laion-ai / laionide-v2
GLIDE from OpenAI finetuned on roughly 30M more samples. See `laionide-v3` for the latest.
Prediction
laion-ai/laionide-v2:da2fb5c363fbc9ec4068004f740b49a7d0a7a6c44c828eb2dd8428c702e59aebIDritzdxzycrc5tozv56cybiqtxaStatusSucceededSourceWebHardware–Total durationCreatedInput
- prompt
- an armchair in the form of an avocado
- side_x
- 64
- side_y
- 64
- batch_size
- 3
- upsample_temp
- 0.998
- guidance_scale
- 10
- upsample_stage
- timestep_respacing
- 40
- sr_timestep_respacing
- 17
{ "prompt": "an armchair in the form of an avocado", "side_x": 64, "side_y": 64, "batch_size": 3, "upsample_temp": 0.998, "guidance_scale": 10, "upsample_stage": true, "timestep_respacing": "40", "sr_timestep_respacing": "17" }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run laion-ai/laionide-v2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "laion-ai/laionide-v2:da2fb5c363fbc9ec4068004f740b49a7d0a7a6c44c828eb2dd8428c702e59aeb", { input: { prompt: "an armchair in the form of an avocado", side_x: 64, side_y: 64, batch_size: 3, upsample_temp: 0.998, guidance_scale: 10, upsample_stage: true, timestep_respacing: "40", sr_timestep_respacing: "17" } } ); 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 replicateImport the client:import replicateRun laion-ai/laionide-v2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "laion-ai/laionide-v2:da2fb5c363fbc9ec4068004f740b49a7d0a7a6c44c828eb2dd8428c702e59aeb", input={ "prompt": "an armchair in the form of an avocado", "side_x": 64, "side_y": 64, "batch_size": 3, "upsample_temp": 0.998, "guidance_scale": 10, "upsample_stage": True, "timestep_respacing": "40", "sr_timestep_respacing": "17" } ) # The laion-ai/laionide-v2 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/laionide-v2/api#output-schema print(item)To learn more, take a look at the guide on getting started with Python.
Run laion-ai/laionide-v2 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": "laion-ai/laionide-v2:da2fb5c363fbc9ec4068004f740b49a7d0a7a6c44c828eb2dd8428c702e59aeb", "input": { "prompt": "an armchair in the form of an avocado", "side_x": 64, "side_y": 64, "batch_size": 3, "upsample_temp": 0.998, "guidance_scale": 10, "upsample_stage": true, "timestep_respacing": "40", "sr_timestep_respacing": "17" } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2022-02-23T01:37:54.381434Z", "created_at": "2022-02-23T01:37:21.100968Z", "data_removed": false, "error": null, "id": "ritzdxzycrc5tozv56cybiqtxa", "input": { "prompt": "an armchair in the form of an avocado", "side_x": 64, "side_y": 64, "batch_size": 3, "upsample_temp": 0.998, "guidance_scale": 10, "upsample_stage": true, "timestep_respacing": "40", "sr_timestep_respacing": "17" }, "logs": "Generating 64x64 samples with 40 timesteps using GLIDE-base-64px...\n\n 0%| | 0/38 [00:00<?, ?it/s]\n 3%|▎ | 1/38 [00:00<00:28, 1.32it/s]\n 5%|▌ | 2/38 [00:01<00:26, 1.38it/s]\n 8%|▊ | 3/38 [00:02<00:24, 1.40it/s]\n 11%|█ | 4/38 [00:02<00:17, 1.99it/s]\n 13%|█▎ | 5/38 [00:02<00:12, 2.60it/s]\n 16%|█▌ | 6/38 [00:02<00:10, 3.18it/s]\n 18%|█▊ | 7/38 [00:02<00:08, 3.73it/s]\n 21%|██ | 8/38 [00:03<00:07, 4.19it/s]\n 24%|██▎ | 9/38 [00:03<00:06, 4.54it/s]\n 26%|██▋ | 10/38 [00:03<00:05, 4.84it/s]\n 29%|██▉ | 11/38 [00:03<00:05, 5.06it/s]\n 32%|███▏ | 12/38 [00:03<00:04, 5.24it/s]\n 34%|███▍ | 13/38 [00:03<00:04, 5.36it/s]\n 37%|███▋ | 14/38 [00:04<00:04, 5.45it/s]\n 39%|███▉ | 15/38 [00:04<00:04, 5.50it/s]\n 42%|████▏ | 16/38 [00:04<00:03, 5.53it/s]\n 45%|████▍ | 17/38 [00:04<00:03, 5.58it/s]\n 47%|████▋ | 18/38 [00:04<00:03, 5.60it/s]\n 50%|█████ | 19/38 [00:04<00:03, 5.63it/s]\n 53%|█████▎ | 20/38 [00:05<00:03, 5.64it/s]\n 55%|█████▌ | 21/38 [00:05<00:03, 5.64it/s]\n 58%|█████▊ | 22/38 [00:05<00:02, 5.64it/s]\n 61%|██████ | 23/38 [00:05<00:02, 5.66it/s]\n 63%|██████▎ | 24/38 [00:05<00:02, 5.66it/s]\n 66%|██████▌ | 25/38 [00:06<00:02, 5.66it/s]\n 68%|██████▊ | 26/38 [00:06<00:02, 5.65it/s]\n 71%|███████ | 27/38 [00:06<00:01, 5.66it/s]\n 74%|███████▎ | 28/38 [00:06<00:01, 5.66it/s]\n 76%|███████▋ | 29/38 [00:06<00:01, 5.66it/s]\n 79%|███████▉ | 30/38 [00:06<00:01, 5.66it/s]\n 82%|████████▏ | 31/38 [00:07<00:01, 5.67it/s]\n 84%|████████▍ | 32/38 [00:07<00:01, 5.67it/s]\n 87%|████████▋ | 33/38 [00:07<00:00, 5.67it/s]\n 89%|████████▉ | 34/38 [00:07<00:00, 5.67it/s]\n 92%|█████████▏| 35/38 [00:07<00:00, 5.66it/s]\n 95%|█████████▍| 36/38 [00:07<00:00, 5.65it/s]\n 97%|█████████▋| 37/38 [00:08<00:00, 5.65it/s]\n100%|██████████| 38/38 [00:08<00:00, 5.63it/s]\n100%|██████████| 38/38 [00:08<00:00, 4.55it/s]\nUpsampling outputs from GLIDE-base 64x64 to 256x256 using 17 timesteps...\n\n 0%| | 0/15 [00:00<?, ?it/s]\n 7%|▋ | 1/15 [00:01<00:26, 1.91s/it]\n 13%|█▎ | 2/15 [00:03<00:24, 1.91s/it]\n 20%|██ | 3/15 [00:05<00:22, 1.91s/it]\n 27%|██▋ | 4/15 [00:06<00:14, 1.34s/it]\n 33%|███▎ | 5/15 [00:06<00:10, 1.03s/it]\n 40%|████ | 6/15 [00:07<00:07, 1.19it/s]\n 47%|████▋ | 7/15 [00:07<00:05, 1.38it/s]\n 53%|█████▎ | 8/15 [00:08<00:04, 1.55it/s]\n 60%|██████ | 9/15 [00:08<00:03, 1.68it/s]\n 67%|██████▋ | 10/15 [00:09<00:02, 1.78it/s]\n 73%|███████▎ | 11/15 [00:09<00:02, 1.86it/s]\n 80%|████████ | 12/15 [00:10<00:01, 1.93it/s]\n 87%|████████▋ | 13/15 [00:10<00:01, 1.97it/s]\n 93%|█████████▎| 14/15 [00:11<00:00, 2.00it/s]\n100%|██████████| 15/15 [00:11<00:00, 2.02it/s]\n100%|██████████| 15/15 [00:11<00:00, 1.30it/s]", "metrics": { "predict_time": 33.056957, "total_time": 33.280466 }, "output": [ { "file": "https://replicate.delivery/mgxm/6219dff7-4763-4733-b574-0dfe7c7c5919/upsample_predictions.png" } ], "started_at": "2022-02-23T01:37:21.324477Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/ritzdxzycrc5tozv56cybiqtxa", "cancel": "https://api.replicate.com/v1/predictions/ritzdxzycrc5tozv56cybiqtxa/cancel" }, "version": "da2fb5c363fbc9ec4068004f740b49a7d0a7a6c44c828eb2dd8428c702e59aeb" }Generated inGenerating 64x64 samples with 40 timesteps using GLIDE-base-64px... 0%| | 0/38 [00:00<?, ?it/s] 3%|▎ | 1/38 [00:00<00:28, 1.32it/s] 5%|▌ | 2/38 [00:01<00:26, 1.38it/s] 8%|▊ | 3/38 [00:02<00:24, 1.40it/s] 11%|█ | 4/38 [00:02<00:17, 1.99it/s] 13%|█▎ | 5/38 [00:02<00:12, 2.60it/s] 16%|█▌ | 6/38 [00:02<00:10, 3.18it/s] 18%|█▊ | 7/38 [00:02<00:08, 3.73it/s] 21%|██ | 8/38 [00:03<00:07, 4.19it/s] 24%|██▎ | 9/38 [00:03<00:06, 4.54it/s] 26%|██▋ | 10/38 [00:03<00:05, 4.84it/s] 29%|██▉ | 11/38 [00:03<00:05, 5.06it/s] 32%|███▏ | 12/38 [00:03<00:04, 5.24it/s] 34%|███▍ | 13/38 [00:03<00:04, 5.36it/s] 37%|███▋ | 14/38 [00:04<00:04, 5.45it/s] 39%|███▉ | 15/38 [00:04<00:04, 5.50it/s] 42%|████▏ | 16/38 [00:04<00:03, 5.53it/s] 45%|████▍ | 17/38 [00:04<00:03, 5.58it/s] 47%|████▋ | 18/38 [00:04<00:03, 5.60it/s] 50%|█████ | 19/38 [00:04<00:03, 5.63it/s] 53%|█████▎ | 20/38 [00:05<00:03, 5.64it/s] 55%|█████▌ | 21/38 [00:05<00:03, 5.64it/s] 58%|█████▊ | 22/38 [00:05<00:02, 5.64it/s] 61%|██████ | 23/38 [00:05<00:02, 5.66it/s] 63%|██████▎ | 24/38 [00:05<00:02, 5.66it/s] 66%|██████▌ | 25/38 [00:06<00:02, 5.66it/s] 68%|██████▊ | 26/38 [00:06<00:02, 5.65it/s] 71%|███████ | 27/38 [00:06<00:01, 5.66it/s] 74%|███████▎ | 28/38 [00:06<00:01, 5.66it/s] 76%|███████▋ | 29/38 [00:06<00:01, 5.66it/s] 79%|███████▉ | 30/38 [00:06<00:01, 5.66it/s] 82%|████████▏ | 31/38 [00:07<00:01, 5.67it/s] 84%|████████▍ | 32/38 [00:07<00:01, 5.67it/s] 87%|████████▋ | 33/38 [00:07<00:00, 5.67it/s] 89%|████████▉ | 34/38 [00:07<00:00, 5.67it/s] 92%|█████████▏| 35/38 [00:07<00:00, 5.66it/s] 95%|█████████▍| 36/38 [00:07<00:00, 5.65it/s] 97%|█████████▋| 37/38 [00:08<00:00, 5.65it/s] 100%|██████████| 38/38 [00:08<00:00, 5.63it/s] 100%|██████████| 38/38 [00:08<00:00, 4.55it/s] Upsampling outputs from GLIDE-base 64x64 to 256x256 using 17 timesteps... 0%| | 0/15 [00:00<?, ?it/s] 7%|▋ | 1/15 [00:01<00:26, 1.91s/it] 13%|█▎ | 2/15 [00:03<00:24, 1.91s/it] 20%|██ | 3/15 [00:05<00:22, 1.91s/it] 27%|██▋ | 4/15 [00:06<00:14, 1.34s/it] 33%|███▎ | 5/15 [00:06<00:10, 1.03s/it] 40%|████ | 6/15 [00:07<00:07, 1.19it/s] 47%|████▋ | 7/15 [00:07<00:05, 1.38it/s] 53%|█████▎ | 8/15 [00:08<00:04, 1.55it/s] 60%|██████ | 9/15 [00:08<00:03, 1.68it/s] 67%|██████▋ | 10/15 [00:09<00:02, 1.78it/s] 73%|███████▎ | 11/15 [00:09<00:02, 1.86it/s] 80%|████████ | 12/15 [00:10<00:01, 1.93it/s] 87%|████████▋ | 13/15 [00:10<00:01, 1.97it/s] 93%|█████████▎| 14/15 [00:11<00:00, 2.00it/s] 100%|██████████| 15/15 [00:11<00:00, 2.02it/s] 100%|██████████| 15/15 [00:11<00:00, 1.30it/s]Prediction
laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48aeIDdmkcgyzgibh23gte7kz45ri7s4StatusSucceededSourceWebHardware–Total durationCreatedInput
- seed
- 23211
- prompt
- an oil painting of 3 men on top of a mountain
- side_x
- "64"
- side_y
- "64"
- batch_size
- "3"
- upsample_temp
- "0.997"
- guidance_scale
- 16
- upsample_stage
- timestep_respacing
- 27
- sr_timestep_respacing
- 17
{ "seed": 23211, "prompt": "an oil painting of 3 men on top of a mountain", "side_x": "64", "side_y": "64", "batch_size": "3", "upsample_temp": "0.997", "guidance_scale": 16, "upsample_stage": true, "timestep_respacing": "27", "sr_timestep_respacing": "17" }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run laion-ai/laionide-v2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae", { input: { seed: 23211, prompt: "an oil painting of 3 men on top of a mountain", side_x: "64", side_y: "64", batch_size: "3", upsample_temp: "0.997", guidance_scale: 16, upsample_stage: true, timestep_respacing: "27", sr_timestep_respacing: "17" } } ); 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 replicateImport the client:import replicateRun laion-ai/laionide-v2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae", input={ "seed": 23211, "prompt": "an oil painting of 3 men on top of a mountain", "side_x": "64", "side_y": "64", "batch_size": "3", "upsample_temp": "0.997", "guidance_scale": 16, "upsample_stage": True, "timestep_respacing": "27", "sr_timestep_respacing": "17" } ) # The laion-ai/laionide-v2 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/laionide-v2/api#output-schema print(item)To learn more, take a look at the guide on getting started with Python.
Run laion-ai/laionide-v2 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": "laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae", "input": { "seed": 23211, "prompt": "an oil painting of 3 men on top of a mountain", "side_x": "64", "side_y": "64", "batch_size": "3", "upsample_temp": "0.997", "guidance_scale": 16, "upsample_stage": true, "timestep_respacing": "27", "sr_timestep_respacing": "17" } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2022-02-23T06:04:52.451404Z", "created_at": "2022-02-23T06:04:19.503912Z", "data_removed": false, "error": null, "id": "dmkcgyzgibh23gte7kz45ri7s4", "input": { "seed": 23211, "prompt": "an oil painting of 3 men on top of a mountain", "side_x": "64", "side_y": "64", "batch_size": "3", "upsample_temp": "0.997", "guidance_scale": 16, "upsample_stage": true, "timestep_respacing": "27", "sr_timestep_respacing": "17" }, "logs": "Generating 64x64 samples with 27 timesteps using GLIDE-base-64px...\n\n 0%| | 0/25 [00:00<?, ?it/s]\n 4%|▍ | 1/25 [00:00<00:19, 1.24it/s]\n 8%|▊ | 2/25 [00:01<00:17, 1.30it/s]\n 12%|█▏ | 3/25 [00:02<00:16, 1.32it/s]\n 16%|█▌ | 4/25 [00:02<00:11, 1.88it/s]\n 20%|██ | 5/25 [00:02<00:08, 2.46it/s]Caught SIGTERM, exiting...\n\n 24%|██▍ | 6/25 [00:02<00:06, 3.01it/s]\n 28%|██▊ | 7/25 [00:03<00:05, 3.52it/s]\n 32%|███▏ | 8/25 [00:03<00:04, 3.96it/s]\n 36%|███▌ | 9/25 [00:03<00:03, 4.31it/s]\n 40%|████ | 10/25 [00:03<00:03, 4.57it/s]\n 44%|████▍ | 11/25 [00:03<00:02, 4.78it/s]\n 48%|████▊ | 12/25 [00:03<00:02, 4.96it/s]\n 52%|█████▏ | 13/25 [00:04<00:02, 5.08it/s]\n 56%|█████▌ | 14/25 [00:04<00:02, 5.16it/s]\n 60%|██████ | 15/25 [00:04<00:01, 5.21it/s]\n 64%|██████▍ | 16/25 [00:04<00:01, 5.24it/s]\n 68%|██████▊ | 17/25 [00:04<00:01, 5.29it/s]\n 72%|███████▏ | 18/25 [00:05<00:01, 5.31it/s]\n 76%|███████▌ | 19/25 [00:05<00:01, 5.31it/s]\n 80%|████████ | 20/25 [00:05<00:00, 5.33it/s]\n 84%|████████▍ | 21/25 [00:05<00:00, 5.34it/s]\n 88%|████████▊ | 22/25 [00:05<00:00, 5.34it/s]\n 92%|█████████▏| 23/25 [00:06<00:00, 5.33it/s]\n 96%|█████████▌| 24/25 [00:06<00:00, 5.33it/s]\n100%|██████████| 25/25 [00:06<00:00, 5.33it/s]\n100%|██████████| 25/25 [00:06<00:00, 3.91it/s]\nUpsampling outputs from GLIDE-base 64x64 to 256x256 using 17 timesteps...\n\n 0%| | 0/15 [00:00<?, ?it/s]\n 7%|▋ | 1/15 [00:02<00:28, 2.04s/it]\n 13%|█▎ | 2/15 [00:04<00:26, 2.05s/it]\n 20%|██ | 3/15 [00:06<00:24, 2.06s/it]\n 27%|██▋ | 4/15 [00:06<00:15, 1.45s/it]\n 33%|███▎ | 5/15 [00:07<00:11, 1.12s/it]\n 40%|████ | 6/15 [00:07<00:08, 1.09it/s]\n 47%|████▋ | 7/15 [00:08<00:06, 1.27it/s]\n 53%|█████▎ | 8/15 [00:08<00:04, 1.42it/s]\n 60%|██████ | 9/15 [00:09<00:03, 1.54it/s]\n 67%|██████▋ | 10/15 [00:09<00:03, 1.64it/s]\n 73%|███████▎ | 11/15 [00:10<00:02, 1.71it/s]\n 80%|████████ | 12/15 [00:10<00:01, 1.76it/s]\n 87%|████████▋ | 13/15 [00:11<00:01, 1.80it/s]\n 93%|█████████▎| 14/15 [00:11<00:00, 1.83it/s]\n100%|██████████| 15/15 [00:12<00:00, 1.85it/s]\n100%|██████████| 15/15 [00:12<00:00, 1.20it/s]", "metrics": { "predict_time": 32.734152, "total_time": 32.947492 }, "output": [ { "file": "https://replicate.delivery/mgxm/489ca32e-0638-457d-9e4d-0520af36a627/base_predictions.png" }, { "file": "https://replicate.delivery/mgxm/6b292967-48c1-4923-93d0-2993015ab712/upsample_predictions.png" } ], "started_at": "2022-02-23T06:04:19.717252Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/dmkcgyzgibh23gte7kz45ri7s4", "cancel": "https://api.replicate.com/v1/predictions/dmkcgyzgibh23gte7kz45ri7s4/cancel" }, "version": "45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae" }Generated inGenerating 64x64 samples with 27 timesteps using GLIDE-base-64px... 0%| | 0/25 [00:00<?, ?it/s] 4%|▍ | 1/25 [00:00<00:19, 1.24it/s] 8%|▊ | 2/25 [00:01<00:17, 1.30it/s] 12%|█▏ | 3/25 [00:02<00:16, 1.32it/s] 16%|█▌ | 4/25 [00:02<00:11, 1.88it/s] 20%|██ | 5/25 [00:02<00:08, 2.46it/s]Caught SIGTERM, exiting... 24%|██▍ | 6/25 [00:02<00:06, 3.01it/s] 28%|██▊ | 7/25 [00:03<00:05, 3.52it/s] 32%|███▏ | 8/25 [00:03<00:04, 3.96it/s] 36%|███▌ | 9/25 [00:03<00:03, 4.31it/s] 40%|████ | 10/25 [00:03<00:03, 4.57it/s] 44%|████▍ | 11/25 [00:03<00:02, 4.78it/s] 48%|████▊ | 12/25 [00:03<00:02, 4.96it/s] 52%|█████▏ | 13/25 [00:04<00:02, 5.08it/s] 56%|█████▌ | 14/25 [00:04<00:02, 5.16it/s] 60%|██████ | 15/25 [00:04<00:01, 5.21it/s] 64%|██████▍ | 16/25 [00:04<00:01, 5.24it/s] 68%|██████▊ | 17/25 [00:04<00:01, 5.29it/s] 72%|███████▏ | 18/25 [00:05<00:01, 5.31it/s] 76%|███████▌ | 19/25 [00:05<00:01, 5.31it/s] 80%|████████ | 20/25 [00:05<00:00, 5.33it/s] 84%|████████▍ | 21/25 [00:05<00:00, 5.34it/s] 88%|████████▊ | 22/25 [00:05<00:00, 5.34it/s] 92%|█████████▏| 23/25 [00:06<00:00, 5.33it/s] 96%|█████████▌| 24/25 [00:06<00:00, 5.33it/s] 100%|██████████| 25/25 [00:06<00:00, 5.33it/s] 100%|██████████| 25/25 [00:06<00:00, 3.91it/s] Upsampling outputs from GLIDE-base 64x64 to 256x256 using 17 timesteps... 0%| | 0/15 [00:00<?, ?it/s] 7%|▋ | 1/15 [00:02<00:28, 2.04s/it] 13%|█▎ | 2/15 [00:04<00:26, 2.05s/it] 20%|██ | 3/15 [00:06<00:24, 2.06s/it] 27%|██▋ | 4/15 [00:06<00:15, 1.45s/it] 33%|███▎ | 5/15 [00:07<00:11, 1.12s/it] 40%|████ | 6/15 [00:07<00:08, 1.09it/s] 47%|████▋ | 7/15 [00:08<00:06, 1.27it/s] 53%|█████▎ | 8/15 [00:08<00:04, 1.42it/s] 60%|██████ | 9/15 [00:09<00:03, 1.54it/s] 67%|██████▋ | 10/15 [00:09<00:03, 1.64it/s] 73%|███████▎ | 11/15 [00:10<00:02, 1.71it/s] 80%|████████ | 12/15 [00:10<00:01, 1.76it/s] 87%|████████▋ | 13/15 [00:11<00:01, 1.80it/s] 93%|█████████▎| 14/15 [00:11<00:00, 1.83it/s] 100%|██████████| 15/15 [00:12<00:00, 1.85it/s] 100%|██████████| 15/15 [00:12<00:00, 1.20it/s]Prediction
laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48aeIDqtpcidz6srb2djjtpzfbzenrsyStatusSucceededSourceWebHardware–Total durationCreatedInput
- seed
- 23211
- prompt
- an oil painting of a woman on top of a mountain
- side_x
- "64"
- side_y
- "64"
- batch_size
- "3"
- upsample_temp
- "0.997"
- guidance_scale
- 16
- upsample_stage
- timestep_respacing
- 27
- sr_timestep_respacing
- 17
{ "seed": 23211, "prompt": "an oil painting of a woman on top of a mountain", "side_x": "64", "side_y": "64", "batch_size": "3", "upsample_temp": "0.997", "guidance_scale": 16, "upsample_stage": true, "timestep_respacing": "27", "sr_timestep_respacing": "17" }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run laion-ai/laionide-v2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae", { input: { seed: 23211, prompt: "an oil painting of a woman on top of a mountain", side_x: "64", side_y: "64", batch_size: "3", upsample_temp: "0.997", guidance_scale: 16, upsample_stage: true, timestep_respacing: "27", sr_timestep_respacing: "17" } } ); 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 replicateImport the client:import replicateRun laion-ai/laionide-v2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae", input={ "seed": 23211, "prompt": "an oil painting of a woman on top of a mountain", "side_x": "64", "side_y": "64", "batch_size": "3", "upsample_temp": "0.997", "guidance_scale": 16, "upsample_stage": True, "timestep_respacing": "27", "sr_timestep_respacing": "17" } ) # The laion-ai/laionide-v2 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/laionide-v2/api#output-schema print(item)To learn more, take a look at the guide on getting started with Python.
Run laion-ai/laionide-v2 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": "laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae", "input": { "seed": 23211, "prompt": "an oil painting of a woman on top of a mountain", "side_x": "64", "side_y": "64", "batch_size": "3", "upsample_temp": "0.997", "guidance_scale": 16, "upsample_stage": true, "timestep_respacing": "27", "sr_timestep_respacing": "17" } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2022-02-23T06:05:59.970173Z", "created_at": "2022-02-23T06:05:12.743819Z", "data_removed": false, "error": null, "id": "qtpcidz6srb2djjtpzfbzenrsy", "input": { "seed": 23211, "prompt": "an oil painting of a woman on top of a mountain", "side_x": "64", "side_y": "64", "batch_size": "3", "upsample_temp": "0.997", "guidance_scale": 16, "upsample_stage": true, "timestep_respacing": "27", "sr_timestep_respacing": "17" }, "logs": "Generating 64x64 samples with 27 timesteps using GLIDE-base-64px...\n\n 0%| | 0/25 [00:00<?, ?it/s]\n 4%|▍ | 1/25 [00:00<00:19, 1.24it/s]\n 8%|▊ | 2/25 [00:01<00:17, 1.31it/s]\n 12%|█▏ | 3/25 [00:02<00:16, 1.33it/s]\n 16%|█▌ | 4/25 [00:02<00:11, 1.89it/s]\n 20%|██ | 5/25 [00:02<00:08, 2.47it/s]\n 24%|██▍ | 6/25 [00:02<00:06, 3.03it/s]\n 28%|██▊ | 7/25 [00:03<00:05, 3.54it/s]\n 32%|███▏ | 8/25 [00:03<00:04, 3.98it/s]\n 36%|███▌ | 9/25 [00:03<00:03, 4.34it/s]\n 40%|████ | 10/25 [00:03<00:03, 4.62it/s]\n 44%|████▍ | 11/25 [00:03<00:02, 4.84it/s]\n 48%|████▊ | 12/25 [00:03<00:02, 5.02it/s]\n 52%|█████▏ | 13/25 [00:04<00:02, 5.15it/s]\n 56%|█████▌ | 14/25 [00:04<00:02, 5.23it/s]\n 60%|██████ | 15/25 [00:04<00:01, 5.29it/s]\n 64%|██████▍ | 16/25 [00:04<00:01, 5.33it/s]\n 68%|██████▊ | 17/25 [00:04<00:01, 5.34it/s]\n 72%|███████▏ | 18/25 [00:05<00:01, 5.34it/s]\n 76%|███████▌ | 19/25 [00:05<00:01, 5.31it/s]\n 80%|████████ | 20/25 [00:05<00:00, 5.35it/s]\n 84%|████████▍ | 21/25 [00:05<00:00, 5.33it/s]\n 88%|████████▊ | 22/25 [00:05<00:00, 5.34it/s]\n 92%|█████████▏| 23/25 [00:05<00:00, 5.34it/s]\n 96%|█████████▌| 24/25 [00:06<00:00, 5.36it/s]\n100%|██████████| 25/25 [00:06<00:00, 5.37it/s]\n100%|██████████| 25/25 [00:06<00:00, 3.93it/s]\nUpsampling outputs from GLIDE-base 64x64 to 256x256 using 17 timesteps...\n\n 0%| | 0/15 [00:00<?, ?it/s]\n 7%|▋ | 1/15 [00:02<00:28, 2.01s/it]\n 13%|█▎ | 2/15 [00:04<00:26, 2.01s/it]\n 20%|██ | 3/15 [00:06<00:24, 2.01s/it]\n 27%|██▋ | 4/15 [00:06<00:15, 1.41s/it]\n 33%|███▎ | 5/15 [00:07<00:10, 1.09s/it]\n 40%|████ | 6/15 [00:07<00:07, 1.13it/s]\n 47%|████▋ | 7/15 [00:08<00:06, 1.31it/s]\n 53%|█████▎ | 8/15 [00:08<00:04, 1.47it/s]\n 60%|██████ | 9/15 [00:09<00:03, 1.60it/s]\n 67%|██████▋ | 10/15 [00:09<00:02, 1.69it/s]\n 73%|███████▎ | 11/15 [00:10<00:02, 1.77it/s]\n 80%|████████ | 12/15 [00:10<00:01, 1.83it/s]\n 87%|████████▋ | 13/15 [00:11<00:01, 1.87it/s]\n 93%|█████████▎| 14/15 [00:11<00:00, 1.90it/s]\n100%|██████████| 15/15 [00:12<00:00, 1.92it/s]\n100%|██████████| 15/15 [00:12<00:00, 1.24it/s]", "metrics": { "predict_time": 31.567495, "total_time": 47.226354 }, "output": [ { "file": "https://replicate.delivery/mgxm/d36994bf-50e5-4eec-91e2-4a29e10b72ff/upsample_predictions.png" } ], "started_at": "2022-02-23T06:05:28.402678Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/qtpcidz6srb2djjtpzfbzenrsy", "cancel": "https://api.replicate.com/v1/predictions/qtpcidz6srb2djjtpzfbzenrsy/cancel" }, "version": "45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae" }Generated inGenerating 64x64 samples with 27 timesteps using GLIDE-base-64px... 0%| | 0/25 [00:00<?, ?it/s] 4%|▍ | 1/25 [00:00<00:19, 1.24it/s] 8%|▊ | 2/25 [00:01<00:17, 1.31it/s] 12%|█▏ | 3/25 [00:02<00:16, 1.33it/s] 16%|█▌ | 4/25 [00:02<00:11, 1.89it/s] 20%|██ | 5/25 [00:02<00:08, 2.47it/s] 24%|██▍ | 6/25 [00:02<00:06, 3.03it/s] 28%|██▊ | 7/25 [00:03<00:05, 3.54it/s] 32%|███▏ | 8/25 [00:03<00:04, 3.98it/s] 36%|███▌ | 9/25 [00:03<00:03, 4.34it/s] 40%|████ | 10/25 [00:03<00:03, 4.62it/s] 44%|████▍ | 11/25 [00:03<00:02, 4.84it/s] 48%|████▊ | 12/25 [00:03<00:02, 5.02it/s] 52%|█████▏ | 13/25 [00:04<00:02, 5.15it/s] 56%|█████▌ | 14/25 [00:04<00:02, 5.23it/s] 60%|██████ | 15/25 [00:04<00:01, 5.29it/s] 64%|██████▍ | 16/25 [00:04<00:01, 5.33it/s] 68%|██████▊ | 17/25 [00:04<00:01, 5.34it/s] 72%|███████▏ | 18/25 [00:05<00:01, 5.34it/s] 76%|███████▌ | 19/25 [00:05<00:01, 5.31it/s] 80%|████████ | 20/25 [00:05<00:00, 5.35it/s] 84%|████████▍ | 21/25 [00:05<00:00, 5.33it/s] 88%|████████▊ | 22/25 [00:05<00:00, 5.34it/s] 92%|█████████▏| 23/25 [00:05<00:00, 5.34it/s] 96%|█████████▌| 24/25 [00:06<00:00, 5.36it/s] 100%|██████████| 25/25 [00:06<00:00, 5.37it/s] 100%|██████████| 25/25 [00:06<00:00, 3.93it/s] Upsampling outputs from GLIDE-base 64x64 to 256x256 using 17 timesteps... 0%| | 0/15 [00:00<?, ?it/s] 7%|▋ | 1/15 [00:02<00:28, 2.01s/it] 13%|█▎ | 2/15 [00:04<00:26, 2.01s/it] 20%|██ | 3/15 [00:06<00:24, 2.01s/it] 27%|██▋ | 4/15 [00:06<00:15, 1.41s/it] 33%|███▎ | 5/15 [00:07<00:10, 1.09s/it] 40%|████ | 6/15 [00:07<00:07, 1.13it/s] 47%|████▋ | 7/15 [00:08<00:06, 1.31it/s] 53%|█████▎ | 8/15 [00:08<00:04, 1.47it/s] 60%|██████ | 9/15 [00:09<00:03, 1.60it/s] 67%|██████▋ | 10/15 [00:09<00:02, 1.69it/s] 73%|███████▎ | 11/15 [00:10<00:02, 1.77it/s] 80%|████████ | 12/15 [00:10<00:01, 1.83it/s] 87%|████████▋ | 13/15 [00:11<00:01, 1.87it/s] 93%|█████████▎| 14/15 [00:11<00:00, 1.90it/s] 100%|██████████| 15/15 [00:12<00:00, 1.92it/s] 100%|██████████| 15/15 [00:12<00:00, 1.24it/s]Prediction
laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48aeIDoraxq4lqo5ajbewcuwzpofqjl4StatusSucceededSourceWebHardware–Total durationCreatedInput
- seed
- 23211
- prompt
- an oil painting portraying earth
- side_x
- "64"
- side_y
- "64"
- batch_size
- "3"
- upsample_temp
- "0.997"
- guidance_scale
- 16
- upsample_stage
- timestep_respacing
- 27
- sr_timestep_respacing
- 17
{ "seed": 23211, "prompt": "an oil painting portraying earth", "side_x": "64", "side_y": "64", "batch_size": "3", "upsample_temp": "0.997", "guidance_scale": 16, "upsample_stage": true, "timestep_respacing": "27", "sr_timestep_respacing": "17" }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run laion-ai/laionide-v2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae", { input: { seed: 23211, prompt: "an oil painting portraying earth", side_x: "64", side_y: "64", batch_size: "3", upsample_temp: "0.997", guidance_scale: 16, upsample_stage: true, timestep_respacing: "27", sr_timestep_respacing: "17" } } ); 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 replicateImport the client:import replicateRun laion-ai/laionide-v2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae", input={ "seed": 23211, "prompt": "an oil painting portraying earth", "side_x": "64", "side_y": "64", "batch_size": "3", "upsample_temp": "0.997", "guidance_scale": 16, "upsample_stage": True, "timestep_respacing": "27", "sr_timestep_respacing": "17" } ) # The laion-ai/laionide-v2 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/laionide-v2/api#output-schema print(item)To learn more, take a look at the guide on getting started with Python.
Run laion-ai/laionide-v2 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": "laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae", "input": { "seed": 23211, "prompt": "an oil painting portraying earth", "side_x": "64", "side_y": "64", "batch_size": "3", "upsample_temp": "0.997", "guidance_scale": 16, "upsample_stage": true, "timestep_respacing": "27", "sr_timestep_respacing": "17" } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2022-02-23T06:09:37.583615Z", "created_at": "2022-02-23T06:08:55.698904Z", "data_removed": false, "error": null, "id": "oraxq4lqo5ajbewcuwzpofqjl4", "input": { "seed": 23211, "prompt": "an oil painting portraying earth", "side_x": "64", "side_y": "64", "batch_size": "3", "upsample_temp": "0.997", "guidance_scale": 16, "upsample_stage": true, "timestep_respacing": "27", "sr_timestep_respacing": "17" }, "logs": "Generating 64x64 samples with 27 timesteps using GLIDE-base-64px...\n\n 0%| | 0/25 [00:00<?, ?it/s]\n 4%|▍ | 1/25 [00:00<00:18, 1.27it/s]\n 8%|▊ | 2/25 [00:01<00:17, 1.32it/s]\n 12%|█▏ | 3/25 [00:02<00:16, 1.34it/s]\n 16%|█▌ | 4/25 [00:02<00:11, 1.90it/s]\n 20%|██ | 5/25 [00:02<00:08, 2.49it/s]\n 24%|██▍ | 6/25 [00:02<00:06, 3.05it/s]\n 28%|██▊ | 7/25 [00:02<00:05, 3.56it/s]\n 32%|███▏ | 8/25 [00:03<00:04, 4.00it/s]\n 36%|███▌ | 9/25 [00:03<00:03, 4.37it/s]\n 40%|████ | 10/25 [00:03<00:03, 4.65it/s]\n 44%|████▍ | 11/25 [00:03<00:02, 4.86it/s]\n 48%|████▊ | 12/25 [00:03<00:02, 5.03it/s]\n 52%|█████▏ | 13/25 [00:04<00:02, 5.13it/s]\n 56%|█████▌ | 14/25 [00:04<00:02, 5.22it/s]\n 60%|██████ | 15/25 [00:04<00:01, 5.29it/s]\n 64%|██████▍ | 16/25 [00:04<00:01, 5.33it/s]\n 68%|██████▊ | 17/25 [00:04<00:01, 5.33it/s]\n 72%|███████▏ | 18/25 [00:05<00:01, 5.36it/s]\n 76%|███████▌ | 19/25 [00:05<00:01, 5.38it/s]\n 80%|████████ | 20/25 [00:05<00:00, 5.41it/s]\n 84%|████████▍ | 21/25 [00:05<00:00, 5.43it/s]\n 88%|████████▊ | 22/25 [00:05<00:00, 5.44it/s]\n 92%|█████████▏| 23/25 [00:05<00:00, 5.43it/s]\n 96%|█████████▌| 24/25 [00:06<00:00, 5.42it/s]\n100%|██████████| 25/25 [00:06<00:00, 5.42it/s]\n100%|██████████| 25/25 [00:06<00:00, 3.96it/s]\nUpsampling outputs from GLIDE-base 64x64 to 256x256 using 17 timesteps...\n\n 0%| | 0/15 [00:00<?, ?it/s]\n 7%|▋ | 1/15 [00:02<00:28, 2.01s/it]\n 13%|█▎ | 2/15 [00:04<00:26, 2.01s/it]\n 20%|██ | 3/15 [00:06<00:24, 2.01s/it]\n 27%|██▋ | 4/15 [00:06<00:15, 1.42s/it]\n 33%|███▎ | 5/15 [00:07<00:10, 1.09s/it]\n 40%|████ | 6/15 [00:07<00:08, 1.12it/s]\n 47%|████▋ | 7/15 [00:08<00:06, 1.31it/s]\n 53%|█████▎ | 8/15 [00:08<00:04, 1.47it/s]\n 60%|██████ | 9/15 [00:09<00:03, 1.60it/s]\n 67%|██████▋ | 10/15 [00:09<00:02, 1.70it/s]\n 73%|███████▎ | 11/15 [00:10<00:02, 1.77it/s]\n 80%|████████ | 12/15 [00:10<00:01, 1.82it/s]\n 87%|████████▋ | 13/15 [00:11<00:01, 1.87it/s]\n 93%|█████████▎| 14/15 [00:11<00:00, 1.89it/s]\n100%|██████████| 15/15 [00:12<00:00, 1.91it/s]\n100%|██████████| 15/15 [00:12<00:00, 1.24it/s]", "metrics": { "predict_time": 32.158065, "total_time": 41.884711 }, "output": [ { "file": "https://replicate.delivery/mgxm/a6c5a5ce-17df-43ad-84bd-22873947e84a/upsample_predictions.png" } ], "started_at": "2022-02-23T06:09:05.425550Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/oraxq4lqo5ajbewcuwzpofqjl4", "cancel": "https://api.replicate.com/v1/predictions/oraxq4lqo5ajbewcuwzpofqjl4/cancel" }, "version": "45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae" }Generated inGenerating 64x64 samples with 27 timesteps using GLIDE-base-64px... 0%| | 0/25 [00:00<?, ?it/s] 4%|▍ | 1/25 [00:00<00:18, 1.27it/s] 8%|▊ | 2/25 [00:01<00:17, 1.32it/s] 12%|█▏ | 3/25 [00:02<00:16, 1.34it/s] 16%|█▌ | 4/25 [00:02<00:11, 1.90it/s] 20%|██ | 5/25 [00:02<00:08, 2.49it/s] 24%|██▍ | 6/25 [00:02<00:06, 3.05it/s] 28%|██▊ | 7/25 [00:02<00:05, 3.56it/s] 32%|███▏ | 8/25 [00:03<00:04, 4.00it/s] 36%|███▌ | 9/25 [00:03<00:03, 4.37it/s] 40%|████ | 10/25 [00:03<00:03, 4.65it/s] 44%|████▍ | 11/25 [00:03<00:02, 4.86it/s] 48%|████▊ | 12/25 [00:03<00:02, 5.03it/s] 52%|█████▏ | 13/25 [00:04<00:02, 5.13it/s] 56%|█████▌ | 14/25 [00:04<00:02, 5.22it/s] 60%|██████ | 15/25 [00:04<00:01, 5.29it/s] 64%|██████▍ | 16/25 [00:04<00:01, 5.33it/s] 68%|██████▊ | 17/25 [00:04<00:01, 5.33it/s] 72%|███████▏ | 18/25 [00:05<00:01, 5.36it/s] 76%|███████▌ | 19/25 [00:05<00:01, 5.38it/s] 80%|████████ | 20/25 [00:05<00:00, 5.41it/s] 84%|████████▍ | 21/25 [00:05<00:00, 5.43it/s] 88%|████████▊ | 22/25 [00:05<00:00, 5.44it/s] 92%|█████████▏| 23/25 [00:05<00:00, 5.43it/s] 96%|█████████▌| 24/25 [00:06<00:00, 5.42it/s] 100%|██████████| 25/25 [00:06<00:00, 5.42it/s] 100%|██████████| 25/25 [00:06<00:00, 3.96it/s] Upsampling outputs from GLIDE-base 64x64 to 256x256 using 17 timesteps... 0%| | 0/15 [00:00<?, ?it/s] 7%|▋ | 1/15 [00:02<00:28, 2.01s/it] 13%|█▎ | 2/15 [00:04<00:26, 2.01s/it] 20%|██ | 3/15 [00:06<00:24, 2.01s/it] 27%|██▋ | 4/15 [00:06<00:15, 1.42s/it] 33%|███▎ | 5/15 [00:07<00:10, 1.09s/it] 40%|████ | 6/15 [00:07<00:08, 1.12it/s] 47%|████▋ | 7/15 [00:08<00:06, 1.31it/s] 53%|█████▎ | 8/15 [00:08<00:04, 1.47it/s] 60%|██████ | 9/15 [00:09<00:03, 1.60it/s] 67%|██████▋ | 10/15 [00:09<00:02, 1.70it/s] 73%|███████▎ | 11/15 [00:10<00:02, 1.77it/s] 80%|████████ | 12/15 [00:10<00:01, 1.82it/s] 87%|████████▋ | 13/15 [00:11<00:01, 1.87it/s] 93%|█████████▎| 14/15 [00:11<00:00, 1.89it/s] 100%|██████████| 15/15 [00:12<00:00, 1.91it/s] 100%|██████████| 15/15 [00:12<00:00, 1.24it/s]Prediction
laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48aeIDxjcgdfiwo5frjajgvijhsqqxiiStatusSucceededSourceWebHardware–Total durationCreatedInput
- seed
- 23211
- prompt
- an oil painting of a canadian goose
- side_x
- "64"
- side_y
- "64"
- batch_size
- "3"
- upsample_temp
- "1.0"
- guidance_scale
- 12
- upsample_stage
- timestep_respacing
- 27
- sr_timestep_respacing
- 17
{ "seed": 23211, "prompt": "an oil painting of a canadian goose", "side_x": "64", "side_y": "64", "batch_size": "3", "upsample_temp": "1.0", "guidance_scale": 12, "upsample_stage": true, "timestep_respacing": "27", "sr_timestep_respacing": "17" }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run laion-ai/laionide-v2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae", { input: { seed: 23211, prompt: "an oil painting of a canadian goose", side_x: "64", side_y: "64", batch_size: "3", upsample_temp: "1.0", guidance_scale: 12, upsample_stage: true, timestep_respacing: "27", sr_timestep_respacing: "17" } } ); 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 replicateImport the client:import replicateRun laion-ai/laionide-v2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae", input={ "seed": 23211, "prompt": "an oil painting of a canadian goose", "side_x": "64", "side_y": "64", "batch_size": "3", "upsample_temp": "1.0", "guidance_scale": 12, "upsample_stage": True, "timestep_respacing": "27", "sr_timestep_respacing": "17" } ) # The laion-ai/laionide-v2 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/laionide-v2/api#output-schema print(item)To learn more, take a look at the guide on getting started with Python.
Run laion-ai/laionide-v2 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": "laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae", "input": { "seed": 23211, "prompt": "an oil painting of a canadian goose", "side_x": "64", "side_y": "64", "batch_size": "3", "upsample_temp": "1.0", "guidance_scale": 12, "upsample_stage": true, "timestep_respacing": "27", "sr_timestep_respacing": "17" } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2022-02-23T06:16:47.657348Z", "created_at": "2022-02-23T06:16:17.159340Z", "data_removed": false, "error": null, "id": "xjcgdfiwo5frjajgvijhsqqxii", "input": { "seed": 23211, "prompt": "an oil painting of a canadian goose", "side_x": "64", "side_y": "64", "batch_size": "3", "upsample_temp": "1.0", "guidance_scale": 12, "upsample_stage": true, "timestep_respacing": "27", "sr_timestep_respacing": "17" }, "logs": "Generating 64x64 samples with 27 timesteps using GLIDE-base-64px...\n\n 0%| | 0/25 [00:00<?, ?it/s]\n 4%|▍ | 1/25 [00:00<00:18, 1.28it/s]\n 8%|▊ | 2/25 [00:01<00:16, 1.37it/s]\n 12%|█▏ | 3/25 [00:02<00:15, 1.40it/s]\n 16%|█▌ | 4/25 [00:02<00:10, 2.00it/s]\n 20%|██ | 5/25 [00:02<00:07, 2.61it/s]\n 24%|██▍ | 6/25 [00:02<00:05, 3.20it/s]\n 28%|██▊ | 7/25 [00:02<00:04, 3.74it/s]\n 32%|███▏ | 8/25 [00:03<00:04, 4.21it/s]\n 36%|███▌ | 9/25 [00:03<00:03, 4.60it/s]\n 40%|████ | 10/25 [00:03<00:03, 4.90it/s]\n 44%|████▍ | 11/25 [00:03<00:02, 5.13it/s]\n 48%|████▊ | 12/25 [00:03<00:02, 5.30it/s]\n 52%|█████▏ | 13/25 [00:03<00:02, 5.42it/s]\n 56%|█████▌ | 14/25 [00:04<00:01, 5.50it/s]\n 60%|██████ | 15/25 [00:04<00:01, 5.57it/s]\n 64%|██████▍ | 16/25 [00:04<00:01, 5.62it/s]\n 68%|██████▊ | 17/25 [00:04<00:01, 5.66it/s]\n 72%|███████▏ | 18/25 [00:04<00:01, 5.67it/s]\n 76%|███████▌ | 19/25 [00:04<00:01, 5.67it/s]\n 80%|████████ | 20/25 [00:05<00:00, 5.70it/s]\n 84%|████████▍ | 21/25 [00:05<00:00, 5.70it/s]\n 88%|████████▊ | 22/25 [00:05<00:00, 5.68it/s]\n 92%|█████████▏| 23/25 [00:05<00:00, 5.69it/s]\n 96%|█████████▌| 24/25 [00:05<00:00, 5.70it/s]\n100%|██████████| 25/25 [00:06<00:00, 5.70it/s]\n100%|██████████| 25/25 [00:06<00:00, 4.16it/s]\nUpsampling outputs from GLIDE-base 64x64 to 256x256 using 17 timesteps...\n\n 0%| | 0/15 [00:00<?, ?it/s]\n 7%|▋ | 1/15 [00:01<00:26, 1.89s/it]Caught SIGTERM, exiting...\n\n 13%|█▎ | 2/15 [00:03<00:24, 1.88s/it]\n 20%|██ | 3/15 [00:05<00:22, 1.88s/it]\n 27%|██▋ | 4/15 [00:06<00:14, 1.33s/it]\n 33%|███▎ | 5/15 [00:06<00:10, 1.02s/it]\n 40%|████ | 6/15 [00:07<00:07, 1.20it/s]\n 47%|████▋ | 7/15 [00:07<00:05, 1.40it/s]\n 53%|█████▎ | 8/15 [00:08<00:04, 1.56it/s]\n 60%|██████ | 9/15 [00:08<00:03, 1.70it/s]\n 67%|██████▋ | 10/15 [00:08<00:02, 1.81it/s]\n 73%|███████▎ | 11/15 [00:09<00:02, 1.89it/s]\n 80%|████████ | 12/15 [00:09<00:01, 1.95it/s]\n 87%|████████▋ | 13/15 [00:10<00:01, 2.00it/s]\n 93%|█████████▎| 14/15 [00:10<00:00, 2.03it/s]\n100%|██████████| 15/15 [00:11<00:00, 2.05it/s]\n100%|██████████| 15/15 [00:11<00:00, 1.32it/s]", "metrics": { "predict_time": 30.288146, "total_time": 30.498008 }, "output": [ { "file": "https://replicate.delivery/mgxm/358863d5-e860-4694-a40d-85de49c79251/base_predictions.png" }, { "file": "https://replicate.delivery/mgxm/7149f416-abe5-4d8d-af7d-cc33cda0491d/upsample_predictions.png" } ], "started_at": "2022-02-23T06:16:17.369202Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/xjcgdfiwo5frjajgvijhsqqxii", "cancel": "https://api.replicate.com/v1/predictions/xjcgdfiwo5frjajgvijhsqqxii/cancel" }, "version": "45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae" }Generated inGenerating 64x64 samples with 27 timesteps using GLIDE-base-64px... 0%| | 0/25 [00:00<?, ?it/s] 4%|▍ | 1/25 [00:00<00:18, 1.28it/s] 8%|▊ | 2/25 [00:01<00:16, 1.37it/s] 12%|█▏ | 3/25 [00:02<00:15, 1.40it/s] 16%|█▌ | 4/25 [00:02<00:10, 2.00it/s] 20%|██ | 5/25 [00:02<00:07, 2.61it/s] 24%|██▍ | 6/25 [00:02<00:05, 3.20it/s] 28%|██▊ | 7/25 [00:02<00:04, 3.74it/s] 32%|███▏ | 8/25 [00:03<00:04, 4.21it/s] 36%|███▌ | 9/25 [00:03<00:03, 4.60it/s] 40%|████ | 10/25 [00:03<00:03, 4.90it/s] 44%|████▍ | 11/25 [00:03<00:02, 5.13it/s] 48%|████▊ | 12/25 [00:03<00:02, 5.30it/s] 52%|█████▏ | 13/25 [00:03<00:02, 5.42it/s] 56%|█████▌ | 14/25 [00:04<00:01, 5.50it/s] 60%|██████ | 15/25 [00:04<00:01, 5.57it/s] 64%|██████▍ | 16/25 [00:04<00:01, 5.62it/s] 68%|██████▊ | 17/25 [00:04<00:01, 5.66it/s] 72%|███████▏ | 18/25 [00:04<00:01, 5.67it/s] 76%|███████▌ | 19/25 [00:04<00:01, 5.67it/s] 80%|████████ | 20/25 [00:05<00:00, 5.70it/s] 84%|████████▍ | 21/25 [00:05<00:00, 5.70it/s] 88%|████████▊ | 22/25 [00:05<00:00, 5.68it/s] 92%|█████████▏| 23/25 [00:05<00:00, 5.69it/s] 96%|█████████▌| 24/25 [00:05<00:00, 5.70it/s] 100%|██████████| 25/25 [00:06<00:00, 5.70it/s] 100%|██████████| 25/25 [00:06<00:00, 4.16it/s] Upsampling outputs from GLIDE-base 64x64 to 256x256 using 17 timesteps... 0%| | 0/15 [00:00<?, ?it/s] 7%|▋ | 1/15 [00:01<00:26, 1.89s/it]Caught SIGTERM, exiting... 13%|█▎ | 2/15 [00:03<00:24, 1.88s/it] 20%|██ | 3/15 [00:05<00:22, 1.88s/it] 27%|██▋ | 4/15 [00:06<00:14, 1.33s/it] 33%|███▎ | 5/15 [00:06<00:10, 1.02s/it] 40%|████ | 6/15 [00:07<00:07, 1.20it/s] 47%|████▋ | 7/15 [00:07<00:05, 1.40it/s] 53%|█████▎ | 8/15 [00:08<00:04, 1.56it/s] 60%|██████ | 9/15 [00:08<00:03, 1.70it/s] 67%|██████▋ | 10/15 [00:08<00:02, 1.81it/s] 73%|███████▎ | 11/15 [00:09<00:02, 1.89it/s] 80%|████████ | 12/15 [00:09<00:01, 1.95it/s] 87%|████████▋ | 13/15 [00:10<00:01, 2.00it/s] 93%|█████████▎| 14/15 [00:10<00:00, 2.03it/s] 100%|██████████| 15/15 [00:11<00:00, 2.05it/s] 100%|██████████| 15/15 [00:11<00:00, 1.32it/s]Prediction
laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48aeIDunde4r2ilvf77czdj6btqpsiwqStatusSucceededSourceWebHardware–Total durationCreatedInput
- seed
- 23211
- prompt
- a cartoon of a horse-goose hybrid chimera combo. a goose is imitating a horse. royalty free.
- side_x
- "64"
- side_y
- "64"
- batch_size
- "3"
- upsample_temp
- "0.997"
- guidance_scale
- 4
- upsample_stage
- timestep_respacing
- 27
- sr_timestep_respacing
- 17
{ "seed": 23211, "prompt": "a cartoon of a horse-goose hybrid chimera combo. a goose is imitating a horse. royalty free.", "side_x": "64", "side_y": "64", "batch_size": "3", "upsample_temp": "0.997", "guidance_scale": 4, "upsample_stage": true, "timestep_respacing": "27", "sr_timestep_respacing": "17" }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run laion-ai/laionide-v2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae", { input: { seed: 23211, prompt: "a cartoon of a horse-goose hybrid chimera combo. a goose is imitating a horse. royalty free.", side_x: "64", side_y: "64", batch_size: "3", upsample_temp: "0.997", guidance_scale: 4, upsample_stage: true, timestep_respacing: "27", sr_timestep_respacing: "17" } } ); 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 replicateImport the client:import replicateRun laion-ai/laionide-v2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae", input={ "seed": 23211, "prompt": "a cartoon of a horse-goose hybrid chimera combo. a goose is imitating a horse. royalty free.", "side_x": "64", "side_y": "64", "batch_size": "3", "upsample_temp": "0.997", "guidance_scale": 4, "upsample_stage": True, "timestep_respacing": "27", "sr_timestep_respacing": "17" } ) # The laion-ai/laionide-v2 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/laionide-v2/api#output-schema print(item)To learn more, take a look at the guide on getting started with Python.
Run laion-ai/laionide-v2 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": "laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae", "input": { "seed": 23211, "prompt": "a cartoon of a horse-goose hybrid chimera combo. a goose is imitating a horse. royalty free.", "side_x": "64", "side_y": "64", "batch_size": "3", "upsample_temp": "0.997", "guidance_scale": 4, "upsample_stage": true, "timestep_respacing": "27", "sr_timestep_respacing": "17" } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2022-02-23T06:24:20.454598Z", "created_at": "2022-02-23T06:23:47.141435Z", "data_removed": false, "error": null, "id": "unde4r2ilvf77czdj6btqpsiwq", "input": { "seed": 23211, "prompt": "a cartoon of a horse-goose hybrid chimera combo. a goose is imitating a horse. royalty free.", "side_x": "64", "side_y": "64", "batch_size": "3", "upsample_temp": "0.997", "guidance_scale": 4, "upsample_stage": true, "timestep_respacing": "27", "sr_timestep_respacing": "17" }, "logs": "Generating 64x64 samples with 27 timesteps using GLIDE-base-64px...\n\n 0%| | 0/25 [00:00<?, ?it/s]\n 4%|▍ | 1/25 [00:00<00:19, 1.24it/s]\n 8%|▊ | 2/25 [00:01<00:17, 1.32it/s]\n 12%|█▏ | 3/25 [00:02<00:16, 1.35it/s]\n 16%|█▌ | 4/25 [00:02<00:10, 1.92it/s]\n 20%|██ | 5/25 [00:02<00:07, 2.50it/s]\n 24%|██▍ | 6/25 [00:02<00:06, 3.06it/s]\n 28%|██▊ | 7/25 [00:02<00:05, 3.58it/s]\n 32%|███▏ | 8/25 [00:03<00:04, 4.03it/s]\n 36%|███▌ | 9/25 [00:03<00:03, 4.39it/s]\n 40%|████ | 10/25 [00:03<00:03, 4.69it/s]\n 44%|████▍ | 11/25 [00:03<00:02, 4.90it/s]\n 48%|████▊ | 12/25 [00:03<00:02, 5.07it/s]\n 52%|█████▏ | 13/25 [00:04<00:02, 5.18it/s]\n 56%|█████▌ | 14/25 [00:04<00:02, 5.28it/s]\n 60%|██████ | 15/25 [00:04<00:01, 5.34it/s]\n 64%|██████▍ | 16/25 [00:04<00:01, 5.38it/s]\n 68%|██████▊ | 17/25 [00:04<00:01, 5.41it/s]\n 72%|███████▏ | 18/25 [00:04<00:01, 5.43it/s]\n 76%|███████▌ | 19/25 [00:05<00:01, 5.44it/s]\n 80%|████████ | 20/25 [00:05<00:00, 5.46it/s]\n 84%|████████▍ | 21/25 [00:05<00:00, 5.45it/s]\n 88%|████████▊ | 22/25 [00:05<00:00, 5.46it/s]\n 92%|█████████▏| 23/25 [00:05<00:00, 5.43it/s]\n 96%|█████████▌| 24/25 [00:06<00:00, 5.40it/s]\n100%|██████████| 25/25 [00:06<00:00, 5.42it/s]\n100%|██████████| 25/25 [00:06<00:00, 3.98it/s]\nUpsampling outputs from GLIDE-base 64x64 to 256x256 using 17 timesteps...\n\n 0%| | 0/15 [00:00<?, ?it/s]\n 7%|▋ | 1/15 [00:01<00:27, 1.99s/it]\n 13%|█▎ | 2/15 [00:03<00:25, 1.99s/it]\n 20%|██ | 3/15 [00:05<00:23, 1.99s/it]\n 27%|██▋ | 4/15 [00:06<00:15, 1.40s/it]\n 33%|███▎ | 5/15 [00:06<00:10, 1.08s/it]\n 40%|████ | 6/15 [00:07<00:07, 1.13it/s]\n 47%|████▋ | 7/15 [00:07<00:06, 1.32it/s]\n 53%|█████▎ | 8/15 [00:08<00:04, 1.48it/s]\n 60%|██████ | 9/15 [00:08<00:03, 1.61it/s]\n 67%|██████▋ | 10/15 [00:09<00:02, 1.71it/s]\n 73%|███████▎ | 11/15 [00:09<00:02, 1.78it/s]\n 80%|████████ | 12/15 [00:10<00:01, 1.84it/s]\n 87%|████████▋ | 13/15 [00:10<00:01, 1.88it/s]\n 93%|█████████▎| 14/15 [00:11<00:00, 1.91it/s]\n100%|██████████| 15/15 [00:12<00:00, 1.93it/s]\n100%|██████████| 15/15 [00:12<00:00, 1.25it/s]", "metrics": { "predict_time": 33.084228, "total_time": 33.313163 }, "output": [ { "file": "https://replicate.delivery/mgxm/51e25d3f-dcbd-41e4-96dd-9a86499fbb23/base_predictions.png" }, { "file": "https://replicate.delivery/mgxm/ac3bc35a-e432-443c-8c26-b6d1a1e8bd2c/upsample_predictions.png" } ], "started_at": "2022-02-23T06:23:47.370370Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/unde4r2ilvf77czdj6btqpsiwq", "cancel": "https://api.replicate.com/v1/predictions/unde4r2ilvf77czdj6btqpsiwq/cancel" }, "version": "45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae" }Generated inGenerating 64x64 samples with 27 timesteps using GLIDE-base-64px... 0%| | 0/25 [00:00<?, ?it/s] 4%|▍ | 1/25 [00:00<00:19, 1.24it/s] 8%|▊ | 2/25 [00:01<00:17, 1.32it/s] 12%|█▏ | 3/25 [00:02<00:16, 1.35it/s] 16%|█▌ | 4/25 [00:02<00:10, 1.92it/s] 20%|██ | 5/25 [00:02<00:07, 2.50it/s] 24%|██▍ | 6/25 [00:02<00:06, 3.06it/s] 28%|██▊ | 7/25 [00:02<00:05, 3.58it/s] 32%|███▏ | 8/25 [00:03<00:04, 4.03it/s] 36%|███▌ | 9/25 [00:03<00:03, 4.39it/s] 40%|████ | 10/25 [00:03<00:03, 4.69it/s] 44%|████▍ | 11/25 [00:03<00:02, 4.90it/s] 48%|████▊ | 12/25 [00:03<00:02, 5.07it/s] 52%|█████▏ | 13/25 [00:04<00:02, 5.18it/s] 56%|█████▌ | 14/25 [00:04<00:02, 5.28it/s] 60%|██████ | 15/25 [00:04<00:01, 5.34it/s] 64%|██████▍ | 16/25 [00:04<00:01, 5.38it/s] 68%|██████▊ | 17/25 [00:04<00:01, 5.41it/s] 72%|███████▏ | 18/25 [00:04<00:01, 5.43it/s] 76%|███████▌ | 19/25 [00:05<00:01, 5.44it/s] 80%|████████ | 20/25 [00:05<00:00, 5.46it/s] 84%|████████▍ | 21/25 [00:05<00:00, 5.45it/s] 88%|████████▊ | 22/25 [00:05<00:00, 5.46it/s] 92%|█████████▏| 23/25 [00:05<00:00, 5.43it/s] 96%|█████████▌| 24/25 [00:06<00:00, 5.40it/s] 100%|██████████| 25/25 [00:06<00:00, 5.42it/s] 100%|██████████| 25/25 [00:06<00:00, 3.98it/s] Upsampling outputs from GLIDE-base 64x64 to 256x256 using 17 timesteps... 0%| | 0/15 [00:00<?, ?it/s] 7%|▋ | 1/15 [00:01<00:27, 1.99s/it] 13%|█▎ | 2/15 [00:03<00:25, 1.99s/it] 20%|██ | 3/15 [00:05<00:23, 1.99s/it] 27%|██▋ | 4/15 [00:06<00:15, 1.40s/it] 33%|███▎ | 5/15 [00:06<00:10, 1.08s/it] 40%|████ | 6/15 [00:07<00:07, 1.13it/s] 47%|████▋ | 7/15 [00:07<00:06, 1.32it/s] 53%|█████▎ | 8/15 [00:08<00:04, 1.48it/s] 60%|██████ | 9/15 [00:08<00:03, 1.61it/s] 67%|██████▋ | 10/15 [00:09<00:02, 1.71it/s] 73%|███████▎ | 11/15 [00:09<00:02, 1.78it/s] 80%|████████ | 12/15 [00:10<00:01, 1.84it/s] 87%|████████▋ | 13/15 [00:10<00:01, 1.88it/s] 93%|█████████▎| 14/15 [00:11<00:00, 1.91it/s] 100%|██████████| 15/15 [00:12<00:00, 1.93it/s] 100%|██████████| 15/15 [00:12<00:00, 1.25it/s]Prediction
laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48aeIDphacwqssqjerrn2pp5x3c3lkeaStatusSucceededSourceWebHardware–Total durationCreatedInput
- prompt
- a 3d model of a rooster
- side_x
- 64
- side_y
- 64
- batch_size
- 3
- upsample_temp
- 0.998
- guidance_scale
- 10
- upsample_stage
- timestep_respacing
- 40
- sr_timestep_respacing
- 17
{ "prompt": "a 3d model of a rooster", "side_x": 64, "side_y": 64, "batch_size": 3, "upsample_temp": 0.998, "guidance_scale": 10, "upsample_stage": true, "timestep_respacing": "40", "sr_timestep_respacing": "17" }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run laion-ai/laionide-v2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae", { input: { prompt: "a 3d model of a rooster", side_x: 64, side_y: 64, batch_size: 3, upsample_temp: 0.998, guidance_scale: 10, upsample_stage: true, timestep_respacing: "40", sr_timestep_respacing: "17" } } ); 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 replicateImport the client:import replicateRun laion-ai/laionide-v2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae", input={ "prompt": "a 3d model of a rooster", "side_x": 64, "side_y": 64, "batch_size": 3, "upsample_temp": 0.998, "guidance_scale": 10, "upsample_stage": True, "timestep_respacing": "40", "sr_timestep_respacing": "17" } ) # The laion-ai/laionide-v2 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/laionide-v2/api#output-schema print(item)To learn more, take a look at the guide on getting started with Python.
Run laion-ai/laionide-v2 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": "laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae", "input": { "prompt": "a 3d model of a rooster", "side_x": 64, "side_y": 64, "batch_size": 3, "upsample_temp": 0.998, "guidance_scale": 10, "upsample_stage": true, "timestep_respacing": "40", "sr_timestep_respacing": "17" } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2022-02-23T06:29:23.053600Z", "created_at": "2022-02-23T06:28:46.627971Z", "data_removed": false, "error": null, "id": "phacwqssqjerrn2pp5x3c3lkea", "input": { "prompt": "a 3d model of a rooster", "side_x": 64, "side_y": 64, "batch_size": 3, "upsample_temp": 0.998, "guidance_scale": 10, "upsample_stage": true, "timestep_respacing": "40", "sr_timestep_respacing": "17" }, "logs": "Generating 64x64 samples with 40 timesteps using GLIDE-base-64px...\n\n 0%| | 0/38 [00:00<?, ?it/s]\n 3%|▎ | 1/38 [00:00<00:28, 1.30it/s]\n 5%|▌ | 2/38 [00:01<00:26, 1.34it/s]\n 8%|▊ | 3/38 [00:02<00:25, 1.35it/s]\n 11%|█ | 4/38 [00:02<00:17, 1.92it/s]\n 13%|█▎ | 5/38 [00:02<00:13, 2.51it/s]\n 16%|█▌ | 6/38 [00:02<00:10, 3.08it/s]\n 18%|█▊ | 7/38 [00:02<00:08, 3.60it/s]\n 21%|██ | 8/38 [00:03<00:07, 4.04it/s]\n 24%|██▎ | 9/38 [00:03<00:06, 4.39it/s]\n 26%|██▋ | 10/38 [00:03<00:05, 4.67it/s]\n 29%|██▉ | 11/38 [00:03<00:05, 4.89it/s]\n 32%|███▏ | 12/38 [00:03<00:05, 5.06it/s]\n 34%|███▍ | 13/38 [00:04<00:04, 5.18it/s]\n 37%|███▋ | 14/38 [00:04<00:04, 5.26it/s]\n 39%|███▉ | 15/38 [00:04<00:04, 5.31it/s]\n 42%|████▏ | 16/38 [00:04<00:04, 5.34it/s]\n 45%|████▍ | 17/38 [00:04<00:03, 5.37it/s]\n 47%|████▋ | 18/38 [00:04<00:03, 5.39it/s]\n 50%|█████ | 19/38 [00:05<00:03, 5.38it/s]\n 53%|█████▎ | 20/38 [00:05<00:03, 5.39it/s]\n 55%|█████▌ | 21/38 [00:05<00:03, 5.39it/s]\n 58%|█████▊ | 22/38 [00:05<00:02, 5.41it/s]\n 61%|██████ | 23/38 [00:05<00:02, 5.42it/s]\n 63%|██████▎ | 24/38 [00:06<00:02, 5.42it/s]\n 66%|██████▌ | 25/38 [00:06<00:02, 5.43it/s]\n 68%|██████▊ | 26/38 [00:06<00:02, 5.43it/s]\n 71%|███████ | 27/38 [00:06<00:02, 5.42it/s]\n 74%|███████▎ | 28/38 [00:06<00:01, 5.39it/s]\n 76%|███████▋ | 29/38 [00:07<00:01, 5.39it/s]\n 79%|███████▉ | 30/38 [00:07<00:01, 5.39it/s]\n 82%|████████▏ | 31/38 [00:07<00:01, 5.40it/s]\n 84%|████████▍ | 32/38 [00:07<00:01, 5.41it/s]\n 87%|████████▋ | 33/38 [00:07<00:00, 5.41it/s]\n 89%|████████▉ | 34/38 [00:07<00:00, 5.42it/s]\n 92%|█████████▏| 35/38 [00:08<00:00, 5.42it/s]\n 95%|█████████▍| 36/38 [00:08<00:00, 5.40it/s]\n 97%|█████████▋| 37/38 [00:08<00:00, 5.40it/s]\n100%|██████████| 38/38 [00:08<00:00, 5.41it/s]\n100%|██████████| 38/38 [00:08<00:00, 4.38it/s]\nUpsampling outputs from GLIDE-base 64x64 to 256x256 using 17 timesteps...\n\n 0%| | 0/15 [00:00<?, ?it/s]\n 7%|▋ | 1/15 [00:02<00:28, 2.02s/it]\n 13%|█▎ | 2/15 [00:04<00:26, 2.01s/it]\n 20%|██ | 3/15 [00:06<00:24, 2.01s/it]\n 27%|██▋ | 4/15 [00:06<00:15, 1.42s/it]\n 33%|███▎ | 5/15 [00:07<00:10, 1.09s/it]\n 40%|████ | 6/15 [00:07<00:08, 1.12it/s]\n 47%|████▋ | 7/15 [00:08<00:06, 1.30it/s]\n 53%|█████▎ | 8/15 [00:08<00:04, 1.46it/s]\n 60%|██████ | 9/15 [00:09<00:03, 1.59it/s]\n 67%|██████▋ | 10/15 [00:09<00:02, 1.68it/s]\n 73%|███████▎ | 11/15 [00:10<00:02, 1.76it/s]\n 80%|████████ | 12/15 [00:10<00:01, 1.81it/s]\n 87%|████████▋ | 13/15 [00:11<00:01, 1.85it/s]\n 93%|█████████▎| 14/15 [00:11<00:00, 1.88it/s]\n100%|██████████| 15/15 [00:12<00:00, 1.90it/s]\n100%|██████████| 15/15 [00:12<00:00, 1.23it/s]", "metrics": { "predict_time": 34.959629, "total_time": 36.425629 }, "output": [ { "file": "https://replicate.delivery/mgxm/ae810877-8e77-4319-a1c8-545ce6361589/base_predictions.png" }, { "file": "https://replicate.delivery/mgxm/2f135dd1-3071-4482-bc56-9cf91c0a78fd/upsample_predictions.png" } ], "started_at": "2022-02-23T06:28:48.093971Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/phacwqssqjerrn2pp5x3c3lkea", "cancel": "https://api.replicate.com/v1/predictions/phacwqssqjerrn2pp5x3c3lkea/cancel" }, "version": "45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae" }Generated inGenerating 64x64 samples with 40 timesteps using GLIDE-base-64px... 0%| | 0/38 [00:00<?, ?it/s] 3%|▎ | 1/38 [00:00<00:28, 1.30it/s] 5%|▌ | 2/38 [00:01<00:26, 1.34it/s] 8%|▊ | 3/38 [00:02<00:25, 1.35it/s] 11%|█ | 4/38 [00:02<00:17, 1.92it/s] 13%|█▎ | 5/38 [00:02<00:13, 2.51it/s] 16%|█▌ | 6/38 [00:02<00:10, 3.08it/s] 18%|█▊ | 7/38 [00:02<00:08, 3.60it/s] 21%|██ | 8/38 [00:03<00:07, 4.04it/s] 24%|██▎ | 9/38 [00:03<00:06, 4.39it/s] 26%|██▋ | 10/38 [00:03<00:05, 4.67it/s] 29%|██▉ | 11/38 [00:03<00:05, 4.89it/s] 32%|███▏ | 12/38 [00:03<00:05, 5.06it/s] 34%|███▍ | 13/38 [00:04<00:04, 5.18it/s] 37%|███▋ | 14/38 [00:04<00:04, 5.26it/s] 39%|███▉ | 15/38 [00:04<00:04, 5.31it/s] 42%|████▏ | 16/38 [00:04<00:04, 5.34it/s] 45%|████▍ | 17/38 [00:04<00:03, 5.37it/s] 47%|████▋ | 18/38 [00:04<00:03, 5.39it/s] 50%|█████ | 19/38 [00:05<00:03, 5.38it/s] 53%|█████▎ | 20/38 [00:05<00:03, 5.39it/s] 55%|█████▌ | 21/38 [00:05<00:03, 5.39it/s] 58%|█████▊ | 22/38 [00:05<00:02, 5.41it/s] 61%|██████ | 23/38 [00:05<00:02, 5.42it/s] 63%|██████▎ | 24/38 [00:06<00:02, 5.42it/s] 66%|██████▌ | 25/38 [00:06<00:02, 5.43it/s] 68%|██████▊ | 26/38 [00:06<00:02, 5.43it/s] 71%|███████ | 27/38 [00:06<00:02, 5.42it/s] 74%|███████▎ | 28/38 [00:06<00:01, 5.39it/s] 76%|███████▋ | 29/38 [00:07<00:01, 5.39it/s] 79%|███████▉ | 30/38 [00:07<00:01, 5.39it/s] 82%|████████▏ | 31/38 [00:07<00:01, 5.40it/s] 84%|████████▍ | 32/38 [00:07<00:01, 5.41it/s] 87%|████████▋ | 33/38 [00:07<00:00, 5.41it/s] 89%|████████▉ | 34/38 [00:07<00:00, 5.42it/s] 92%|█████████▏| 35/38 [00:08<00:00, 5.42it/s] 95%|█████████▍| 36/38 [00:08<00:00, 5.40it/s] 97%|█████████▋| 37/38 [00:08<00:00, 5.40it/s] 100%|██████████| 38/38 [00:08<00:00, 5.41it/s] 100%|██████████| 38/38 [00:08<00:00, 4.38it/s] Upsampling outputs from GLIDE-base 64x64 to 256x256 using 17 timesteps... 0%| | 0/15 [00:00<?, ?it/s] 7%|▋ | 1/15 [00:02<00:28, 2.02s/it] 13%|█▎ | 2/15 [00:04<00:26, 2.01s/it] 20%|██ | 3/15 [00:06<00:24, 2.01s/it] 27%|██▋ | 4/15 [00:06<00:15, 1.42s/it] 33%|███▎ | 5/15 [00:07<00:10, 1.09s/it] 40%|████ | 6/15 [00:07<00:08, 1.12it/s] 47%|████▋ | 7/15 [00:08<00:06, 1.30it/s] 53%|█████▎ | 8/15 [00:08<00:04, 1.46it/s] 60%|██████ | 9/15 [00:09<00:03, 1.59it/s] 67%|██████▋ | 10/15 [00:09<00:02, 1.68it/s] 73%|███████▎ | 11/15 [00:10<00:02, 1.76it/s] 80%|████████ | 12/15 [00:10<00:01, 1.81it/s] 87%|████████▋ | 13/15 [00:11<00:01, 1.85it/s] 93%|█████████▎| 14/15 [00:11<00:00, 1.88it/s] 100%|██████████| 15/15 [00:12<00:00, 1.90it/s] 100%|██████████| 15/15 [00:12<00:00, 1.23it/s]Prediction
laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48aeIDx2pid4zdufhp5ahnyw7cuyc5bqStatusSucceededSourceWebHardware–Total durationCreatedInput
- prompt
- 3d model of a pikachu
- side_x
- 64
- side_y
- 64
- batch_size
- 3
- upsample_temp
- "1.0"
- guidance_scale
- 16
- upsample_stage
- timestep_respacing
- 40
- sr_timestep_respacing
- 17
{ "prompt": "3d model of a pikachu", "side_x": 64, "side_y": 64, "batch_size": 3, "upsample_temp": "1.0", "guidance_scale": 16, "upsample_stage": true, "timestep_respacing": "40", "sr_timestep_respacing": "17" }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run laion-ai/laionide-v2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae", { input: { prompt: "3d model of a pikachu", side_x: 64, side_y: 64, batch_size: 3, upsample_temp: "1.0", guidance_scale: 16, upsample_stage: true, timestep_respacing: "40", sr_timestep_respacing: "17" } } ); 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 replicateImport the client:import replicateRun laion-ai/laionide-v2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae", input={ "prompt": "3d model of a pikachu", "side_x": 64, "side_y": 64, "batch_size": 3, "upsample_temp": "1.0", "guidance_scale": 16, "upsample_stage": True, "timestep_respacing": "40", "sr_timestep_respacing": "17" } ) # The laion-ai/laionide-v2 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/laionide-v2/api#output-schema print(item)To learn more, take a look at the guide on getting started with Python.
Run laion-ai/laionide-v2 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": "laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae", "input": { "prompt": "3d model of a pikachu", "side_x": 64, "side_y": 64, "batch_size": 3, "upsample_temp": "1.0", "guidance_scale": 16, "upsample_stage": true, "timestep_respacing": "40", "sr_timestep_respacing": "17" } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2022-02-23T06:35:47.124530Z", "created_at": "2022-02-23T06:34:55.571216Z", "data_removed": false, "error": null, "id": "x2pid4zdufhp5ahnyw7cuyc5bq", "input": { "prompt": "3d model of a pikachu", "side_x": 64, "side_y": 64, "batch_size": 3, "upsample_temp": "1.0", "guidance_scale": 16, "upsample_stage": true, "timestep_respacing": "40", "sr_timestep_respacing": "17" }, "logs": "Generating 64x64 samples with 40 timesteps using GLIDE-base-64px...\n\n 0%| | 0/38 [00:00<?, ?it/s]\n 3%|▎ | 1/38 [00:01<00:52, 1.42s/it]\n 5%|▌ | 2/38 [00:02<00:35, 1.01it/s]\n 8%|▊ | 3/38 [00:02<00:30, 1.17it/s]\n 11%|█ | 4/38 [00:02<00:20, 1.70it/s]\n 13%|█▎ | 5/38 [00:03<00:14, 2.28it/s]\n 16%|█▌ | 6/38 [00:03<00:11, 2.86it/s]\n 18%|█▊ | 7/38 [00:03<00:09, 3.42it/s]\n 21%|██ | 8/38 [00:03<00:07, 3.92it/s]\n 24%|██▎ | 9/38 [00:03<00:06, 4.34it/s]\n 26%|██▋ | 10/38 [00:04<00:05, 4.69it/s]\n 29%|██▉ | 11/38 [00:04<00:05, 4.96it/s]\n 32%|███▏ | 12/38 [00:04<00:05, 5.18it/s]\n 34%|███▍ | 13/38 [00:04<00:04, 5.34it/s]\n 37%|███▋ | 14/38 [00:04<00:04, 5.47it/s]\n 39%|███▉ | 15/38 [00:04<00:04, 5.53it/s]\n 42%|████▏ | 16/38 [00:05<00:03, 5.59it/s]\n 45%|████▍ | 17/38 [00:05<00:03, 5.62it/s]\n 47%|████▋ | 18/38 [00:05<00:03, 5.63it/s]\n 50%|█████ | 19/38 [00:05<00:03, 5.65it/s]\n 53%|█████▎ | 20/38 [00:05<00:03, 5.68it/s]\n 55%|█████▌ | 21/38 [00:05<00:02, 5.70it/s]\n 58%|█████▊ | 22/38 [00:06<00:02, 5.70it/s]\n 61%|██████ | 23/38 [00:06<00:02, 5.70it/s]\n 63%|██████▎ | 24/38 [00:06<00:02, 5.71it/s]\n 66%|██████▌ | 25/38 [00:06<00:02, 5.71it/s]\n 68%|██████▊ | 26/38 [00:06<00:02, 5.67it/s]\n 71%|███████ | 27/38 [00:07<00:01, 5.71it/s]\n 74%|███████▎ | 28/38 [00:07<00:01, 5.70it/s]\n 76%|███████▋ | 29/38 [00:07<00:01, 5.74it/s]\n 79%|███████▉ | 30/38 [00:07<00:01, 5.70it/s]\n 82%|████████▏ | 31/38 [00:07<00:01, 5.69it/s]\n 84%|████████▍ | 32/38 [00:07<00:01, 5.70it/s]\n 87%|████████▋ | 33/38 [00:08<00:00, 5.70it/s]\n 89%|████████▉ | 34/38 [00:08<00:00, 5.69it/s]\n 92%|█████████▏| 35/38 [00:08<00:00, 5.69it/s]\n 95%|█████████▍| 36/38 [00:08<00:00, 5.70it/s]\n 97%|█████████▋| 37/38 [00:08<00:00, 5.69it/s]\n100%|██████████| 38/38 [00:08<00:00, 5.68it/s]\n100%|██████████| 38/38 [00:08<00:00, 4.25it/s]\nUpsampling outputs from GLIDE-base 64x64 to 256x256 using 17 timesteps...\n\n 0%| | 0/15 [00:00<?, ?it/s]\n 7%|▋ | 1/15 [00:01<00:26, 1.89s/it]\n 13%|█▎ | 2/15 [00:03<00:24, 1.89s/it]\n 20%|██ | 3/15 [00:05<00:22, 1.89s/it]\n 27%|██▋ | 4/15 [00:06<00:14, 1.33s/it]\n 33%|███▎ | 5/15 [00:06<00:10, 1.02s/it]\n 40%|████ | 6/15 [00:07<00:07, 1.19it/s]\n 47%|████▋ | 7/15 [00:07<00:05, 1.39it/s]\n 53%|█████▎ | 8/15 [00:08<00:04, 1.56it/s]\n 60%|██████ | 9/15 [00:08<00:03, 1.69it/s]\n 67%|██████▋ | 10/15 [00:09<00:02, 1.80it/s]\n 73%|███████▎ | 11/15 [00:09<00:02, 1.88it/s]\n 80%|████████ | 12/15 [00:09<00:01, 1.94it/s]\n 87%|████████▋ | 13/15 [00:10<00:01, 1.99it/s]\n 93%|█████████▎| 14/15 [00:10<00:00, 2.01it/s]\n100%|██████████| 15/15 [00:11<00:00, 2.04it/s]\n100%|██████████| 15/15 [00:11<00:00, 1.32it/s]", "metrics": { "predict_time": 42.975133, "total_time": 51.553314 }, "output": [ { "file": "https://replicate.delivery/mgxm/bde54be2-bfa4-4513-b427-d7c9d3f130cb/upsample_predictions.png" } ], "started_at": "2022-02-23T06:35:04.149397Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/x2pid4zdufhp5ahnyw7cuyc5bq", "cancel": "https://api.replicate.com/v1/predictions/x2pid4zdufhp5ahnyw7cuyc5bq/cancel" }, "version": "45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae" }Generated inGenerating 64x64 samples with 40 timesteps using GLIDE-base-64px... 0%| | 0/38 [00:00<?, ?it/s] 3%|▎ | 1/38 [00:01<00:52, 1.42s/it] 5%|▌ | 2/38 [00:02<00:35, 1.01it/s] 8%|▊ | 3/38 [00:02<00:30, 1.17it/s] 11%|█ | 4/38 [00:02<00:20, 1.70it/s] 13%|█▎ | 5/38 [00:03<00:14, 2.28it/s] 16%|█▌ | 6/38 [00:03<00:11, 2.86it/s] 18%|█▊ | 7/38 [00:03<00:09, 3.42it/s] 21%|██ | 8/38 [00:03<00:07, 3.92it/s] 24%|██▎ | 9/38 [00:03<00:06, 4.34it/s] 26%|██▋ | 10/38 [00:04<00:05, 4.69it/s] 29%|██▉ | 11/38 [00:04<00:05, 4.96it/s] 32%|███▏ | 12/38 [00:04<00:05, 5.18it/s] 34%|███▍ | 13/38 [00:04<00:04, 5.34it/s] 37%|███▋ | 14/38 [00:04<00:04, 5.47it/s] 39%|███▉ | 15/38 [00:04<00:04, 5.53it/s] 42%|████▏ | 16/38 [00:05<00:03, 5.59it/s] 45%|████▍ | 17/38 [00:05<00:03, 5.62it/s] 47%|████▋ | 18/38 [00:05<00:03, 5.63it/s] 50%|█████ | 19/38 [00:05<00:03, 5.65it/s] 53%|█████▎ | 20/38 [00:05<00:03, 5.68it/s] 55%|█████▌ | 21/38 [00:05<00:02, 5.70it/s] 58%|█████▊ | 22/38 [00:06<00:02, 5.70it/s] 61%|██████ | 23/38 [00:06<00:02, 5.70it/s] 63%|██████▎ | 24/38 [00:06<00:02, 5.71it/s] 66%|██████▌ | 25/38 [00:06<00:02, 5.71it/s] 68%|██████▊ | 26/38 [00:06<00:02, 5.67it/s] 71%|███████ | 27/38 [00:07<00:01, 5.71it/s] 74%|███████▎ | 28/38 [00:07<00:01, 5.70it/s] 76%|███████▋ | 29/38 [00:07<00:01, 5.74it/s] 79%|███████▉ | 30/38 [00:07<00:01, 5.70it/s] 82%|████████▏ | 31/38 [00:07<00:01, 5.69it/s] 84%|████████▍ | 32/38 [00:07<00:01, 5.70it/s] 87%|████████▋ | 33/38 [00:08<00:00, 5.70it/s] 89%|████████▉ | 34/38 [00:08<00:00, 5.69it/s] 92%|█████████▏| 35/38 [00:08<00:00, 5.69it/s] 95%|█████████▍| 36/38 [00:08<00:00, 5.70it/s] 97%|█████████▋| 37/38 [00:08<00:00, 5.69it/s] 100%|██████████| 38/38 [00:08<00:00, 5.68it/s] 100%|██████████| 38/38 [00:08<00:00, 4.25it/s] Upsampling outputs from GLIDE-base 64x64 to 256x256 using 17 timesteps... 0%| | 0/15 [00:00<?, ?it/s] 7%|▋ | 1/15 [00:01<00:26, 1.89s/it] 13%|█▎ | 2/15 [00:03<00:24, 1.89s/it] 20%|██ | 3/15 [00:05<00:22, 1.89s/it] 27%|██▋ | 4/15 [00:06<00:14, 1.33s/it] 33%|███▎ | 5/15 [00:06<00:10, 1.02s/it] 40%|████ | 6/15 [00:07<00:07, 1.19it/s] 47%|████▋ | 7/15 [00:07<00:05, 1.39it/s] 53%|█████▎ | 8/15 [00:08<00:04, 1.56it/s] 60%|██████ | 9/15 [00:08<00:03, 1.69it/s] 67%|██████▋ | 10/15 [00:09<00:02, 1.80it/s] 73%|███████▎ | 11/15 [00:09<00:02, 1.88it/s] 80%|████████ | 12/15 [00:09<00:01, 1.94it/s] 87%|████████▋ | 13/15 [00:10<00:01, 1.99it/s] 93%|█████████▎| 14/15 [00:10<00:00, 2.01it/s] 100%|██████████| 15/15 [00:11<00:00, 2.04it/s] 100%|██████████| 15/15 [00:11<00:00, 1.32it/s]Prediction
laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48aeID4g2mvsoqknemlc3cf24fgx4cgiStatusSucceededSourceWebHardware–Total durationCreatedInput
- seed
- 23211
- prompt
- a windmill
- side_x
- "64"
- side_y
- "64"
- batch_size
- "3"
- upsample_temp
- "0.997"
- guidance_scale
- 16
- upsample_stage
- timestep_respacing
- 27
- sr_timestep_respacing
- 17
{ "seed": 23211, "prompt": "a windmill", "side_x": "64", "side_y": "64", "batch_size": "3", "upsample_temp": "0.997", "guidance_scale": 16, "upsample_stage": true, "timestep_respacing": "27", "sr_timestep_respacing": "17" }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run laion-ai/laionide-v2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae", { input: { seed: 23211, prompt: "a windmill", side_x: "64", side_y: "64", batch_size: "3", upsample_temp: "0.997", guidance_scale: 16, upsample_stage: true, timestep_respacing: "27", sr_timestep_respacing: "17" } } ); 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 replicateImport the client:import replicateRun laion-ai/laionide-v2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae", input={ "seed": 23211, "prompt": "a windmill", "side_x": "64", "side_y": "64", "batch_size": "3", "upsample_temp": "0.997", "guidance_scale": 16, "upsample_stage": True, "timestep_respacing": "27", "sr_timestep_respacing": "17" } ) # The laion-ai/laionide-v2 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/laionide-v2/api#output-schema print(item)To learn more, take a look at the guide on getting started with Python.
Run laion-ai/laionide-v2 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": "laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae", "input": { "seed": 23211, "prompt": "a windmill", "side_x": "64", "side_y": "64", "batch_size": "3", "upsample_temp": "0.997", "guidance_scale": 16, "upsample_stage": true, "timestep_respacing": "27", "sr_timestep_respacing": "17" } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2022-02-23T12:53:10.941272Z", "created_at": "2022-02-23T12:52:39.948987Z", "data_removed": false, "error": null, "id": "4g2mvsoqknemlc3cf24fgx4cgi", "input": { "seed": 23211, "prompt": "a windmill", "side_x": "64", "side_y": "64", "batch_size": "3", "upsample_temp": "0.997", "guidance_scale": 16, "upsample_stage": true, "timestep_respacing": "27", "sr_timestep_respacing": "17" }, "logs": "Generating 64x64 samples with 27 timesteps using GLIDE-base-64px...\n\n 0%| | 0/25 [00:00<?, ?it/s]\n 4%|▍ | 1/25 [00:00<00:18, 1.28it/s]\n 8%|▊ | 2/25 [00:01<00:17, 1.33it/s]\n 12%|█▏ | 3/25 [00:02<00:16, 1.35it/s]\n 16%|█▌ | 4/25 [00:02<00:10, 1.92it/s]\n 20%|██ | 5/25 [00:02<00:08, 2.50it/s]\n 24%|██▍ | 6/25 [00:02<00:06, 3.06it/s]\n 28%|██▊ | 7/25 [00:02<00:05, 3.58it/s]\n 32%|███▏ | 8/25 [00:03<00:04, 4.02it/s]\n 36%|███▌ | 9/25 [00:03<00:03, 4.39it/s]\n 40%|████ | 10/25 [00:03<00:03, 4.66it/s]\n 44%|████▍ | 11/25 [00:03<00:02, 4.87it/s]\n 48%|████▊ | 12/25 [00:03<00:02, 5.01it/s]\n 52%|█████▏ | 13/25 [00:04<00:02, 5.14it/s]\n 56%|█████▌ | 14/25 [00:04<00:02, 5.23it/s]\n 60%|██████ | 15/25 [00:04<00:01, 5.30it/s]\n 64%|██████▍ | 16/25 [00:04<00:01, 5.33it/s]\n 68%|██████▊ | 17/25 [00:04<00:01, 5.36it/s]\n 72%|███████▏ | 18/25 [00:05<00:01, 5.37it/s]\n 76%|███████▌ | 19/25 [00:05<00:01, 5.37it/s]\n 80%|████████ | 20/25 [00:05<00:00, 5.38it/s]\n 84%|████████▍ | 21/25 [00:05<00:00, 5.39it/s]\n 88%|████████▊ | 22/25 [00:05<00:00, 5.39it/s]\n 92%|█████████▏| 23/25 [00:05<00:00, 5.38it/s]\n 96%|█████████▌| 24/25 [00:06<00:00, 5.37it/s]\n100%|██████████| 25/25 [00:06<00:00, 5.33it/s]\n100%|██████████| 25/25 [00:06<00:00, 3.96it/s]\nUpsampling outputs from GLIDE-base 64x64 to 256x256 using 17 timesteps...\n\n 0%| | 0/15 [00:00<?, ?it/s]\n 7%|▋ | 1/15 [00:02<00:28, 2.02s/it]\n 13%|█▎ | 2/15 [00:04<00:26, 2.02s/it]\n 20%|██ | 3/15 [00:06<00:24, 2.03s/it]\n 27%|██▋ | 4/15 [00:06<00:15, 1.43s/it]\n 33%|███▎ | 5/15 [00:07<00:10, 1.10s/it]\n 40%|████ | 6/15 [00:07<00:08, 1.11it/s]\n 47%|████▋ | 7/15 [00:08<00:06, 1.30it/s]\n 53%|█████▎ | 8/15 [00:08<00:04, 1.45it/s]\n 60%|██████ | 9/15 [00:09<00:03, 1.57it/s]\n 67%|██████▋ | 10/15 [00:09<00:02, 1.67it/s]\n 73%|███████▎ | 11/15 [00:10<00:02, 1.74it/s]\n 80%|████████ | 12/15 [00:10<00:01, 1.79it/s]\n 87%|████████▋ | 13/15 [00:11<00:01, 1.83it/s]\n 93%|█████████▎| 14/15 [00:11<00:00, 1.86it/s]\n100%|██████████| 15/15 [00:12<00:00, 1.88it/s]\n100%|██████████| 15/15 [00:12<00:00, 1.22it/s]", "metrics": { "predict_time": 30.799669, "total_time": 30.992285 }, "output": [ { "file": "https://replicate.delivery/mgxm/c884f598-7e71-4937-b04b-b808f833596a/upsample_predictions.png" } ], "started_at": "2022-02-23T12:52:40.141603Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/4g2mvsoqknemlc3cf24fgx4cgi", "cancel": "https://api.replicate.com/v1/predictions/4g2mvsoqknemlc3cf24fgx4cgi/cancel" }, "version": "45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae" }Generated inGenerating 64x64 samples with 27 timesteps using GLIDE-base-64px... 0%| | 0/25 [00:00<?, ?it/s] 4%|▍ | 1/25 [00:00<00:18, 1.28it/s] 8%|▊ | 2/25 [00:01<00:17, 1.33it/s] 12%|█▏ | 3/25 [00:02<00:16, 1.35it/s] 16%|█▌ | 4/25 [00:02<00:10, 1.92it/s] 20%|██ | 5/25 [00:02<00:08, 2.50it/s] 24%|██▍ | 6/25 [00:02<00:06, 3.06it/s] 28%|██▊ | 7/25 [00:02<00:05, 3.58it/s] 32%|███▏ | 8/25 [00:03<00:04, 4.02it/s] 36%|███▌ | 9/25 [00:03<00:03, 4.39it/s] 40%|████ | 10/25 [00:03<00:03, 4.66it/s] 44%|████▍ | 11/25 [00:03<00:02, 4.87it/s] 48%|████▊ | 12/25 [00:03<00:02, 5.01it/s] 52%|█████▏ | 13/25 [00:04<00:02, 5.14it/s] 56%|█████▌ | 14/25 [00:04<00:02, 5.23it/s] 60%|██████ | 15/25 [00:04<00:01, 5.30it/s] 64%|██████▍ | 16/25 [00:04<00:01, 5.33it/s] 68%|██████▊ | 17/25 [00:04<00:01, 5.36it/s] 72%|███████▏ | 18/25 [00:05<00:01, 5.37it/s] 76%|███████▌ | 19/25 [00:05<00:01, 5.37it/s] 80%|████████ | 20/25 [00:05<00:00, 5.38it/s] 84%|████████▍ | 21/25 [00:05<00:00, 5.39it/s] 88%|████████▊ | 22/25 [00:05<00:00, 5.39it/s] 92%|█████████▏| 23/25 [00:05<00:00, 5.38it/s] 96%|█████████▌| 24/25 [00:06<00:00, 5.37it/s] 100%|██████████| 25/25 [00:06<00:00, 5.33it/s] 100%|██████████| 25/25 [00:06<00:00, 3.96it/s] Upsampling outputs from GLIDE-base 64x64 to 256x256 using 17 timesteps... 0%| | 0/15 [00:00<?, ?it/s] 7%|▋ | 1/15 [00:02<00:28, 2.02s/it] 13%|█▎ | 2/15 [00:04<00:26, 2.02s/it] 20%|██ | 3/15 [00:06<00:24, 2.03s/it] 27%|██▋ | 4/15 [00:06<00:15, 1.43s/it] 33%|███▎ | 5/15 [00:07<00:10, 1.10s/it] 40%|████ | 6/15 [00:07<00:08, 1.11it/s] 47%|████▋ | 7/15 [00:08<00:06, 1.30it/s] 53%|█████▎ | 8/15 [00:08<00:04, 1.45it/s] 60%|██████ | 9/15 [00:09<00:03, 1.57it/s] 67%|██████▋ | 10/15 [00:09<00:02, 1.67it/s] 73%|███████▎ | 11/15 [00:10<00:02, 1.74it/s] 80%|████████ | 12/15 [00:10<00:01, 1.79it/s] 87%|████████▋ | 13/15 [00:11<00:01, 1.83it/s] 93%|█████████▎| 14/15 [00:11<00:00, 1.86it/s] 100%|██████████| 15/15 [00:12<00:00, 1.88it/s] 100%|██████████| 15/15 [00:12<00:00, 1.22it/s]Prediction
laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48aeIDv5kytnvbmjc2zbgaygtec32bsyStatusSucceededSourceWebHardware–Total durationCreatedInput
- seed
- 23211
- prompt
- the city streets of new york are crowded at night
- side_x
- "64"
- side_y
- "64"
- batch_size
- "3"
- upsample_temp
- "0.997"
- guidance_scale
- 3
- upsample_stage
- timestep_respacing
- 27
- sr_timestep_respacing
- 17
{ "seed": 23211, "prompt": "the city streets of new york are crowded at night", "side_x": "64", "side_y": "64", "batch_size": "3", "upsample_temp": "0.997", "guidance_scale": 3, "upsample_stage": true, "timestep_respacing": "27", "sr_timestep_respacing": "17" }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run laion-ai/laionide-v2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae", { input: { seed: 23211, prompt: "the city streets of new york are crowded at night", side_x: "64", side_y: "64", batch_size: "3", upsample_temp: "0.997", guidance_scale: 3, upsample_stage: true, timestep_respacing: "27", sr_timestep_respacing: "17" } } ); 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 replicateImport the client:import replicateRun laion-ai/laionide-v2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae", input={ "seed": 23211, "prompt": "the city streets of new york are crowded at night", "side_x": "64", "side_y": "64", "batch_size": "3", "upsample_temp": "0.997", "guidance_scale": 3, "upsample_stage": True, "timestep_respacing": "27", "sr_timestep_respacing": "17" } ) # The laion-ai/laionide-v2 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/laionide-v2/api#output-schema print(item)To learn more, take a look at the guide on getting started with Python.
Run laion-ai/laionide-v2 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": "laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae", "input": { "seed": 23211, "prompt": "the city streets of new york are crowded at night", "side_x": "64", "side_y": "64", "batch_size": "3", "upsample_temp": "0.997", "guidance_scale": 3, "upsample_stage": true, "timestep_respacing": "27", "sr_timestep_respacing": "17" } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2022-02-23T12:55:36.780227Z", "created_at": "2022-02-23T12:55:01.349499Z", "data_removed": false, "error": null, "id": "v5kytnvbmjc2zbgaygtec32bsy", "input": { "seed": 23211, "prompt": "the city streets of new york are crowded at night", "side_x": "64", "side_y": "64", "batch_size": "3", "upsample_temp": "0.997", "guidance_scale": 3, "upsample_stage": true, "timestep_respacing": "27", "sr_timestep_respacing": "17" }, "logs": "Generating 64x64 samples with 27 timesteps using GLIDE-base-64px...\n\n 0%| | 0/25 [00:00<?, ?it/s]\n 4%|▍ | 1/25 [00:00<00:18, 1.27it/s]\n 8%|▊ | 2/25 [00:01<00:17, 1.31it/s]\n 12%|█▏ | 3/25 [00:02<00:16, 1.33it/s]\n 16%|█▌ | 4/25 [00:02<00:11, 1.89it/s]\n 20%|██ | 5/25 [00:02<00:08, 2.46it/s]\n 24%|██▍ | 6/25 [00:02<00:06, 3.01it/s]\n 28%|██▊ | 7/25 [00:03<00:05, 3.52it/s]\n 32%|███▏ | 8/25 [00:03<00:04, 3.95it/s]\n 36%|███▌ | 9/25 [00:03<00:03, 4.30it/s]\n 40%|████ | 10/25 [00:03<00:03, 4.58it/s]\n 44%|████▍ | 11/25 [00:03<00:02, 4.77it/s]\n 48%|████▊ | 12/25 [00:03<00:02, 4.92it/s]\n 52%|█████▏ | 13/25 [00:04<00:02, 5.04it/s]\n 56%|█████▌ | 14/25 [00:04<00:02, 5.12it/s]\n 60%|██████ | 15/25 [00:04<00:01, 5.19it/s]\n 64%|██████▍ | 16/25 [00:04<00:01, 5.23it/s]\n 68%|██████▊ | 17/25 [00:04<00:01, 5.25it/s]\n 72%|███████▏ | 18/25 [00:05<00:01, 5.28it/s]\n 76%|███████▌ | 19/25 [00:05<00:01, 5.29it/s]\n 80%|████████ | 20/25 [00:05<00:00, 5.30it/s]\n 84%|████████▍ | 21/25 [00:05<00:00, 5.31it/s]\n 88%|████████▊ | 22/25 [00:05<00:00, 5.30it/s]\n 92%|█████████▏| 23/25 [00:06<00:00, 5.30it/s]\n 96%|█████████▌| 24/25 [00:06<00:00, 5.31it/s]\n100%|██████████| 25/25 [00:06<00:00, 5.30it/s]\n100%|██████████| 25/25 [00:06<00:00, 3.90it/s]\nUpsampling outputs from GLIDE-base 64x64 to 256x256 using 17 timesteps...\n\n 0%| | 0/15 [00:00<?, ?it/s]\n 7%|▋ | 1/15 [00:02<00:28, 2.06s/it]\n 13%|█▎ | 2/15 [00:04<00:26, 2.05s/it]\n 20%|██ | 3/15 [00:06<00:24, 2.06s/it]\n 27%|██▋ | 4/15 [00:06<00:15, 1.45s/it]\n 33%|███▎ | 5/15 [00:07<00:11, 1.11s/it]\n 40%|████ | 6/15 [00:07<00:08, 1.10it/s]\n 47%|████▋ | 7/15 [00:08<00:06, 1.27it/s]\n 53%|█████▎ | 8/15 [00:08<00:04, 1.43it/s]\n 60%|██████ | 9/15 [00:09<00:03, 1.55it/s]\n 67%|██████▋ | 10/15 [00:09<00:03, 1.64it/s]\n 73%|███████▎ | 11/15 [00:10<00:02, 1.71it/s]\n 80%|████████ | 12/15 [00:10<00:01, 1.77it/s]\n 87%|████████▋ | 13/15 [00:11<00:01, 1.80it/s]\n 93%|█████████▎| 14/15 [00:11<00:00, 1.83it/s]\n100%|██████████| 15/15 [00:12<00:00, 1.85it/s]\n100%|██████████| 15/15 [00:12<00:00, 1.20it/s]", "metrics": { "predict_time": 35.273301, "total_time": 35.430728 }, "output": [ { "file": "https://replicate.delivery/mgxm/07e8bddd-eb15-4a16-a2b1-e7f67662587e/base_predictions.png" }, { "file": "https://replicate.delivery/mgxm/06edbaed-f751-43c9-b694-e69b95f95571/upsample_predictions.png" } ], "started_at": "2022-02-23T12:55:01.506926Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/v5kytnvbmjc2zbgaygtec32bsy", "cancel": "https://api.replicate.com/v1/predictions/v5kytnvbmjc2zbgaygtec32bsy/cancel" }, "version": "45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae" }Generated inGenerating 64x64 samples with 27 timesteps using GLIDE-base-64px... 0%| | 0/25 [00:00<?, ?it/s] 4%|▍ | 1/25 [00:00<00:18, 1.27it/s] 8%|▊ | 2/25 [00:01<00:17, 1.31it/s] 12%|█▏ | 3/25 [00:02<00:16, 1.33it/s] 16%|█▌ | 4/25 [00:02<00:11, 1.89it/s] 20%|██ | 5/25 [00:02<00:08, 2.46it/s] 24%|██▍ | 6/25 [00:02<00:06, 3.01it/s] 28%|██▊ | 7/25 [00:03<00:05, 3.52it/s] 32%|███▏ | 8/25 [00:03<00:04, 3.95it/s] 36%|███▌ | 9/25 [00:03<00:03, 4.30it/s] 40%|████ | 10/25 [00:03<00:03, 4.58it/s] 44%|████▍ | 11/25 [00:03<00:02, 4.77it/s] 48%|████▊ | 12/25 [00:03<00:02, 4.92it/s] 52%|█████▏ | 13/25 [00:04<00:02, 5.04it/s] 56%|█████▌ | 14/25 [00:04<00:02, 5.12it/s] 60%|██████ | 15/25 [00:04<00:01, 5.19it/s] 64%|██████▍ | 16/25 [00:04<00:01, 5.23it/s] 68%|██████▊ | 17/25 [00:04<00:01, 5.25it/s] 72%|███████▏ | 18/25 [00:05<00:01, 5.28it/s] 76%|███████▌ | 19/25 [00:05<00:01, 5.29it/s] 80%|████████ | 20/25 [00:05<00:00, 5.30it/s] 84%|████████▍ | 21/25 [00:05<00:00, 5.31it/s] 88%|████████▊ | 22/25 [00:05<00:00, 5.30it/s] 92%|█████████▏| 23/25 [00:06<00:00, 5.30it/s] 96%|█████████▌| 24/25 [00:06<00:00, 5.31it/s] 100%|██████████| 25/25 [00:06<00:00, 5.30it/s] 100%|██████████| 25/25 [00:06<00:00, 3.90it/s] Upsampling outputs from GLIDE-base 64x64 to 256x256 using 17 timesteps... 0%| | 0/15 [00:00<?, ?it/s] 7%|▋ | 1/15 [00:02<00:28, 2.06s/it] 13%|█▎ | 2/15 [00:04<00:26, 2.05s/it] 20%|██ | 3/15 [00:06<00:24, 2.06s/it] 27%|██▋ | 4/15 [00:06<00:15, 1.45s/it] 33%|███▎ | 5/15 [00:07<00:11, 1.11s/it] 40%|████ | 6/15 [00:07<00:08, 1.10it/s] 47%|████▋ | 7/15 [00:08<00:06, 1.27it/s] 53%|█████▎ | 8/15 [00:08<00:04, 1.43it/s] 60%|██████ | 9/15 [00:09<00:03, 1.55it/s] 67%|██████▋ | 10/15 [00:09<00:03, 1.64it/s] 73%|███████▎ | 11/15 [00:10<00:02, 1.71it/s] 80%|████████ | 12/15 [00:10<00:01, 1.77it/s] 87%|████████▋ | 13/15 [00:11<00:01, 1.80it/s] 93%|█████████▎| 14/15 [00:11<00:00, 1.83it/s] 100%|██████████| 15/15 [00:12<00:00, 1.85it/s] 100%|██████████| 15/15 [00:12<00:00, 1.20it/s]Prediction
laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48aeIDcj7rwkehqfbzdi6tys2f6nampyStatusSucceededSourceWebHardware–Total durationCreatedInput
- seed
- 23211
- prompt
- there is a green apple on the table
- side_x
- "64"
- side_y
- "64"
- batch_size
- "3"
- upsample_temp
- "0.997"
- guidance_scale
- 10
- upsample_stage
- timestep_respacing
- 27
- sr_timestep_respacing
- 17
{ "seed": 23211, "prompt": "there is a green apple on the table", "side_x": "64", "side_y": "64", "batch_size": "3", "upsample_temp": "0.997", "guidance_scale": 10, "upsample_stage": true, "timestep_respacing": "27", "sr_timestep_respacing": "17" }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run laion-ai/laionide-v2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae", { input: { seed: 23211, prompt: "there is a green apple on the table", side_x: "64", side_y: "64", batch_size: "3", upsample_temp: "0.997", guidance_scale: 10, upsample_stage: true, timestep_respacing: "27", sr_timestep_respacing: "17" } } ); 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 replicateImport the client:import replicateRun laion-ai/laionide-v2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae", input={ "seed": 23211, "prompt": "there is a green apple on the table", "side_x": "64", "side_y": "64", "batch_size": "3", "upsample_temp": "0.997", "guidance_scale": 10, "upsample_stage": True, "timestep_respacing": "27", "sr_timestep_respacing": "17" } ) # The laion-ai/laionide-v2 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/laionide-v2/api#output-schema print(item)To learn more, take a look at the guide on getting started with Python.
Run laion-ai/laionide-v2 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": "laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae", "input": { "seed": 23211, "prompt": "there is a green apple on the table", "side_x": "64", "side_y": "64", "batch_size": "3", "upsample_temp": "0.997", "guidance_scale": 10, "upsample_stage": true, "timestep_respacing": "27", "sr_timestep_respacing": "17" } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2022-02-23T12:58:40.065188Z", "created_at": "2022-02-23T12:57:50.379882Z", "data_removed": false, "error": null, "id": "cj7rwkehqfbzdi6tys2f6nampy", "input": { "seed": 23211, "prompt": "there is a green apple on the table", "side_x": "64", "side_y": "64", "batch_size": "3", "upsample_temp": "0.997", "guidance_scale": 10, "upsample_stage": true, "timestep_respacing": "27", "sr_timestep_respacing": "17" }, "logs": "Generating 64x64 samples with 27 timesteps using GLIDE-base-64px...\n\n 0%| | 0/25 [00:00<?, ?it/s]\n 4%|▍ | 1/25 [00:01<00:26, 1.12s/it]\n 8%|▊ | 2/25 [00:01<00:20, 1.13it/s]\n 12%|█▏ | 3/25 [00:02<00:17, 1.23it/s]\n 16%|█▌ | 4/25 [00:02<00:11, 1.78it/s]\n 20%|██ | 5/25 [00:02<00:08, 2.36it/s]\n 24%|██▍ | 6/25 [00:03<00:06, 2.93it/s]\n 28%|██▊ | 7/25 [00:03<00:05, 3.46it/s]\n 32%|███▏ | 8/25 [00:03<00:04, 3.95it/s]\n 36%|███▌ | 9/25 [00:03<00:03, 4.33it/s]\n 40%|████ | 10/25 [00:03<00:03, 4.62it/s]\n 44%|████▍ | 11/25 [00:04<00:02, 4.88it/s]\n 48%|████▊ | 12/25 [00:04<00:02, 5.06it/s]\n 52%|█████▏ | 13/25 [00:04<00:02, 5.19it/s]\n 56%|█████▌ | 14/25 [00:04<00:02, 5.29it/s]\n 60%|██████ | 15/25 [00:04<00:01, 5.36it/s]\n 64%|██████▍ | 16/25 [00:04<00:01, 5.39it/s]\n 68%|██████▊ | 17/25 [00:05<00:01, 5.42it/s]\n 72%|███████▏ | 18/25 [00:05<00:01, 5.46it/s]\n 76%|███████▌ | 19/25 [00:05<00:01, 5.49it/s]\n 80%|████████ | 20/25 [00:05<00:00, 5.50it/s]\n 84%|████████▍ | 21/25 [00:05<00:00, 5.50it/s]\n 88%|████████▊ | 22/25 [00:06<00:00, 5.48it/s]\n 92%|█████████▏| 23/25 [00:06<00:00, 5.47it/s]\n 96%|█████████▌| 24/25 [00:06<00:00, 5.46it/s]\n100%|██████████| 25/25 [00:06<00:00, 5.48it/s]\n100%|██████████| 25/25 [00:06<00:00, 3.81it/s]\nUpsampling outputs from GLIDE-base 64x64 to 256x256 using 17 timesteps...\n\n 0%| | 0/15 [00:00<?, ?it/s]\n 7%|▋ | 1/15 [00:01<00:27, 1.97s/it]\n 13%|█▎ | 2/15 [00:03<00:25, 1.97s/it]\n 20%|██ | 3/15 [00:05<00:23, 1.98s/it]\n 27%|██▋ | 4/15 [00:06<00:15, 1.39s/it]\n 33%|███▎ | 5/15 [00:06<00:10, 1.07s/it]\n 40%|████ | 6/15 [00:07<00:07, 1.14it/s]\n 47%|████▋ | 7/15 [00:07<00:06, 1.33it/s]\n 53%|█████▎ | 8/15 [00:08<00:04, 1.49it/s]\n 60%|██████ | 9/15 [00:08<00:03, 1.62it/s]\n 67%|██████▋ | 10/15 [00:09<00:02, 1.72it/s]\n 73%|███████▎ | 11/15 [00:09<00:02, 1.79it/s]\n 80%|████████ | 12/15 [00:10<00:01, 1.85it/s]\n 87%|████████▋ | 13/15 [00:10<00:01, 1.89it/s]\n 93%|█████████▎| 14/15 [00:11<00:00, 1.92it/s]\n100%|██████████| 15/15 [00:11<00:00, 1.93it/s]\n100%|██████████| 15/15 [00:11<00:00, 1.26it/s]", "metrics": { "predict_time": 33.980541, "total_time": 49.685306 }, "output": [ { "file": "https://replicate.delivery/mgxm/c572bbaa-ceb0-4c0f-b5c2-6b2270327083/base_predictions.png" }, { "file": "https://replicate.delivery/mgxm/c946018c-fc82-4ae6-8ec3-6dc7e5fad039/upsample_predictions.png" } ], "started_at": "2022-02-23T12:58:06.084647Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/cj7rwkehqfbzdi6tys2f6nampy", "cancel": "https://api.replicate.com/v1/predictions/cj7rwkehqfbzdi6tys2f6nampy/cancel" }, "version": "45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae" }Generated inGenerating 64x64 samples with 27 timesteps using GLIDE-base-64px... 0%| | 0/25 [00:00<?, ?it/s] 4%|▍ | 1/25 [00:01<00:26, 1.12s/it] 8%|▊ | 2/25 [00:01<00:20, 1.13it/s] 12%|█▏ | 3/25 [00:02<00:17, 1.23it/s] 16%|█▌ | 4/25 [00:02<00:11, 1.78it/s] 20%|██ | 5/25 [00:02<00:08, 2.36it/s] 24%|██▍ | 6/25 [00:03<00:06, 2.93it/s] 28%|██▊ | 7/25 [00:03<00:05, 3.46it/s] 32%|███▏ | 8/25 [00:03<00:04, 3.95it/s] 36%|███▌ | 9/25 [00:03<00:03, 4.33it/s] 40%|████ | 10/25 [00:03<00:03, 4.62it/s] 44%|████▍ | 11/25 [00:04<00:02, 4.88it/s] 48%|████▊ | 12/25 [00:04<00:02, 5.06it/s] 52%|█████▏ | 13/25 [00:04<00:02, 5.19it/s] 56%|█████▌ | 14/25 [00:04<00:02, 5.29it/s] 60%|██████ | 15/25 [00:04<00:01, 5.36it/s] 64%|██████▍ | 16/25 [00:04<00:01, 5.39it/s] 68%|██████▊ | 17/25 [00:05<00:01, 5.42it/s] 72%|███████▏ | 18/25 [00:05<00:01, 5.46it/s] 76%|███████▌ | 19/25 [00:05<00:01, 5.49it/s] 80%|████████ | 20/25 [00:05<00:00, 5.50it/s] 84%|████████▍ | 21/25 [00:05<00:00, 5.50it/s] 88%|████████▊ | 22/25 [00:06<00:00, 5.48it/s] 92%|█████████▏| 23/25 [00:06<00:00, 5.47it/s] 96%|█████████▌| 24/25 [00:06<00:00, 5.46it/s] 100%|██████████| 25/25 [00:06<00:00, 5.48it/s] 100%|██████████| 25/25 [00:06<00:00, 3.81it/s] Upsampling outputs from GLIDE-base 64x64 to 256x256 using 17 timesteps... 0%| | 0/15 [00:00<?, ?it/s] 7%|▋ | 1/15 [00:01<00:27, 1.97s/it] 13%|█▎ | 2/15 [00:03<00:25, 1.97s/it] 20%|██ | 3/15 [00:05<00:23, 1.98s/it] 27%|██▋ | 4/15 [00:06<00:15, 1.39s/it] 33%|███▎ | 5/15 [00:06<00:10, 1.07s/it] 40%|████ | 6/15 [00:07<00:07, 1.14it/s] 47%|████▋ | 7/15 [00:07<00:06, 1.33it/s] 53%|█████▎ | 8/15 [00:08<00:04, 1.49it/s] 60%|██████ | 9/15 [00:08<00:03, 1.62it/s] 67%|██████▋ | 10/15 [00:09<00:02, 1.72it/s] 73%|███████▎ | 11/15 [00:09<00:02, 1.79it/s] 80%|████████ | 12/15 [00:10<00:01, 1.85it/s] 87%|████████▋ | 13/15 [00:10<00:01, 1.89it/s] 93%|█████████▎| 14/15 [00:11<00:00, 1.92it/s] 100%|██████████| 15/15 [00:11<00:00, 1.93it/s] 100%|██████████| 15/15 [00:11<00:00, 1.26it/s]Prediction
laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48aeIDirqpgri4yzfrfe2jcsjh52frweStatusSucceededSourceWebHardware–Total durationCreatedInput
- seed
- 23211
- prompt
- an xbox 360 controller
- side_x
- "64"
- side_y
- "64"
- batch_size
- "3"
- upsample_temp
- "0.997"
- guidance_scale
- 8
- upsample_stage
- timestep_respacing
- 27
- sr_timestep_respacing
- 17
{ "seed": 23211, "prompt": "an xbox 360 controller", "side_x": "64", "side_y": "64", "batch_size": "3", "upsample_temp": "0.997", "guidance_scale": 8, "upsample_stage": true, "timestep_respacing": "27", "sr_timestep_respacing": "17" }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run laion-ai/laionide-v2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae", { input: { seed: 23211, prompt: "an xbox 360 controller", side_x: "64", side_y: "64", batch_size: "3", upsample_temp: "0.997", guidance_scale: 8, upsample_stage: true, timestep_respacing: "27", sr_timestep_respacing: "17" } } ); 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 replicateImport the client:import replicateRun laion-ai/laionide-v2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae", input={ "seed": 23211, "prompt": "an xbox 360 controller", "side_x": "64", "side_y": "64", "batch_size": "3", "upsample_temp": "0.997", "guidance_scale": 8, "upsample_stage": True, "timestep_respacing": "27", "sr_timestep_respacing": "17" } ) # The laion-ai/laionide-v2 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/laionide-v2/api#output-schema print(item)To learn more, take a look at the guide on getting started with Python.
Run laion-ai/laionide-v2 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": "laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae", "input": { "seed": 23211, "prompt": "an xbox 360 controller", "side_x": "64", "side_y": "64", "batch_size": "3", "upsample_temp": "0.997", "guidance_scale": 8, "upsample_stage": true, "timestep_respacing": "27", "sr_timestep_respacing": "17" } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2022-02-23T13:02:40.680266Z", "created_at": "2022-02-23T13:02:06.312775Z", "data_removed": false, "error": null, "id": "irqpgri4yzfrfe2jcsjh52frwe", "input": { "seed": 23211, "prompt": "an xbox 360 controller", "side_x": "64", "side_y": "64", "batch_size": "3", "upsample_temp": "0.997", "guidance_scale": 8, "upsample_stage": true, "timestep_respacing": "27", "sr_timestep_respacing": "17" }, "logs": "Generating 64x64 samples with 27 timesteps using GLIDE-base-64px...\n\n 0%| | 0/25 [00:00<?, ?it/s]\n 4%|▍ | 1/25 [00:00<00:19, 1.24it/s]\n 8%|▊ | 2/25 [00:01<00:17, 1.31it/s]\n 12%|█▏ | 3/25 [00:02<00:16, 1.34it/s]\n 16%|█▌ | 4/25 [00:02<00:11, 1.90it/s]\n 20%|██ | 5/25 [00:02<00:08, 2.49it/s]\n 24%|██▍ | 6/25 [00:02<00:06, 3.05it/s]\n 28%|██▊ | 7/25 [00:03<00:05, 3.56it/s]\n 32%|███▏ | 8/25 [00:03<00:04, 4.00it/s]\n 36%|███▌ | 9/25 [00:03<00:03, 4.36it/s]\n 40%|████ | 10/25 [00:03<00:03, 4.64it/s]\n 44%|████▍ | 11/25 [00:03<00:02, 4.86it/s]\n 48%|████▊ | 12/25 [00:03<00:02, 5.02it/s]\n 52%|█████▏ | 13/25 [00:04<00:02, 5.15it/s]\n 56%|█████▌ | 14/25 [00:04<00:02, 5.24it/s]\n 60%|██████ | 15/25 [00:04<00:01, 5.29it/s]\n 64%|██████▍ | 16/25 [00:04<00:01, 5.32it/s]\n 68%|██████▊ | 17/25 [00:04<00:01, 5.35it/s]\n 72%|███████▏ | 18/25 [00:05<00:01, 5.37it/s]\n 76%|███████▌ | 19/25 [00:05<00:01, 5.37it/s]\n 80%|████████ | 20/25 [00:05<00:00, 5.38it/s]\n 84%|████████▍ | 21/25 [00:05<00:00, 5.40it/s]\n 88%|████████▊ | 22/25 [00:05<00:00, 5.41it/s]\n 92%|█████████▏| 23/25 [00:05<00:00, 5.42it/s]\n 96%|█████████▌| 24/25 [00:06<00:00, 5.43it/s]\n100%|██████████| 25/25 [00:06<00:00, 5.42it/s]\n100%|██████████| 25/25 [00:06<00:00, 3.96it/s]\nUpsampling outputs from GLIDE-base 64x64 to 256x256 using 17 timesteps...\n\n 0%| | 0/15 [00:00<?, ?it/s]\n 7%|▋ | 1/15 [00:02<00:28, 2.00s/it]\n 13%|█▎ | 2/15 [00:03<00:25, 2.00s/it]\n 20%|██ | 3/15 [00:06<00:24, 2.00s/it]\n 27%|██▋ | 4/15 [00:06<00:15, 1.41s/it]\n 33%|███▎ | 5/15 [00:07<00:10, 1.08s/it]\n 40%|████ | 6/15 [00:07<00:07, 1.13it/s]\n 47%|████▋ | 7/15 [00:08<00:06, 1.31it/s]\n 53%|█████▎ | 8/15 [00:08<00:04, 1.47it/s]\n 60%|██████ | 9/15 [00:09<00:03, 1.60it/s]\n 67%|██████▋ | 10/15 [00:09<00:02, 1.70it/s]\n 73%|███████▎ | 11/15 [00:10<00:02, 1.77it/s]\n 80%|████████ | 12/15 [00:10<00:01, 1.83it/s]\n 87%|████████▋ | 13/15 [00:11<00:01, 1.87it/s]\n 93%|█████████▎| 14/15 [00:11<00:00, 1.90it/s]\n100%|██████████| 15/15 [00:12<00:00, 1.92it/s]\n100%|██████████| 15/15 [00:12<00:00, 1.24it/s]", "metrics": { "predict_time": 34.146994, "total_time": 34.367491 }, "output": [ { "file": "https://replicate.delivery/mgxm/3698f40b-d7f2-4ea8-b269-7d0eb1f53b80/base_predictions.png" }, { "file": "https://replicate.delivery/mgxm/6dad1002-5f8b-4f70-8bf2-1ff2330c661d/upsample_predictions.png" } ], "started_at": "2022-02-23T13:02:06.533272Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/irqpgri4yzfrfe2jcsjh52frwe", "cancel": "https://api.replicate.com/v1/predictions/irqpgri4yzfrfe2jcsjh52frwe/cancel" }, "version": "45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae" }Generated inGenerating 64x64 samples with 27 timesteps using GLIDE-base-64px... 0%| | 0/25 [00:00<?, ?it/s] 4%|▍ | 1/25 [00:00<00:19, 1.24it/s] 8%|▊ | 2/25 [00:01<00:17, 1.31it/s] 12%|█▏ | 3/25 [00:02<00:16, 1.34it/s] 16%|█▌ | 4/25 [00:02<00:11, 1.90it/s] 20%|██ | 5/25 [00:02<00:08, 2.49it/s] 24%|██▍ | 6/25 [00:02<00:06, 3.05it/s] 28%|██▊ | 7/25 [00:03<00:05, 3.56it/s] 32%|███▏ | 8/25 [00:03<00:04, 4.00it/s] 36%|███▌ | 9/25 [00:03<00:03, 4.36it/s] 40%|████ | 10/25 [00:03<00:03, 4.64it/s] 44%|████▍ | 11/25 [00:03<00:02, 4.86it/s] 48%|████▊ | 12/25 [00:03<00:02, 5.02it/s] 52%|█████▏ | 13/25 [00:04<00:02, 5.15it/s] 56%|█████▌ | 14/25 [00:04<00:02, 5.24it/s] 60%|██████ | 15/25 [00:04<00:01, 5.29it/s] 64%|██████▍ | 16/25 [00:04<00:01, 5.32it/s] 68%|██████▊ | 17/25 [00:04<00:01, 5.35it/s] 72%|███████▏ | 18/25 [00:05<00:01, 5.37it/s] 76%|███████▌ | 19/25 [00:05<00:01, 5.37it/s] 80%|████████ | 20/25 [00:05<00:00, 5.38it/s] 84%|████████▍ | 21/25 [00:05<00:00, 5.40it/s] 88%|████████▊ | 22/25 [00:05<00:00, 5.41it/s] 92%|█████████▏| 23/25 [00:05<00:00, 5.42it/s] 96%|█████████▌| 24/25 [00:06<00:00, 5.43it/s] 100%|██████████| 25/25 [00:06<00:00, 5.42it/s] 100%|██████████| 25/25 [00:06<00:00, 3.96it/s] Upsampling outputs from GLIDE-base 64x64 to 256x256 using 17 timesteps... 0%| | 0/15 [00:00<?, ?it/s] 7%|▋ | 1/15 [00:02<00:28, 2.00s/it] 13%|█▎ | 2/15 [00:03<00:25, 2.00s/it] 20%|██ | 3/15 [00:06<00:24, 2.00s/it] 27%|██▋ | 4/15 [00:06<00:15, 1.41s/it] 33%|███▎ | 5/15 [00:07<00:10, 1.08s/it] 40%|████ | 6/15 [00:07<00:07, 1.13it/s] 47%|████▋ | 7/15 [00:08<00:06, 1.31it/s] 53%|█████▎ | 8/15 [00:08<00:04, 1.47it/s] 60%|██████ | 9/15 [00:09<00:03, 1.60it/s] 67%|██████▋ | 10/15 [00:09<00:02, 1.70it/s] 73%|███████▎ | 11/15 [00:10<00:02, 1.77it/s] 80%|████████ | 12/15 [00:10<00:01, 1.83it/s] 87%|████████▋ | 13/15 [00:11<00:01, 1.87it/s] 93%|█████████▎| 14/15 [00:11<00:00, 1.90it/s] 100%|██████████| 15/15 [00:12<00:00, 1.92it/s] 100%|██████████| 15/15 [00:12<00:00, 1.24it/s]Prediction
laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48aeInput
- seed
- 23211
- prompt
- a professional high quality illustration of a turtle owl chimera. a turtle imitating an owl. a turtle made of owl.
- side_x
- "64"
- side_y
- "64"
- batch_size
- "3"
- upsample_temp
- "0.997"
- guidance_scale
- 16
- upsample_stage
- timestep_respacing
- 27
- sr_timestep_respacing
- 17
{ "seed": 23211, "prompt": "a professional high quality illustration of a turtle owl chimera. a turtle imitating an owl. a turtle made of owl.", "side_x": "64", "side_y": "64", "batch_size": "3", "upsample_temp": "0.997", "guidance_scale": 16, "upsample_stage": true, "timestep_respacing": "27", "sr_timestep_respacing": "17" }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run laion-ai/laionide-v2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae", { input: { seed: 23211, prompt: "a professional high quality illustration of a turtle owl chimera. a turtle imitating an owl. a turtle made of owl.", side_x: "64", side_y: "64", batch_size: "3", upsample_temp: "0.997", guidance_scale: 16, upsample_stage: true, timestep_respacing: "27", sr_timestep_respacing: "17" } } ); 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 replicateImport the client:import replicateRun laion-ai/laionide-v2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae", input={ "seed": 23211, "prompt": "a professional high quality illustration of a turtle owl chimera. a turtle imitating an owl. a turtle made of owl.", "side_x": "64", "side_y": "64", "batch_size": "3", "upsample_temp": "0.997", "guidance_scale": 16, "upsample_stage": True, "timestep_respacing": "27", "sr_timestep_respacing": "17" } ) # The laion-ai/laionide-v2 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/laionide-v2/api#output-schema print(item)To learn more, take a look at the guide on getting started with Python.
Run laion-ai/laionide-v2 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": "laion-ai/laionide-v2:45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae", "input": { "seed": 23211, "prompt": "a professional high quality illustration of a turtle owl chimera. a turtle imitating an owl. a turtle made of owl.", "side_x": "64", "side_y": "64", "batch_size": "3", "upsample_temp": "0.997", "guidance_scale": 16, "upsample_stage": true, "timestep_respacing": "27", "sr_timestep_respacing": "17" } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2022-02-24T08:17:58.234219Z", "created_at": "2022-02-24T08:16:05.824831Z", "data_removed": false, "error": null, "id": "td7djfzk6zgjdh3jaclnvhdwxq", "input": { "seed": 23211, "prompt": "a professional high quality illustration of a turtle owl chimera. a turtle imitating an owl. a turtle made of owl.", "side_x": "64", "side_y": "64", "batch_size": "3", "upsample_temp": "0.997", "guidance_scale": 16, "upsample_stage": true, "timestep_respacing": "27", "sr_timestep_respacing": "17" }, "logs": "Generating 64x64 samples with 27 timesteps using GLIDE-base-64px...\n\n 0%| | 0/25 [00:00<?, ?it/s]\n 4%|▍ | 1/25 [00:01<00:25, 1.07s/it]\n 8%|▊ | 2/25 [00:01<00:19, 1.19it/s]\n 12%|█▏ | 3/25 [00:02<00:16, 1.31it/s]\n 16%|█▌ | 4/25 [00:02<00:11, 1.88it/s]\n 20%|██ | 5/25 [00:02<00:08, 2.49it/s]\n 24%|██▍ | 6/25 [00:02<00:06, 3.09it/s]\n 28%|██▊ | 7/25 [00:03<00:04, 3.65it/s]\n 32%|███▏ | 8/25 [00:03<00:04, 4.13it/s]\n 36%|███▌ | 9/25 [00:03<00:03, 4.53it/s]\n 40%|████ | 10/25 [00:03<00:03, 4.85it/s]\n 44%|████▍ | 11/25 [00:03<00:02, 5.12it/s]\n 48%|████▊ | 12/25 [00:03<00:02, 5.29it/s]\n 52%|█████▏ | 13/25 [00:04<00:02, 5.43it/s]\n 56%|█████▌ | 14/25 [00:04<00:01, 5.55it/s]\n 60%|██████ | 15/25 [00:04<00:01, 5.64it/s]\n 64%|██████▍ | 16/25 [00:04<00:01, 5.70it/s]\n 68%|██████▊ | 17/25 [00:04<00:01, 5.74it/s]\n 72%|███████▏ | 18/25 [00:05<00:01, 5.78it/s]\n 76%|███████▌ | 19/25 [00:05<00:01, 5.79it/s]\n 80%|████████ | 20/25 [00:05<00:00, 5.83it/s]\n 84%|████████▍ | 21/25 [00:05<00:00, 5.84it/s]\n 88%|████████▊ | 22/25 [00:05<00:00, 5.80it/s]\n 92%|█████████▏| 23/25 [00:05<00:00, 5.80it/s]\n 96%|█████████▌| 24/25 [00:06<00:00, 5.79it/s]\n100%|██████████| 25/25 [00:06<00:00, 5.79it/s]\n100%|██████████| 25/25 [00:06<00:00, 4.02it/s]\nUpsampling outputs from GLIDE-base 64x64 to 256x256 using 17 timesteps...\n\n 0%| | 0/15 [00:00<?, ?it/s]\n 7%|▋ | 1/15 [00:01<00:25, 1.85s/it]\n 13%|█▎ | 2/15 [00:03<00:24, 1.85s/it]\n 20%|██ | 3/15 [00:05<00:22, 1.84s/it]\n 27%|██▋ | 4/15 [00:05<00:14, 1.30s/it]\n 33%|███▎ | 5/15 [00:06<00:09, 1.00it/s]\n 40%|████ | 6/15 [00:06<00:07, 1.22it/s]\n 47%|████▋ | 7/15 [00:07<00:05, 1.43it/s]\n 53%|█████▎ | 8/15 [00:07<00:04, 1.60it/s]\n 60%|██████ | 9/15 [00:08<00:03, 1.74it/s]\n 67%|██████▋ | 10/15 [00:08<00:02, 1.85it/s]\n 73%|███████▎ | 11/15 [00:09<00:02, 1.93it/s]\n 80%|████████ | 12/15 [00:09<00:01, 1.99it/s]\n 87%|████████▋ | 13/15 [00:10<00:00, 2.04it/s]\n 93%|█████████▎| 14/15 [00:10<00:00, 2.07it/s]\n100%|██████████| 15/15 [00:11<00:00, 2.10it/s]\n100%|██████████| 15/15 [00:11<00:00, 1.35it/s]", "metrics": { "predict_time": 32.309985, "total_time": 112.409388 }, "output": [ { "file": "https://replicate.delivery/mgxm/ab49a244-1a31-43a7-9322-5b0c62f118cb/upsample_predictions.png" } ], "started_at": "2022-02-24T08:17:25.924234Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/td7djfzk6zgjdh3jaclnvhdwxq", "cancel": "https://api.replicate.com/v1/predictions/td7djfzk6zgjdh3jaclnvhdwxq/cancel" }, "version": "45c75f75ff746493080d172c7e154ee3d921b7726b5e4b380066822965bd48ae" }Generated inGenerating 64x64 samples with 27 timesteps using GLIDE-base-64px... 0%| | 0/25 [00:00<?, ?it/s] 4%|▍ | 1/25 [00:01<00:25, 1.07s/it] 8%|▊ | 2/25 [00:01<00:19, 1.19it/s] 12%|█▏ | 3/25 [00:02<00:16, 1.31it/s] 16%|█▌ | 4/25 [00:02<00:11, 1.88it/s] 20%|██ | 5/25 [00:02<00:08, 2.49it/s] 24%|██▍ | 6/25 [00:02<00:06, 3.09it/s] 28%|██▊ | 7/25 [00:03<00:04, 3.65it/s] 32%|███▏ | 8/25 [00:03<00:04, 4.13it/s] 36%|███▌ | 9/25 [00:03<00:03, 4.53it/s] 40%|████ | 10/25 [00:03<00:03, 4.85it/s] 44%|████▍ | 11/25 [00:03<00:02, 5.12it/s] 48%|████▊ | 12/25 [00:03<00:02, 5.29it/s] 52%|█████▏ | 13/25 [00:04<00:02, 5.43it/s] 56%|█████▌ | 14/25 [00:04<00:01, 5.55it/s] 60%|██████ | 15/25 [00:04<00:01, 5.64it/s] 64%|██████▍ | 16/25 [00:04<00:01, 5.70it/s] 68%|██████▊ | 17/25 [00:04<00:01, 5.74it/s] 72%|███████▏ | 18/25 [00:05<00:01, 5.78it/s] 76%|███████▌ | 19/25 [00:05<00:01, 5.79it/s] 80%|████████ | 20/25 [00:05<00:00, 5.83it/s] 84%|████████▍ | 21/25 [00:05<00:00, 5.84it/s] 88%|████████▊ | 22/25 [00:05<00:00, 5.80it/s] 92%|█████████▏| 23/25 [00:05<00:00, 5.80it/s] 96%|█████████▌| 24/25 [00:06<00:00, 5.79it/s] 100%|██████████| 25/25 [00:06<00:00, 5.79it/s] 100%|██████████| 25/25 [00:06<00:00, 4.02it/s] Upsampling outputs from GLIDE-base 64x64 to 256x256 using 17 timesteps... 0%| | 0/15 [00:00<?, ?it/s] 7%|▋ | 1/15 [00:01<00:25, 1.85s/it] 13%|█▎ | 2/15 [00:03<00:24, 1.85s/it] 20%|██ | 3/15 [00:05<00:22, 1.84s/it] 27%|██▋ | 4/15 [00:05<00:14, 1.30s/it] 33%|███▎ | 5/15 [00:06<00:09, 1.00it/s] 40%|████ | 6/15 [00:06<00:07, 1.22it/s] 47%|████▋ | 7/15 [00:07<00:05, 1.43it/s] 53%|█████▎ | 8/15 [00:07<00:04, 1.60it/s] 60%|██████ | 9/15 [00:08<00:03, 1.74it/s] 67%|██████▋ | 10/15 [00:08<00:02, 1.85it/s] 73%|███████▎ | 11/15 [00:09<00:02, 1.93it/s] 80%|████████ | 12/15 [00:09<00:01, 1.99it/s] 87%|████████▋ | 13/15 [00:10<00:00, 2.04it/s] 93%|█████████▎| 14/15 [00:10<00:00, 2.07it/s] 100%|██████████| 15/15 [00:11<00:00, 2.10it/s] 100%|██████████| 15/15 [00:11<00:00, 1.35it/s]
Want to make some of these yourself?
Run this model
