.1 Running diffusion... 0%| | 0/100 [00:00<?, ?it/s] 1%| | 1/100 [00:01<02:40, 1.62s/it] 2%|▏ | 2/100 [00:03<02:39, 1.63s/it] 3%|▎ | 3/100 [00:04<02:38, 1.63s/it] 4%|▍ | 4/100 [00:05<01:50, 1.15s/it] 5%|▌ | 5/100 [00:05<01:23, 1.14it/s] 6%|▌ | 6/100 [00:06<01:07, 1.39it/s] 7%|▋ | 7/100 [00:06<00:57, 1.62it/s] 8%|▊ | 8/100 [00:06<00:50, 1.82it/s] 9%|▉ | 9/100 [00:07<00:45, 1.98it/s] 10%|█ | 10/100 [00:07<00:42, 2.11it/s] 11%|█ | 11/100 [00:08<00:40, 2.20it/s] 12%|█▏ | 12/100 [00:08<00:38, 2.27it/s] 13%|█▎ | 13/100 [00:08<00:37, 2.32it/s] 14%|█▍ | 14/100 [00:09<00:36, 2.36it/s] 15%|█▌ | 15/100 [00:09<00:35, 2.39it/s] 16%|█▌ | 16/100 [00:10<00:34, 2.41it/s] 17%|█▋ | 17/100 [00:10<00:34, 2.42it/s] 18%|█▊ | 18/100 [00:10<00:33, 2.43it/s] 19%|█▉ | 19/100 [00:11<00:33, 2.44it/s] 20%|██ | 20/100 [00:11<00:32, 2.45it/s] 21%|██ | 21/100 [00:12<00:32, 2.45it/s] 22%|██▏ | 22/100 [00:12<00:31, 2.46it/s] 23%|██▎ | 23/100 [00:13<00:31, 2.46it/s] 24%|██▍ | 24/100 [00:13<00:30, 2.46it/s] 25%|██▌ | 25/100 [00:13<00:30, 2.46it/s] 26%|██▌ | 26/100 [00:14<00:30, 2.46it/s] 27%|██▋ | 27/100 [00:14<00:29, 2.46it/s] 28%|██▊ | 28/100 [00:15<00:29, 2.46it/s] 29%|██▉ | 29/100 [00:15<00:28, 2.46it/s] 30%|███ | 30/100 [00:15<00:28, 2.46it/s] 31%|███ | 31/100 [00:16<00:28, 2.46it/s] 32%|███▏ | 32/100 [00:16<00:27, 2.46it/s] 33%|███▎ | 33/100 [00:17<00:27, 2.47it/s] 34%|███▍ | 34/100 [00:17<00:26, 2.47it/s] 35%|███▌ | 35/100 [00:17<00:26, 2.47it/s] 36%|███▌ | 36/100 [00:18<00:25, 2.47it/s] 37%|███▋ | 37/100 [00:18<00:25, 2.47it/s] 38%|███▊ | 38/100 [00:19<00:25, 2.47it/s] 39%|███▉ | 39/100 [00:19<00:24, 2.46it/s] 40%|████ | 40/100 [00:19<00:24, 2.47it/s] 41%|████ | 41/100 [00:20<00:23, 2.46it/s] 42%|████▏ | 42/100 [00:20<00:23, 2.47it/s] 43%|████▎ | 43/100 [00:21<00:23, 2.47it/s] 44%|████▍ | 44/100 [00:21<00:22, 2.47it/s] 45%|████▌ | 45/100 [00:21<00:22, 2.47it/s] 46%|████▌ | 46/100 [00:22<00:21, 2.47it/s] 47%|████▋ | 47/100 [00:22<00:21, 2.47it/s] 48%|████▊ | 48/100 [00:23<00:21, 2.47it/s] 49%|████▉ | 49/100 [00:23<00:20, 2.47it/s] 50%|█████ | 50/100 [00:23<00:20, 2.47it/s] 51%|█████ | 51/100 [00:24<00:19, 2.47it/s] 52%|█████▏ | 52/100 [00:24<00:19, 2.47it/s] 53%|█████▎ | 53/100 [00:25<00:19, 2.47it/s] 54%|█████▍ | 54/100 [00:25<00:18, 2.47it/s] 55%|█████▌ | 55/100 [00:25<00:18, 2.47it/s] 56%|█████▌ | 56/100 [00:26<00:17, 2.48it/s] 57%|█████▋ | 57/100 [00:26<00:17, 2.48it/s] 58%|█████▊ | 58/100 [00:27<00:16, 2.48it/s] 59%|█████▉ | 59/100 [00:27<00:16, 2.48it/s] 60%|██████ | 60/100 [00:28<00:16, 2.48it/s] 61%|██████ | 61/100 [00:28<00:15, 2.48it/s] 62%|██████▏ | 62/100 [00:28<00:15, 2.48it/s] 63%|██████▎ | 63/100 [00:29<00:14, 2.48it/s] 64%|██████▍ | 64/100 [00:29<00:14, 2.49it/s] 65%|██████▌ | 65/100 [00:30<00:14, 2.49it/s] 66%|██████▌ | 66/100 [00:30<00:13, 2.48it/s] 67%|██████▋ | 67/100 [00:30<00:13, 2.49it/s] 68%|██████▊ | 68/100 [00:31<00:12, 2.49it/s] 69%|██████▉ | 69/100 [00:31<00:12, 2.49it/s] 70%|███████ | 70/100 [00:32<00:12, 2.49it/s] 71%|███████ | 71/100 [00:32<00:11, 2.48it/s] 72%|███████▏ | 72/100 [00:32<00:11, 2.49it/s] 73%|███████▎ | 73/100 [00:33<00:10, 2.49it/s] 74%|███████▍ | 74/100 [00:33<00:10, 2.50it/s] 75%|███████▌ | 75/100 [00:34<00:10, 2.49it/s] 76%|███████▌ | 76/100 [00:34<00:09, 2.49it/s] 77%|███████▋ | 77/100 [00:34<00:09, 2.49it/s] 78%|███████▊ | 78/100 [00:35<00:08, 2.49it/s] 79%|███████▉ | 79/100 [00:35<00:08, 2.49it/s] 80%|████████ | 80/100 [00:36<00:08, 2.49it/s] 81%|████████ | 81/100 [00:36<00:07, 2.48it/s] 82%|████████▏ | 82/100 [00:36<00:07, 2.49it/s] 83%|████████▎ | 83/100 [00:37<00:06, 2.49it/s] 84%|████████▍ | 84/100 [00:37<00:06, 2.49it/s] 85%|████████▌ | 85/100 [00:38<00:06, 2.49it/s] 86%|████████▌ | 86/100 [00:38<00:05, 2.49it/s] 87%|████████▋ | 87/100 [00:38<00:05, 2.49it/s] 88%|████████▊ | 88/100 [00:39<00:04, 2.50it/s] 89%|████████▉ | 89/100 [00:39<00:04, 2.49it/s] 90%|█████████ | 90/100 [00:40<00:04, 2.49it/s] 91%|█████████ | 91/100 [00:40<00:03, 2.49it/s] 92%|█████████▏| 92/100 [00:40<00:03, 2.49it/s] 93%|█████████▎| 93/100 [00:41<00:02, 2.49it/s] 94%|█████████▍| 94/100 [00:41<00:02, 2.49it/s] 95%|█████████▌| 95/100 [00:42<00:02, 2.50it/s] 96%|█████████▌| 96/100 [00:42<00:01, 2.50it/s] 97%|█████████▋| 97/100 [00:42<00:01, 2.49it/s] 98%|█████████▊| 98/100 [00:43<00:00, 2.50it/s] 99%|█████████▉| 99/100 [00:43<00:00, 2.50it/s] 100%|██████████| 100/100 [00:44<00:00, 2.50it/s] 100%|██████████| 100/100 [00:44<00:00, 2.27it/s] Saving final sample/s
Want to make some of these yourself?
Run this model