ai-forever / kandinsky-2
text2img model trained on LAION HighRes and fine-tuned on internal datasets
Prediction
ai-forever/kandinsky-2:65a15f6e3c538ee4adf5142411455308926714f7d3f5c940d9f7bc519e0e5c1aInput
- prompt
- a beautiful landscape photo, epic, dawn light, 8k, mountains, river, dramatic, award winning
- scheduler
- p_sampler
- prior_steps
- 5
- guidance_scale
- 4
- prior_cf_scale
- 4
- num_inference_steps
- 100
{ "prompt": "a beautiful landscape photo, epic, dawn light, 8k, mountains, river, dramatic, award winning", "scheduler": "p_sampler", "prior_steps": "5", "guidance_scale": 4, "prior_cf_scale": 4, "num_inference_steps": 100 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run ai-forever/kandinsky-2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "ai-forever/kandinsky-2:65a15f6e3c538ee4adf5142411455308926714f7d3f5c940d9f7bc519e0e5c1a", { input: { prompt: "a beautiful landscape photo, epic, dawn light, 8k, mountains, river, dramatic, award winning", scheduler: "p_sampler", prior_steps: "5", guidance_scale: 4, prior_cf_scale: 4, num_inference_steps: 100 } } ); // To access the file URL: console.log(output.url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Import the client:import replicate
Run ai-forever/kandinsky-2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "ai-forever/kandinsky-2:65a15f6e3c538ee4adf5142411455308926714f7d3f5c940d9f7bc519e0e5c1a", input={ "prompt": "a beautiful landscape photo, epic, dawn light, 8k, mountains, river, dramatic, award winning", "scheduler": "p_sampler", "prior_steps": "5", "guidance_scale": 4, "prior_cf_scale": 4, "num_inference_steps": 100 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run ai-forever/kandinsky-2 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": "ai-forever/kandinsky-2:65a15f6e3c538ee4adf5142411455308926714f7d3f5c940d9f7bc519e0e5c1a", "input": { "prompt": "a beautiful landscape photo, epic, dawn light, 8k, mountains, river, dramatic, award winning", "scheduler": "p_sampler", "prior_steps": "5", "guidance_scale": 4, "prior_cf_scale": 4, "num_inference_steps": 100 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-04-11T20:03:23.641162Z", "created_at": "2023-04-11T20:03:06.746357Z", "data_removed": false, "error": null, "id": "xi43ss7qpnf6beckaoulfk7xca", "input": { "prompt": "a beautiful landscape photo, epic, dawn light, 8k, mountains, river, dramatic, award winning", "scheduler": "p_sampler", "prior_steps": "5", "guidance_scale": 4, "prior_cf_scale": 4, "num_inference_steps": 100 }, "logs": "0%| | 0/100 [00:00<?, ?it/s]\n 2%|▏ | 2/100 [00:00<00:08, 11.31it/s]\n 4%|▍ | 4/100 [00:00<00:08, 11.29it/s]\n 6%|▌ | 6/100 [00:00<00:08, 11.41it/s]\n 8%|▊ | 8/100 [00:00<00:08, 11.43it/s]\n 10%|█ | 10/100 [00:00<00:07, 11.46it/s]\n 12%|█▏ | 12/100 [00:01<00:07, 11.47it/s]\n 14%|█▍ | 14/100 [00:01<00:07, 11.36it/s]\n 16%|█▌ | 16/100 [00:01<00:07, 11.29it/s]\n 18%|█▊ | 18/100 [00:01<00:07, 11.33it/s]\n 20%|██ | 20/100 [00:01<00:07, 11.36it/s]\n 22%|██▏ | 22/100 [00:01<00:06, 11.37it/s]\n 24%|██▍ | 24/100 [00:02<00:06, 11.40it/s]\n 26%|██▌ | 26/100 [00:02<00:06, 11.35it/s]\n 28%|██▊ | 28/100 [00:02<00:06, 11.37it/s]\n 30%|███ | 30/100 [00:02<00:06, 11.45it/s]\n 32%|███▏ | 32/100 [00:02<00:05, 11.50it/s]\n 34%|███▍ | 34/100 [00:02<00:05, 11.55it/s]\n 36%|███▌ | 36/100 [00:03<00:05, 11.57it/s]\n 38%|███▊ | 38/100 [00:03<00:05, 11.53it/s]\n 40%|████ | 40/100 [00:03<00:05, 11.51it/s]\n 42%|████▏ | 42/100 [00:03<00:05, 11.49it/s]\n 44%|████▍ | 44/100 [00:03<00:04, 11.47it/s]\n 46%|████▌ | 46/100 [00:04<00:04, 11.48it/s]\n 48%|████▊ | 48/100 [00:04<00:04, 11.47it/s]\n 50%|█████ | 50/100 [00:04<00:04, 11.43it/s]\n 52%|█████▏ | 52/100 [00:04<00:04, 11.44it/s]\n 54%|█████▍ | 54/100 [00:04<00:04, 11.41it/s]\n 56%|█████▌ | 56/100 [00:04<00:03, 11.42it/s]\n 58%|█████▊ | 58/100 [00:05<00:03, 11.46it/s]\n 60%|██████ | 60/100 [00:05<00:03, 11.44it/s]\n 62%|██████▏ | 62/100 [00:05<00:03, 11.37it/s]\n 64%|██████▍ | 64/100 [00:05<00:03, 11.29it/s]\n 66%|██████▌ | 66/100 [00:05<00:03, 11.30it/s]\n 68%|██████▊ | 68/100 [00:05<00:02, 11.32it/s]\n 70%|███████ | 70/100 [00:06<00:02, 11.35it/s]\n 72%|███████▏ | 72/100 [00:06<00:02, 11.34it/s]\n 74%|███████▍ | 74/100 [00:06<00:02, 11.35it/s]\n 76%|███████▌ | 76/100 [00:06<00:02, 11.33it/s]\n 78%|███████▊ | 78/100 [00:06<00:01, 11.36it/s]\n 80%|████████ | 80/100 [00:07<00:01, 11.39it/s]\n 82%|████████▏ | 82/100 [00:07<00:01, 11.40it/s]\n 84%|████████▍ | 84/100 [00:07<00:01, 11.26it/s]\n 86%|████████▌ | 86/100 [00:07<00:01, 11.29it/s]\n 88%|████████▊ | 88/100 [00:07<00:01, 11.34it/s]\n 90%|█████████ | 90/100 [00:07<00:00, 11.39it/s]\n 92%|█████████▏| 92/100 [00:08<00:00, 11.40it/s]\n 94%|█████████▍| 94/100 [00:08<00:00, 11.21it/s]\n 96%|█████████▌| 96/100 [00:08<00:00, 11.28it/s]\n 98%|█████████▊| 98/100 [00:08<00:00, 11.32it/s]\n100%|██████████| 100/100 [00:08<00:00, 11.36it/s]\n100%|██████████| 100/100 [00:08<00:00, 11.39it/s]", "metrics": { "predict_time": 10.060902, "total_time": 16.894805 }, "output": "https://replicate.delivery/pbxt/iQKHCerzd4wEPyRNbJYhTqeKNhRxwqiaYgyLAN09mEaK82wQA/out.png", "started_at": "2023-04-11T20:03:13.580260Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/xi43ss7qpnf6beckaoulfk7xca", "cancel": "https://api.replicate.com/v1/predictions/xi43ss7qpnf6beckaoulfk7xca/cancel" }, "version": "65a15f6e3c538ee4adf5142411455308926714f7d3f5c940d9f7bc519e0e5c1a" }
Generated in0%| | 0/100 [00:00<?, ?it/s] 2%|▏ | 2/100 [00:00<00:08, 11.31it/s] 4%|▍ | 4/100 [00:00<00:08, 11.29it/s] 6%|▌ | 6/100 [00:00<00:08, 11.41it/s] 8%|▊ | 8/100 [00:00<00:08, 11.43it/s] 10%|█ | 10/100 [00:00<00:07, 11.46it/s] 12%|█▏ | 12/100 [00:01<00:07, 11.47it/s] 14%|█▍ | 14/100 [00:01<00:07, 11.36it/s] 16%|█▌ | 16/100 [00:01<00:07, 11.29it/s] 18%|█▊ | 18/100 [00:01<00:07, 11.33it/s] 20%|██ | 20/100 [00:01<00:07, 11.36it/s] 22%|██▏ | 22/100 [00:01<00:06, 11.37it/s] 24%|██▍ | 24/100 [00:02<00:06, 11.40it/s] 26%|██▌ | 26/100 [00:02<00:06, 11.35it/s] 28%|██▊ | 28/100 [00:02<00:06, 11.37it/s] 30%|███ | 30/100 [00:02<00:06, 11.45it/s] 32%|███▏ | 32/100 [00:02<00:05, 11.50it/s] 34%|███▍ | 34/100 [00:02<00:05, 11.55it/s] 36%|███▌ | 36/100 [00:03<00:05, 11.57it/s] 38%|███▊ | 38/100 [00:03<00:05, 11.53it/s] 40%|████ | 40/100 [00:03<00:05, 11.51it/s] 42%|████▏ | 42/100 [00:03<00:05, 11.49it/s] 44%|████▍ | 44/100 [00:03<00:04, 11.47it/s] 46%|████▌ | 46/100 [00:04<00:04, 11.48it/s] 48%|████▊ | 48/100 [00:04<00:04, 11.47it/s] 50%|█████ | 50/100 [00:04<00:04, 11.43it/s] 52%|█████▏ | 52/100 [00:04<00:04, 11.44it/s] 54%|█████▍ | 54/100 [00:04<00:04, 11.41it/s] 56%|█████▌ | 56/100 [00:04<00:03, 11.42it/s] 58%|█████▊ | 58/100 [00:05<00:03, 11.46it/s] 60%|██████ | 60/100 [00:05<00:03, 11.44it/s] 62%|██████▏ | 62/100 [00:05<00:03, 11.37it/s] 64%|██████▍ | 64/100 [00:05<00:03, 11.29it/s] 66%|██████▌ | 66/100 [00:05<00:03, 11.30it/s] 68%|██████▊ | 68/100 [00:05<00:02, 11.32it/s] 70%|███████ | 70/100 [00:06<00:02, 11.35it/s] 72%|███████▏ | 72/100 [00:06<00:02, 11.34it/s] 74%|███████▍ | 74/100 [00:06<00:02, 11.35it/s] 76%|███████▌ | 76/100 [00:06<00:02, 11.33it/s] 78%|███████▊ | 78/100 [00:06<00:01, 11.36it/s] 80%|████████ | 80/100 [00:07<00:01, 11.39it/s] 82%|████████▏ | 82/100 [00:07<00:01, 11.40it/s] 84%|████████▍ | 84/100 [00:07<00:01, 11.26it/s] 86%|████████▌ | 86/100 [00:07<00:01, 11.29it/s] 88%|████████▊ | 88/100 [00:07<00:01, 11.34it/s] 90%|█████████ | 90/100 [00:07<00:00, 11.39it/s] 92%|█████████▏| 92/100 [00:08<00:00, 11.40it/s] 94%|█████████▍| 94/100 [00:08<00:00, 11.21it/s] 96%|█████████▌| 96/100 [00:08<00:00, 11.28it/s] 98%|█████████▊| 98/100 [00:08<00:00, 11.32it/s] 100%|██████████| 100/100 [00:08<00:00, 11.36it/s] 100%|██████████| 100/100 [00:08<00:00, 11.39it/s]
Prediction
ai-forever/kandinsky-2:9c0bf7d5cf2ed934c5921faf61882657c03c4def9d9cb88330c15bd795edb098Input
- prompt
- red cat, 4k photo
- scheduler
- p_sampler
- prior_steps
- 5
- guidance_scale
- 4
- prior_cf_scale
- 4
- num_inference_steps
- 100
{ "prompt": "red cat, 4k photo", "scheduler": "p_sampler", "prior_steps": "5", "guidance_scale": 4, "prior_cf_scale": 4, "num_inference_steps": 100 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run ai-forever/kandinsky-2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "ai-forever/kandinsky-2:9c0bf7d5cf2ed934c5921faf61882657c03c4def9d9cb88330c15bd795edb098", { input: { prompt: "red cat, 4k photo", scheduler: "p_sampler", prior_steps: "5", guidance_scale: 4, prior_cf_scale: 4, num_inference_steps: 100 } } ); // To access the file URL: console.log(output.url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Import the client:import replicate
Run ai-forever/kandinsky-2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "ai-forever/kandinsky-2:9c0bf7d5cf2ed934c5921faf61882657c03c4def9d9cb88330c15bd795edb098", input={ "prompt": "red cat, 4k photo", "scheduler": "p_sampler", "prior_steps": "5", "guidance_scale": 4, "prior_cf_scale": 4, "num_inference_steps": 100 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run ai-forever/kandinsky-2 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": "ai-forever/kandinsky-2:9c0bf7d5cf2ed934c5921faf61882657c03c4def9d9cb88330c15bd795edb098", "input": { "prompt": "red cat, 4k photo", "scheduler": "p_sampler", "prior_steps": "5", "guidance_scale": 4, "prior_cf_scale": 4, "num_inference_steps": 100 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-04-05T14:18:17.379573Z", "created_at": "2023-04-05T14:17:05.824020Z", "data_removed": false, "error": null, "id": "wixq75uo65glnjcdgrqtngdz4q", "input": { "prompt": "red cat, 4k photo", "scheduler": "p_sampler", "prior_steps": "5", "guidance_scale": 4, "prior_cf_scale": 4, "num_inference_steps": 100 }, "logs": "0%| | 0/100 [00:00<?, ?it/s]\n 1%| | 1/100 [00:00<01:21, 1.21it/s]\n 2%|▏ | 2/100 [00:01<01:08, 1.42it/s]\n 3%|▎ | 3/100 [00:02<01:04, 1.51it/s]\n 4%|▍ | 4/100 [00:02<01:02, 1.54it/s]\n 5%|▌ | 5/100 [00:03<01:00, 1.56it/s]\n 6%|▌ | 6/100 [00:03<01:00, 1.57it/s]\n 7%|▋ | 7/100 [00:04<00:59, 1.57it/s]\n 8%|▊ | 8/100 [00:05<00:58, 1.58it/s]\n 9%|▉ | 9/100 [00:05<00:57, 1.58it/s]\n 10%|█ | 10/100 [00:06<00:56, 1.58it/s]\n 11%|█ | 11/100 [00:07<00:56, 1.58it/s]\n 12%|█▏ | 12/100 [00:07<00:55, 1.58it/s]\n 13%|█▎ | 13/100 [00:08<00:54, 1.59it/s]\n 14%|█▍ | 14/100 [00:08<00:54, 1.58it/s]\n 15%|█▌ | 15/100 [00:09<00:53, 1.58it/s]\n 16%|█▌ | 16/100 [00:10<00:53, 1.58it/s]\n 17%|█▋ | 17/100 [00:10<00:52, 1.59it/s]\n 18%|█▊ | 18/100 [00:11<00:51, 1.59it/s]\n 19%|█▉ | 19/100 [00:12<00:51, 1.59it/s]\n 20%|██ | 20/100 [00:12<00:50, 1.58it/s]\n 21%|██ | 21/100 [00:13<00:50, 1.58it/s]\n 22%|██▏ | 22/100 [00:14<00:49, 1.58it/s]\n 23%|██▎ | 23/100 [00:14<00:48, 1.58it/s]\n 24%|██▍ | 24/100 [00:15<00:48, 1.58it/s]\n 25%|██▌ | 25/100 [00:15<00:47, 1.57it/s]\n 26%|██▌ | 26/100 [00:16<00:46, 1.58it/s]\n 27%|██▋ | 27/100 [00:17<00:46, 1.57it/s]\n 28%|██▊ | 28/100 [00:17<00:45, 1.58it/s]\n 29%|██▉ | 29/100 [00:18<00:45, 1.57it/s]\n 30%|███ | 30/100 [00:19<00:44, 1.57it/s]\n 31%|███ | 31/100 [00:19<00:44, 1.57it/s]\n 32%|███▏ | 32/100 [00:20<00:43, 1.57it/s]\n 33%|███▎ | 33/100 [00:21<00:42, 1.57it/s]\n 34%|███▍ | 34/100 [00:21<00:42, 1.57it/s]\n 35%|███▌ | 35/100 [00:22<00:41, 1.56it/s]\n 36%|███▌ | 36/100 [00:22<00:40, 1.56it/s]\n 37%|███▋ | 37/100 [00:23<00:40, 1.56it/s]\n 38%|███▊ | 38/100 [00:24<00:39, 1.56it/s]\n 39%|███▉ | 39/100 [00:24<00:39, 1.56it/s]\n 40%|████ | 40/100 [00:25<00:38, 1.56it/s]\n 41%|████ | 41/100 [00:26<00:37, 1.56it/s]\n 42%|████▏ | 42/100 [00:26<00:37, 1.55it/s]\n 43%|████▎ | 43/100 [00:27<00:36, 1.56it/s]\n 44%|████▍ | 44/100 [00:28<00:35, 1.56it/s]\n 45%|████▌ | 45/100 [00:28<00:35, 1.56it/s]\n 46%|████▌ | 46/100 [00:29<00:34, 1.56it/s]\n 47%|████▋ | 47/100 [00:30<00:33, 1.56it/s]\n 48%|████▊ | 48/100 [00:30<00:33, 1.56it/s]\n 49%|████▉ | 49/100 [00:31<00:32, 1.56it/s]\n 50%|█████ | 50/100 [00:31<00:32, 1.56it/s]\n 51%|█████ | 51/100 [00:32<00:31, 1.56it/s]\n 52%|█████▏ | 52/100 [00:33<00:30, 1.55it/s]\n 53%|█████▎ | 53/100 [00:33<00:30, 1.55it/s]\n 54%|█████▍ | 54/100 [00:34<00:29, 1.55it/s]\n 55%|█████▌ | 55/100 [00:35<00:28, 1.55it/s]\n 56%|█████▌ | 56/100 [00:35<00:28, 1.55it/s]\n 57%|█████▋ | 57/100 [00:36<00:27, 1.55it/s]\n 58%|█████▊ | 58/100 [00:37<00:27, 1.54it/s]\n 59%|█████▉ | 59/100 [00:37<00:26, 1.54it/s]\n 60%|██████ | 60/100 [00:38<00:25, 1.54it/s]\n 61%|██████ | 61/100 [00:39<00:25, 1.54it/s]\n 62%|██████▏ | 62/100 [00:39<00:24, 1.54it/s]\n 63%|██████▎ | 63/100 [00:40<00:24, 1.54it/s]\n 64%|██████▍ | 64/100 [00:41<00:23, 1.54it/s]\n 65%|██████▌ | 65/100 [00:41<00:22, 1.54it/s]\n 66%|██████▌ | 66/100 [00:42<00:22, 1.54it/s]\n 67%|██████▋ | 67/100 [00:42<00:21, 1.54it/s]\n 68%|██████▊ | 68/100 [00:43<00:20, 1.54it/s]\n 69%|██████▉ | 69/100 [00:44<00:20, 1.54it/s]\n 70%|███████ | 70/100 [00:44<00:19, 1.54it/s]\n 71%|███████ | 71/100 [00:45<00:18, 1.54it/s]\n 72%|███████▏ | 72/100 [00:46<00:18, 1.54it/s]\n 73%|███████▎ | 73/100 [00:46<00:17, 1.53it/s]\n 74%|███████▍ | 74/100 [00:47<00:16, 1.54it/s]\n 75%|███████▌ | 75/100 [00:48<00:16, 1.53it/s]\n 76%|███████▌ | 76/100 [00:48<00:15, 1.54it/s]\n 77%|███████▋ | 77/100 [00:49<00:14, 1.54it/s]\n 78%|███████▊ | 78/100 [00:50<00:14, 1.54it/s]\n 79%|███████▉ | 79/100 [00:50<00:13, 1.54it/s]\n 80%|████████ | 80/100 [00:51<00:13, 1.54it/s]\n 81%|████████ | 81/100 [00:52<00:12, 1.54it/s]\n 82%|████████▏ | 82/100 [00:52<00:11, 1.54it/s]\n 83%|████████▎ | 83/100 [00:53<00:11, 1.54it/s]\n 84%|████████▍ | 84/100 [00:54<00:10, 1.54it/s]\n 85%|████████▌ | 85/100 [00:54<00:09, 1.54it/s]\n 86%|████████▌ | 86/100 [00:55<00:09, 1.54it/s]\n 87%|████████▋ | 87/100 [00:55<00:08, 1.54it/s]\n 88%|████████▊ | 88/100 [00:56<00:07, 1.54it/s]\n 89%|████████▉ | 89/100 [00:57<00:07, 1.54it/s]\n 90%|█████████ | 90/100 [00:57<00:06, 1.54it/s]\n 91%|█████████ | 91/100 [00:58<00:05, 1.54it/s]\n 92%|█████████▏| 92/100 [00:59<00:05, 1.54it/s]\n 93%|█████████▎| 93/100 [00:59<00:04, 1.54it/s]\n 94%|█████████▍| 94/100 [01:00<00:03, 1.54it/s]\n 95%|█████████▌| 95/100 [01:01<00:03, 1.53it/s]\n 96%|█████████▌| 96/100 [01:01<00:02, 1.53it/s]\n 97%|█████████▋| 97/100 [01:02<00:01, 1.53it/s]\n 98%|█████████▊| 98/100 [01:03<00:01, 1.53it/s]\n 99%|█████████▉| 99/100 [01:03<00:00, 1.52it/s]\n100%|██████████| 100/100 [01:04<00:00, 1.52it/s]\n100%|██████████| 100/100 [01:04<00:00, 1.55it/s]", "metrics": { "predict_time": 71.261476, "total_time": 71.555553 }, "output": "https://replicate.delivery/pbxt/NsOpfQRos43e40IzSq4SY7NTtxGodmSWo1m74K17SVpoUzuQA/out.png", "started_at": "2023-04-05T14:17:06.118097Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/wixq75uo65glnjcdgrqtngdz4q", "cancel": "https://api.replicate.com/v1/predictions/wixq75uo65glnjcdgrqtngdz4q/cancel" }, "version": "9c0bf7d5cf2ed934c5921faf61882657c03c4def9d9cb88330c15bd795edb098" }
Generated in0%| | 0/100 [00:00<?, ?it/s] 1%| | 1/100 [00:00<01:21, 1.21it/s] 2%|▏ | 2/100 [00:01<01:08, 1.42it/s] 3%|▎ | 3/100 [00:02<01:04, 1.51it/s] 4%|▍ | 4/100 [00:02<01:02, 1.54it/s] 5%|▌ | 5/100 [00:03<01:00, 1.56it/s] 6%|▌ | 6/100 [00:03<01:00, 1.57it/s] 7%|▋ | 7/100 [00:04<00:59, 1.57it/s] 8%|▊ | 8/100 [00:05<00:58, 1.58it/s] 9%|▉ | 9/100 [00:05<00:57, 1.58it/s] 10%|█ | 10/100 [00:06<00:56, 1.58it/s] 11%|█ | 11/100 [00:07<00:56, 1.58it/s] 12%|█▏ | 12/100 [00:07<00:55, 1.58it/s] 13%|█▎ | 13/100 [00:08<00:54, 1.59it/s] 14%|█▍ | 14/100 [00:08<00:54, 1.58it/s] 15%|█▌ | 15/100 [00:09<00:53, 1.58it/s] 16%|█▌ | 16/100 [00:10<00:53, 1.58it/s] 17%|█▋ | 17/100 [00:10<00:52, 1.59it/s] 18%|█▊ | 18/100 [00:11<00:51, 1.59it/s] 19%|█▉ | 19/100 [00:12<00:51, 1.59it/s] 20%|██ | 20/100 [00:12<00:50, 1.58it/s] 21%|██ | 21/100 [00:13<00:50, 1.58it/s] 22%|██▏ | 22/100 [00:14<00:49, 1.58it/s] 23%|██▎ | 23/100 [00:14<00:48, 1.58it/s] 24%|██▍ | 24/100 [00:15<00:48, 1.58it/s] 25%|██▌ | 25/100 [00:15<00:47, 1.57it/s] 26%|██▌ | 26/100 [00:16<00:46, 1.58it/s] 27%|██▋ | 27/100 [00:17<00:46, 1.57it/s] 28%|██▊ | 28/100 [00:17<00:45, 1.58it/s] 29%|██▉ | 29/100 [00:18<00:45, 1.57it/s] 30%|███ | 30/100 [00:19<00:44, 1.57it/s] 31%|███ | 31/100 [00:19<00:44, 1.57it/s] 32%|███▏ | 32/100 [00:20<00:43, 1.57it/s] 33%|███▎ | 33/100 [00:21<00:42, 1.57it/s] 34%|███▍ | 34/100 [00:21<00:42, 1.57it/s] 35%|███▌ | 35/100 [00:22<00:41, 1.56it/s] 36%|███▌ | 36/100 [00:22<00:40, 1.56it/s] 37%|███▋ | 37/100 [00:23<00:40, 1.56it/s] 38%|███▊ | 38/100 [00:24<00:39, 1.56it/s] 39%|███▉ | 39/100 [00:24<00:39, 1.56it/s] 40%|████ | 40/100 [00:25<00:38, 1.56it/s] 41%|████ | 41/100 [00:26<00:37, 1.56it/s] 42%|████▏ | 42/100 [00:26<00:37, 1.55it/s] 43%|████▎ | 43/100 [00:27<00:36, 1.56it/s] 44%|████▍ | 44/100 [00:28<00:35, 1.56it/s] 45%|████▌ | 45/100 [00:28<00:35, 1.56it/s] 46%|████▌ | 46/100 [00:29<00:34, 1.56it/s] 47%|████▋ | 47/100 [00:30<00:33, 1.56it/s] 48%|████▊ | 48/100 [00:30<00:33, 1.56it/s] 49%|████▉ | 49/100 [00:31<00:32, 1.56it/s] 50%|█████ | 50/100 [00:31<00:32, 1.56it/s] 51%|█████ | 51/100 [00:32<00:31, 1.56it/s] 52%|█████▏ | 52/100 [00:33<00:30, 1.55it/s] 53%|█████▎ | 53/100 [00:33<00:30, 1.55it/s] 54%|█████▍ | 54/100 [00:34<00:29, 1.55it/s] 55%|█████▌ | 55/100 [00:35<00:28, 1.55it/s] 56%|█████▌ | 56/100 [00:35<00:28, 1.55it/s] 57%|█████▋ | 57/100 [00:36<00:27, 1.55it/s] 58%|█████▊ | 58/100 [00:37<00:27, 1.54it/s] 59%|█████▉ | 59/100 [00:37<00:26, 1.54it/s] 60%|██████ | 60/100 [00:38<00:25, 1.54it/s] 61%|██████ | 61/100 [00:39<00:25, 1.54it/s] 62%|██████▏ | 62/100 [00:39<00:24, 1.54it/s] 63%|██████▎ | 63/100 [00:40<00:24, 1.54it/s] 64%|██████▍ | 64/100 [00:41<00:23, 1.54it/s] 65%|██████▌ | 65/100 [00:41<00:22, 1.54it/s] 66%|██████▌ | 66/100 [00:42<00:22, 1.54it/s] 67%|██████▋ | 67/100 [00:42<00:21, 1.54it/s] 68%|██████▊ | 68/100 [00:43<00:20, 1.54it/s] 69%|██████▉ | 69/100 [00:44<00:20, 1.54it/s] 70%|███████ | 70/100 [00:44<00:19, 1.54it/s] 71%|███████ | 71/100 [00:45<00:18, 1.54it/s] 72%|███████▏ | 72/100 [00:46<00:18, 1.54it/s] 73%|███████▎ | 73/100 [00:46<00:17, 1.53it/s] 74%|███████▍ | 74/100 [00:47<00:16, 1.54it/s] 75%|███████▌ | 75/100 [00:48<00:16, 1.53it/s] 76%|███████▌ | 76/100 [00:48<00:15, 1.54it/s] 77%|███████▋ | 77/100 [00:49<00:14, 1.54it/s] 78%|███████▊ | 78/100 [00:50<00:14, 1.54it/s] 79%|███████▉ | 79/100 [00:50<00:13, 1.54it/s] 80%|████████ | 80/100 [00:51<00:13, 1.54it/s] 81%|████████ | 81/100 [00:52<00:12, 1.54it/s] 82%|████████▏ | 82/100 [00:52<00:11, 1.54it/s] 83%|████████▎ | 83/100 [00:53<00:11, 1.54it/s] 84%|████████▍ | 84/100 [00:54<00:10, 1.54it/s] 85%|████████▌ | 85/100 [00:54<00:09, 1.54it/s] 86%|████████▌ | 86/100 [00:55<00:09, 1.54it/s] 87%|████████▋ | 87/100 [00:55<00:08, 1.54it/s] 88%|████████▊ | 88/100 [00:56<00:07, 1.54it/s] 89%|████████▉ | 89/100 [00:57<00:07, 1.54it/s] 90%|█████████ | 90/100 [00:57<00:06, 1.54it/s] 91%|█████████ | 91/100 [00:58<00:05, 1.54it/s] 92%|█████████▏| 92/100 [00:59<00:05, 1.54it/s] 93%|█████████▎| 93/100 [00:59<00:04, 1.54it/s] 94%|█████████▍| 94/100 [01:00<00:03, 1.54it/s] 95%|█████████▌| 95/100 [01:01<00:03, 1.53it/s] 96%|█████████▌| 96/100 [01:01<00:02, 1.53it/s] 97%|█████████▋| 97/100 [01:02<00:01, 1.53it/s] 98%|█████████▊| 98/100 [01:03<00:01, 1.53it/s] 99%|█████████▉| 99/100 [01:03<00:00, 1.52it/s] 100%|██████████| 100/100 [01:04<00:00, 1.52it/s] 100%|██████████| 100/100 [01:04<00:00, 1.55it/s]
Prediction
ai-forever/kandinsky-2:9c0bf7d5cf2ed934c5921faf61882657c03c4def9d9cb88330c15bd795edb098Input
- prompt
- Einstein in space around the logarithm scheme
- scheduler
- ddim_sampler
- prior_steps
- 5
- guidance_scale
- 5
- prior_cf_scale
- 4
- num_inference_steps
- 100
{ "prompt": "Einstein in space around the logarithm scheme", "scheduler": "ddim_sampler", "prior_steps": "5", "guidance_scale": 5, "prior_cf_scale": 4, "num_inference_steps": 100 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run ai-forever/kandinsky-2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "ai-forever/kandinsky-2:9c0bf7d5cf2ed934c5921faf61882657c03c4def9d9cb88330c15bd795edb098", { input: { prompt: "Einstein in space around the logarithm scheme", scheduler: "ddim_sampler", prior_steps: "5", guidance_scale: 5, prior_cf_scale: 4, num_inference_steps: 100 } } ); // To access the file URL: console.log(output.url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Import the client:import replicate
Run ai-forever/kandinsky-2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "ai-forever/kandinsky-2:9c0bf7d5cf2ed934c5921faf61882657c03c4def9d9cb88330c15bd795edb098", input={ "prompt": "Einstein in space around the logarithm scheme", "scheduler": "ddim_sampler", "prior_steps": "5", "guidance_scale": 5, "prior_cf_scale": 4, "num_inference_steps": 100 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run ai-forever/kandinsky-2 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": "ai-forever/kandinsky-2:9c0bf7d5cf2ed934c5921faf61882657c03c4def9d9cb88330c15bd795edb098", "input": { "prompt": "Einstein in space around the logarithm scheme", "scheduler": "ddim_sampler", "prior_steps": "5", "guidance_scale": 5, "prior_cf_scale": 4, "num_inference_steps": 100 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-04-05T14:24:04.983419Z", "created_at": "2023-04-05T14:22:54.003108Z", "data_removed": false, "error": null, "id": "zntgj3qqcbbqbgufbv3egxqooi", "input": { "prompt": "Einstein in space around the logarithm scheme", "scheduler": "ddim_sampler", "prior_steps": "5", "guidance_scale": 5, "prior_cf_scale": 4, "num_inference_steps": 100 }, "logs": "DDIM Sampler: 0%| | 0/100 [00:00<?, ?it/s]\nDDIM Sampler: 1%| | 1/100 [00:00<01:04, 1.53it/s]\nDDIM Sampler: 2%|▏ | 2/100 [00:01<01:04, 1.52it/s]\nDDIM Sampler: 3%|▎ | 3/100 [00:01<01:04, 1.51it/s]\nDDIM Sampler: 4%|▍ | 4/100 [00:02<01:03, 1.51it/s]\nDDIM Sampler: 5%|▌ | 5/100 [00:03<01:02, 1.51it/s]\nDDIM Sampler: 6%|▌ | 6/100 [00:03<01:02, 1.50it/s]\nDDIM Sampler: 7%|▋ | 7/100 [00:04<01:02, 1.50it/s]\nDDIM Sampler: 8%|▊ | 8/100 [00:05<01:01, 1.50it/s]\nDDIM Sampler: 9%|▉ | 9/100 [00:05<01:00, 1.49it/s]\nDDIM Sampler: 10%|█ | 10/100 [00:06<01:00, 1.50it/s]\nDDIM Sampler: 11%|█ | 11/100 [00:07<00:59, 1.49it/s]\nDDIM Sampler: 12%|█▏ | 12/100 [00:08<00:59, 1.49it/s]\nDDIM Sampler: 13%|█▎ | 13/100 [00:08<00:58, 1.48it/s]\nDDIM Sampler: 14%|█▍ | 14/100 [00:09<00:58, 1.48it/s]\nDDIM Sampler: 15%|█▌ | 15/100 [00:10<00:57, 1.48it/s]\nDDIM Sampler: 16%|█▌ | 16/100 [00:10<00:56, 1.48it/s]\nDDIM Sampler: 17%|█▋ | 17/100 [00:11<00:56, 1.47it/s]\nDDIM Sampler: 18%|█▊ | 18/100 [00:12<00:55, 1.47it/s]\nDDIM Sampler: 19%|█▉ | 19/100 [00:12<00:55, 1.46it/s]\nDDIM Sampler: 20%|██ | 20/100 [00:13<00:54, 1.46it/s]\nDDIM Sampler: 21%|██ | 21/100 [00:14<00:54, 1.46it/s]\nDDIM Sampler: 22%|██▏ | 22/100 [00:14<00:53, 1.45it/s]\nDDIM Sampler: 23%|██▎ | 23/100 [00:15<00:53, 1.45it/s]\nDDIM Sampler: 24%|██▍ | 24/100 [00:16<00:52, 1.45it/s]\nDDIM Sampler: 25%|██▌ | 25/100 [00:16<00:51, 1.45it/s]\nDDIM Sampler: 26%|██▌ | 26/100 [00:17<00:51, 1.45it/s]\nDDIM Sampler: 27%|██▋ | 27/100 [00:18<00:50, 1.45it/s]\nDDIM Sampler: 28%|██▊ | 28/100 [00:18<00:49, 1.45it/s]\nDDIM Sampler: 29%|██▉ | 29/100 [00:19<00:49, 1.45it/s]\nDDIM Sampler: 30%|███ | 30/100 [00:20<00:48, 1.45it/s]\nDDIM Sampler: 31%|███ | 31/100 [00:21<00:47, 1.44it/s]\nDDIM Sampler: 32%|███▏ | 32/100 [00:21<00:47, 1.44it/s]\nDDIM Sampler: 33%|███▎ | 33/100 [00:22<00:46, 1.43it/s]\nDDIM Sampler: 34%|███▍ | 34/100 [00:23<00:45, 1.43it/s]\nDDIM Sampler: 35%|███▌ | 35/100 [00:23<00:45, 1.43it/s]\nDDIM Sampler: 36%|███▌ | 36/100 [00:24<00:44, 1.44it/s]\nDDIM Sampler: 37%|███▋ | 37/100 [00:25<00:43, 1.43it/s]\nDDIM Sampler: 38%|███▊ | 38/100 [00:25<00:43, 1.43it/s]\nDDIM Sampler: 39%|███▉ | 39/100 [00:26<00:42, 1.43it/s]\nDDIM Sampler: 40%|████ | 40/100 [00:27<00:41, 1.43it/s]\nDDIM Sampler: 41%|████ | 41/100 [00:28<00:41, 1.43it/s]\nDDIM Sampler: 42%|████▏ | 42/100 [00:28<00:40, 1.42it/s]\nDDIM Sampler: 43%|████▎ | 43/100 [00:29<00:39, 1.43it/s]\nDDIM Sampler: 44%|████▍ | 44/100 [00:30<00:39, 1.42it/s]\nDDIM Sampler: 45%|████▌ | 45/100 [00:30<00:38, 1.42it/s]\nDDIM Sampler: 46%|████▌ | 46/100 [00:31<00:37, 1.42it/s]\nDDIM Sampler: 47%|████▋ | 47/100 [00:32<00:37, 1.42it/s]\nDDIM Sampler: 48%|████▊ | 48/100 [00:33<00:36, 1.42it/s]\nDDIM Sampler: 49%|████▉ | 49/100 [00:33<00:35, 1.42it/s]\nDDIM Sampler: 50%|█████ | 50/100 [00:34<00:35, 1.42it/s]\nDDIM Sampler: 51%|█████ | 51/100 [00:35<00:34, 1.43it/s]\nDDIM Sampler: 52%|█████▏ | 52/100 [00:35<00:33, 1.42it/s]\nDDIM Sampler: 53%|█████▎ | 53/100 [00:36<00:33, 1.42it/s]\nDDIM Sampler: 54%|█████▍ | 54/100 [00:37<00:32, 1.43it/s]\nDDIM Sampler: 55%|█████▌ | 55/100 [00:37<00:31, 1.42it/s]\nDDIM Sampler: 56%|█████▌ | 56/100 [00:38<00:30, 1.43it/s]\nDDIM Sampler: 57%|█████▋ | 57/100 [00:39<00:29, 1.43it/s]\nDDIM Sampler: 58%|█████▊ | 58/100 [00:39<00:29, 1.44it/s]\nDDIM Sampler: 59%|█████▉ | 59/100 [00:40<00:28, 1.44it/s]\nDDIM Sampler: 60%|██████ | 60/100 [00:41<00:27, 1.44it/s]\nDDIM Sampler: 61%|██████ | 61/100 [00:42<00:26, 1.45it/s]\nDDIM Sampler: 62%|██████▏ | 62/100 [00:42<00:26, 1.44it/s]\nDDIM Sampler: 63%|██████▎ | 63/100 [00:43<00:25, 1.45it/s]\nDDIM Sampler: 64%|██████▍ | 64/100 [00:44<00:24, 1.45it/s]\nDDIM Sampler: 65%|██████▌ | 65/100 [00:44<00:24, 1.45it/s]\nDDIM Sampler: 66%|██████▌ | 66/100 [00:45<00:23, 1.45it/s]\nDDIM Sampler: 67%|██████▋ | 67/100 [00:46<00:22, 1.45it/s]\nDDIM Sampler: 68%|██████▊ | 68/100 [00:46<00:22, 1.45it/s]\nDDIM Sampler: 69%|██████▉ | 69/100 [00:47<00:21, 1.45it/s]\nDDIM Sampler: 70%|███████ | 70/100 [00:48<00:20, 1.45it/s]\nDDIM Sampler: 71%|███████ | 71/100 [00:48<00:19, 1.45it/s]\nDDIM Sampler: 72%|███████▏ | 72/100 [00:49<00:19, 1.45it/s]\nDDIM Sampler: 73%|███████▎ | 73/100 [00:50<00:18, 1.45it/s]\nDDIM Sampler: 74%|███████▍ | 74/100 [00:51<00:17, 1.45it/s]\nDDIM Sampler: 75%|███████▌ | 75/100 [00:51<00:17, 1.45it/s]\nDDIM Sampler: 76%|███████▌ | 76/100 [00:52<00:16, 1.45it/s]\nDDIM Sampler: 77%|███████▋ | 77/100 [00:53<00:15, 1.46it/s]\nDDIM Sampler: 78%|███████▊ | 78/100 [00:53<00:15, 1.46it/s]\nDDIM Sampler: 79%|███████▉ | 79/100 [00:54<00:14, 1.46it/s]\nDDIM Sampler: 80%|████████ | 80/100 [00:55<00:13, 1.46it/s]\nDDIM Sampler: 81%|████████ | 81/100 [00:55<00:12, 1.46it/s]\nDDIM Sampler: 82%|████████▏ | 82/100 [00:56<00:12, 1.47it/s]\nDDIM Sampler: 83%|████████▎ | 83/100 [00:57<00:11, 1.47it/s]\nDDIM Sampler: 84%|████████▍ | 84/100 [00:57<00:10, 1.47it/s]\nDDIM Sampler: 85%|████████▌ | 85/100 [00:58<00:10, 1.47it/s]\nDDIM Sampler: 86%|████████▌ | 86/100 [00:59<00:09, 1.47it/s]\nDDIM Sampler: 87%|████████▋ | 87/100 [00:59<00:08, 1.47it/s]\nDDIM Sampler: 88%|████████▊ | 88/100 [01:00<00:08, 1.47it/s]\nDDIM Sampler: 89%|████████▉ | 89/100 [01:01<00:07, 1.47it/s]\nDDIM Sampler: 90%|█████████ | 90/100 [01:01<00:06, 1.47it/s]\nDDIM Sampler: 91%|█████████ | 91/100 [01:02<00:06, 1.47it/s]\nDDIM Sampler: 92%|█████████▏| 92/100 [01:03<00:05, 1.47it/s]\nDDIM Sampler: 93%|█████████▎| 93/100 [01:03<00:04, 1.47it/s]\nDDIM Sampler: 94%|█████████▍| 94/100 [01:04<00:04, 1.47it/s]\nDDIM Sampler: 95%|█████████▌| 95/100 [01:05<00:03, 1.48it/s]\nDDIM Sampler: 96%|█████████▌| 96/100 [01:05<00:02, 1.48it/s]\nDDIM Sampler: 97%|█████████▋| 97/100 [01:06<00:02, 1.48it/s]\nDDIM Sampler: 98%|█████████▊| 98/100 [01:07<00:01, 1.48it/s]\nDDIM Sampler: 99%|█████████▉| 99/100 [01:08<00:00, 1.48it/s]\nDDIM Sampler: 100%|██████████| 100/100 [01:08<00:00, 1.48it/s]\nDDIM Sampler: 100%|██████████| 100/100 [01:08<00:00, 1.46it/s]", "metrics": { "predict_time": 70.88947, "total_time": 70.980311 }, "output": "https://replicate.delivery/pbxt/2ReXGPtHrE1xe09lakZGFNY6FSdXUOPfSNkw2PAIXAAJ0mdhA/out.png", "started_at": "2023-04-05T14:22:54.093949Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/zntgj3qqcbbqbgufbv3egxqooi", "cancel": "https://api.replicate.com/v1/predictions/zntgj3qqcbbqbgufbv3egxqooi/cancel" }, "version": "9c0bf7d5cf2ed934c5921faf61882657c03c4def9d9cb88330c15bd795edb098" }
Generated inDDIM Sampler: 0%| | 0/100 [00:00<?, ?it/s] DDIM Sampler: 1%| | 1/100 [00:00<01:04, 1.53it/s] DDIM Sampler: 2%|▏ | 2/100 [00:01<01:04, 1.52it/s] DDIM Sampler: 3%|▎ | 3/100 [00:01<01:04, 1.51it/s] DDIM Sampler: 4%|▍ | 4/100 [00:02<01:03, 1.51it/s] DDIM Sampler: 5%|▌ | 5/100 [00:03<01:02, 1.51it/s] DDIM Sampler: 6%|▌ | 6/100 [00:03<01:02, 1.50it/s] DDIM Sampler: 7%|▋ | 7/100 [00:04<01:02, 1.50it/s] DDIM Sampler: 8%|▊ | 8/100 [00:05<01:01, 1.50it/s] DDIM Sampler: 9%|▉ | 9/100 [00:05<01:00, 1.49it/s] DDIM Sampler: 10%|█ | 10/100 [00:06<01:00, 1.50it/s] DDIM Sampler: 11%|█ | 11/100 [00:07<00:59, 1.49it/s] DDIM Sampler: 12%|█▏ | 12/100 [00:08<00:59, 1.49it/s] DDIM Sampler: 13%|█▎ | 13/100 [00:08<00:58, 1.48it/s] DDIM Sampler: 14%|█▍ | 14/100 [00:09<00:58, 1.48it/s] DDIM Sampler: 15%|█▌ | 15/100 [00:10<00:57, 1.48it/s] DDIM Sampler: 16%|█▌ | 16/100 [00:10<00:56, 1.48it/s] DDIM Sampler: 17%|█▋ | 17/100 [00:11<00:56, 1.47it/s] DDIM Sampler: 18%|█▊ | 18/100 [00:12<00:55, 1.47it/s] DDIM Sampler: 19%|█▉ | 19/100 [00:12<00:55, 1.46it/s] DDIM Sampler: 20%|██ | 20/100 [00:13<00:54, 1.46it/s] DDIM Sampler: 21%|██ | 21/100 [00:14<00:54, 1.46it/s] DDIM Sampler: 22%|██▏ | 22/100 [00:14<00:53, 1.45it/s] DDIM Sampler: 23%|██▎ | 23/100 [00:15<00:53, 1.45it/s] DDIM Sampler: 24%|██▍ | 24/100 [00:16<00:52, 1.45it/s] DDIM Sampler: 25%|██▌ | 25/100 [00:16<00:51, 1.45it/s] DDIM Sampler: 26%|██▌ | 26/100 [00:17<00:51, 1.45it/s] DDIM Sampler: 27%|██▋ | 27/100 [00:18<00:50, 1.45it/s] DDIM Sampler: 28%|██▊ | 28/100 [00:18<00:49, 1.45it/s] DDIM Sampler: 29%|██▉ | 29/100 [00:19<00:49, 1.45it/s] DDIM Sampler: 30%|███ | 30/100 [00:20<00:48, 1.45it/s] DDIM Sampler: 31%|███ | 31/100 [00:21<00:47, 1.44it/s] DDIM Sampler: 32%|███▏ | 32/100 [00:21<00:47, 1.44it/s] DDIM Sampler: 33%|███▎ | 33/100 [00:22<00:46, 1.43it/s] DDIM Sampler: 34%|███▍ | 34/100 [00:23<00:45, 1.43it/s] DDIM Sampler: 35%|███▌ | 35/100 [00:23<00:45, 1.43it/s] DDIM Sampler: 36%|███▌ | 36/100 [00:24<00:44, 1.44it/s] DDIM Sampler: 37%|███▋ | 37/100 [00:25<00:43, 1.43it/s] DDIM Sampler: 38%|███▊ | 38/100 [00:25<00:43, 1.43it/s] DDIM Sampler: 39%|███▉ | 39/100 [00:26<00:42, 1.43it/s] DDIM Sampler: 40%|████ | 40/100 [00:27<00:41, 1.43it/s] DDIM Sampler: 41%|████ | 41/100 [00:28<00:41, 1.43it/s] DDIM Sampler: 42%|████▏ | 42/100 [00:28<00:40, 1.42it/s] DDIM Sampler: 43%|████▎ | 43/100 [00:29<00:39, 1.43it/s] DDIM Sampler: 44%|████▍ | 44/100 [00:30<00:39, 1.42it/s] DDIM Sampler: 45%|████▌ | 45/100 [00:30<00:38, 1.42it/s] DDIM Sampler: 46%|████▌ | 46/100 [00:31<00:37, 1.42it/s] DDIM Sampler: 47%|████▋ | 47/100 [00:32<00:37, 1.42it/s] DDIM Sampler: 48%|████▊ | 48/100 [00:33<00:36, 1.42it/s] DDIM Sampler: 49%|████▉ | 49/100 [00:33<00:35, 1.42it/s] DDIM Sampler: 50%|█████ | 50/100 [00:34<00:35, 1.42it/s] DDIM Sampler: 51%|█████ | 51/100 [00:35<00:34, 1.43it/s] DDIM Sampler: 52%|█████▏ | 52/100 [00:35<00:33, 1.42it/s] DDIM Sampler: 53%|█████▎ | 53/100 [00:36<00:33, 1.42it/s] DDIM Sampler: 54%|█████▍ | 54/100 [00:37<00:32, 1.43it/s] DDIM Sampler: 55%|█████▌ | 55/100 [00:37<00:31, 1.42it/s] DDIM Sampler: 56%|█████▌ | 56/100 [00:38<00:30, 1.43it/s] DDIM Sampler: 57%|█████▋ | 57/100 [00:39<00:29, 1.43it/s] DDIM Sampler: 58%|█████▊ | 58/100 [00:39<00:29, 1.44it/s] DDIM Sampler: 59%|█████▉ | 59/100 [00:40<00:28, 1.44it/s] DDIM Sampler: 60%|██████ | 60/100 [00:41<00:27, 1.44it/s] DDIM Sampler: 61%|██████ | 61/100 [00:42<00:26, 1.45it/s] DDIM Sampler: 62%|██████▏ | 62/100 [00:42<00:26, 1.44it/s] DDIM Sampler: 63%|██████▎ | 63/100 [00:43<00:25, 1.45it/s] DDIM Sampler: 64%|██████▍ | 64/100 [00:44<00:24, 1.45it/s] DDIM Sampler: 65%|██████▌ | 65/100 [00:44<00:24, 1.45it/s] DDIM Sampler: 66%|██████▌ | 66/100 [00:45<00:23, 1.45it/s] DDIM Sampler: 67%|██████▋ | 67/100 [00:46<00:22, 1.45it/s] DDIM Sampler: 68%|██████▊ | 68/100 [00:46<00:22, 1.45it/s] DDIM Sampler: 69%|██████▉ | 69/100 [00:47<00:21, 1.45it/s] DDIM Sampler: 70%|███████ | 70/100 [00:48<00:20, 1.45it/s] DDIM Sampler: 71%|███████ | 71/100 [00:48<00:19, 1.45it/s] DDIM Sampler: 72%|███████▏ | 72/100 [00:49<00:19, 1.45it/s] DDIM Sampler: 73%|███████▎ | 73/100 [00:50<00:18, 1.45it/s] DDIM Sampler: 74%|███████▍ | 74/100 [00:51<00:17, 1.45it/s] DDIM Sampler: 75%|███████▌ | 75/100 [00:51<00:17, 1.45it/s] DDIM Sampler: 76%|███████▌ | 76/100 [00:52<00:16, 1.45it/s] DDIM Sampler: 77%|███████▋ | 77/100 [00:53<00:15, 1.46it/s] DDIM Sampler: 78%|███████▊ | 78/100 [00:53<00:15, 1.46it/s] DDIM Sampler: 79%|███████▉ | 79/100 [00:54<00:14, 1.46it/s] DDIM Sampler: 80%|████████ | 80/100 [00:55<00:13, 1.46it/s] DDIM Sampler: 81%|████████ | 81/100 [00:55<00:12, 1.46it/s] DDIM Sampler: 82%|████████▏ | 82/100 [00:56<00:12, 1.47it/s] DDIM Sampler: 83%|████████▎ | 83/100 [00:57<00:11, 1.47it/s] DDIM Sampler: 84%|████████▍ | 84/100 [00:57<00:10, 1.47it/s] DDIM Sampler: 85%|████████▌ | 85/100 [00:58<00:10, 1.47it/s] DDIM Sampler: 86%|████████▌ | 86/100 [00:59<00:09, 1.47it/s] DDIM Sampler: 87%|████████▋ | 87/100 [00:59<00:08, 1.47it/s] DDIM Sampler: 88%|████████▊ | 88/100 [01:00<00:08, 1.47it/s] DDIM Sampler: 89%|████████▉ | 89/100 [01:01<00:07, 1.47it/s] DDIM Sampler: 90%|█████████ | 90/100 [01:01<00:06, 1.47it/s] DDIM Sampler: 91%|█████████ | 91/100 [01:02<00:06, 1.47it/s] DDIM Sampler: 92%|█████████▏| 92/100 [01:03<00:05, 1.47it/s] DDIM Sampler: 93%|█████████▎| 93/100 [01:03<00:04, 1.47it/s] DDIM Sampler: 94%|█████████▍| 94/100 [01:04<00:04, 1.47it/s] DDIM Sampler: 95%|█████████▌| 95/100 [01:05<00:03, 1.48it/s] DDIM Sampler: 96%|█████████▌| 96/100 [01:05<00:02, 1.48it/s] DDIM Sampler: 97%|█████████▋| 97/100 [01:06<00:02, 1.48it/s] DDIM Sampler: 98%|█████████▊| 98/100 [01:07<00:01, 1.48it/s] DDIM Sampler: 99%|█████████▉| 99/100 [01:08<00:00, 1.48it/s] DDIM Sampler: 100%|██████████| 100/100 [01:08<00:00, 1.48it/s] DDIM Sampler: 100%|██████████| 100/100 [01:08<00:00, 1.46it/s]
Prediction
ai-forever/kandinsky-2:65a15f6e3c538ee4adf5142411455308926714f7d3f5c940d9f7bc519e0e5c1aInput
- prompt
- a film still of a cute bird in a tree from a 2.5d animated movie, sharp focus
- scheduler
- p_sampler
- prior_steps
- 5
- guidance_scale
- 4
- prior_cf_scale
- 4
- num_inference_steps
- 100
{ "prompt": "a film still of a cute bird in a tree from a 2.5d animated movie, sharp focus", "scheduler": "p_sampler", "prior_steps": "5", "guidance_scale": 4, "prior_cf_scale": 4, "num_inference_steps": 100 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run ai-forever/kandinsky-2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "ai-forever/kandinsky-2:65a15f6e3c538ee4adf5142411455308926714f7d3f5c940d9f7bc519e0e5c1a", { input: { prompt: "a film still of a cute bird in a tree from a 2.5d animated movie, sharp focus", scheduler: "p_sampler", prior_steps: "5", guidance_scale: 4, prior_cf_scale: 4, num_inference_steps: 100 } } ); // To access the file URL: console.log(output.url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Import the client:import replicate
Run ai-forever/kandinsky-2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "ai-forever/kandinsky-2:65a15f6e3c538ee4adf5142411455308926714f7d3f5c940d9f7bc519e0e5c1a", input={ "prompt": "a film still of a cute bird in a tree from a 2.5d animated movie, sharp focus", "scheduler": "p_sampler", "prior_steps": "5", "guidance_scale": 4, "prior_cf_scale": 4, "num_inference_steps": 100 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run ai-forever/kandinsky-2 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": "ai-forever/kandinsky-2:65a15f6e3c538ee4adf5142411455308926714f7d3f5c940d9f7bc519e0e5c1a", "input": { "prompt": "a film still of a cute bird in a tree from a 2.5d animated movie, sharp focus", "scheduler": "p_sampler", "prior_steps": "5", "guidance_scale": 4, "prior_cf_scale": 4, "num_inference_steps": 100 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-04-13T15:58:40.016477Z", "created_at": "2023-04-13T15:58:29.935324Z", "data_removed": false, "error": null, "id": "orhyygbpcngmjnf4hecr6kdiwm", "input": { "prompt": "a film still of a cute bird in a tree from a 2.5d animated movie, sharp focus", "scheduler": "p_sampler", "prior_steps": "5", "guidance_scale": 4, "prior_cf_scale": 4, "num_inference_steps": 100 }, "logs": "0%| | 0/100 [00:00<?, ?it/s]\n 2%|▏ | 2/100 [00:00<00:09, 10.88it/s]\n 4%|▍ | 4/100 [00:00<00:08, 10.95it/s]\n 6%|▌ | 6/100 [00:00<00:08, 11.17it/s]\n 8%|▊ | 8/100 [00:00<00:08, 11.40it/s]\n 10%|█ | 10/100 [00:00<00:07, 11.43it/s]\n 12%|█▏ | 12/100 [00:01<00:07, 11.51it/s]\n 14%|█▍ | 14/100 [00:01<00:07, 11.55it/s]\n 16%|█▌ | 16/100 [00:01<00:07, 11.54it/s]\n 18%|█▊ | 18/100 [00:01<00:07, 11.62it/s]\n 20%|██ | 20/100 [00:01<00:06, 11.67it/s]\n 22%|██▏ | 22/100 [00:01<00:06, 11.67it/s]\n 24%|██▍ | 24/100 [00:02<00:06, 11.64it/s]\n 26%|██▌ | 26/100 [00:02<00:06, 11.63it/s]\n 28%|██▊ | 28/100 [00:02<00:06, 11.56it/s]\n 30%|███ | 30/100 [00:02<00:06, 11.53it/s]\n 32%|███▏ | 32/100 [00:02<00:05, 11.53it/s]\n 34%|███▍ | 34/100 [00:02<00:05, 11.50it/s]\n 36%|███▌ | 36/100 [00:03<00:05, 11.44it/s]\n 38%|███▊ | 38/100 [00:03<00:05, 11.42it/s]\n 40%|████ | 40/100 [00:03<00:05, 11.40it/s]\n 42%|████▏ | 42/100 [00:03<00:05, 11.48it/s]\n 44%|████▍ | 44/100 [00:03<00:04, 11.56it/s]\n 46%|████▌ | 46/100 [00:03<00:04, 11.61it/s]\n 48%|████▊ | 48/100 [00:04<00:04, 11.61it/s]\n 50%|█████ | 50/100 [00:04<00:04, 11.57it/s]\n 52%|█████▏ | 52/100 [00:04<00:04, 11.59it/s]\n 54%|█████▍ | 54/100 [00:04<00:03, 11.62it/s]\n 56%|█████▌ | 56/100 [00:04<00:03, 11.49it/s]\n 58%|█████▊ | 58/100 [00:05<00:03, 11.56it/s]\n 60%|██████ | 60/100 [00:05<00:03, 11.59it/s]\n 62%|██████▏ | 62/100 [00:05<00:03, 11.58it/s]\n 64%|██████▍ | 64/100 [00:05<00:03, 11.58it/s]\n 66%|██████▌ | 66/100 [00:05<00:02, 11.67it/s]\n 68%|██████▊ | 68/100 [00:05<00:02, 11.73it/s]\n 70%|███████ | 70/100 [00:06<00:02, 11.71it/s]\n 72%|███████▏ | 72/100 [00:06<00:02, 11.73it/s]\n 74%|███████▍ | 74/100 [00:06<00:02, 11.60it/s]\n 76%|███████▌ | 76/100 [00:06<00:02, 11.57it/s]\n 78%|███████▊ | 78/100 [00:06<00:01, 11.61it/s]\n 80%|████████ | 80/100 [00:06<00:01, 11.61it/s]\n 82%|████████▏ | 82/100 [00:07<00:01, 11.66it/s]\n 84%|████████▍ | 84/100 [00:07<00:01, 11.67it/s]\n 86%|████████▌ | 86/100 [00:07<00:01, 11.60it/s]\n 88%|████████▊ | 88/100 [00:07<00:01, 11.54it/s]\n 90%|█████████ | 90/100 [00:07<00:00, 11.59it/s]\n 92%|█████████▏| 92/100 [00:07<00:00, 11.58it/s]\n 94%|█████████▍| 94/100 [00:08<00:00, 11.62it/s]\n 96%|█████████▌| 96/100 [00:08<00:00, 11.62it/s]\n 98%|█████████▊| 98/100 [00:08<00:00, 11.60it/s]\n100%|██████████| 100/100 [00:08<00:00, 11.64it/s]\n100%|██████████| 100/100 [00:08<00:00, 11.57it/s]", "metrics": { "predict_time": 9.964629, "total_time": 10.081153 }, "output": "https://replicate.delivery/pbxt/rINssGt0mxrlC5tAXq2o7LGVDBMLe1t1V4UMzSF83g1XxuYIA/out.png", "started_at": "2023-04-13T15:58:30.051848Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/orhyygbpcngmjnf4hecr6kdiwm", "cancel": "https://api.replicate.com/v1/predictions/orhyygbpcngmjnf4hecr6kdiwm/cancel" }, "version": "65a15f6e3c538ee4adf5142411455308926714f7d3f5c940d9f7bc519e0e5c1a" }
Generated in0%| | 0/100 [00:00<?, ?it/s] 2%|▏ | 2/100 [00:00<00:09, 10.88it/s] 4%|▍ | 4/100 [00:00<00:08, 10.95it/s] 6%|▌ | 6/100 [00:00<00:08, 11.17it/s] 8%|▊ | 8/100 [00:00<00:08, 11.40it/s] 10%|█ | 10/100 [00:00<00:07, 11.43it/s] 12%|█▏ | 12/100 [00:01<00:07, 11.51it/s] 14%|█▍ | 14/100 [00:01<00:07, 11.55it/s] 16%|█▌ | 16/100 [00:01<00:07, 11.54it/s] 18%|█▊ | 18/100 [00:01<00:07, 11.62it/s] 20%|██ | 20/100 [00:01<00:06, 11.67it/s] 22%|██▏ | 22/100 [00:01<00:06, 11.67it/s] 24%|██▍ | 24/100 [00:02<00:06, 11.64it/s] 26%|██▌ | 26/100 [00:02<00:06, 11.63it/s] 28%|██▊ | 28/100 [00:02<00:06, 11.56it/s] 30%|███ | 30/100 [00:02<00:06, 11.53it/s] 32%|███▏ | 32/100 [00:02<00:05, 11.53it/s] 34%|███▍ | 34/100 [00:02<00:05, 11.50it/s] 36%|███▌ | 36/100 [00:03<00:05, 11.44it/s] 38%|███▊ | 38/100 [00:03<00:05, 11.42it/s] 40%|████ | 40/100 [00:03<00:05, 11.40it/s] 42%|████▏ | 42/100 [00:03<00:05, 11.48it/s] 44%|████▍ | 44/100 [00:03<00:04, 11.56it/s] 46%|████▌ | 46/100 [00:03<00:04, 11.61it/s] 48%|████▊ | 48/100 [00:04<00:04, 11.61it/s] 50%|█████ | 50/100 [00:04<00:04, 11.57it/s] 52%|█████▏ | 52/100 [00:04<00:04, 11.59it/s] 54%|█████▍ | 54/100 [00:04<00:03, 11.62it/s] 56%|█████▌ | 56/100 [00:04<00:03, 11.49it/s] 58%|█████▊ | 58/100 [00:05<00:03, 11.56it/s] 60%|██████ | 60/100 [00:05<00:03, 11.59it/s] 62%|██████▏ | 62/100 [00:05<00:03, 11.58it/s] 64%|██████▍ | 64/100 [00:05<00:03, 11.58it/s] 66%|██████▌ | 66/100 [00:05<00:02, 11.67it/s] 68%|██████▊ | 68/100 [00:05<00:02, 11.73it/s] 70%|███████ | 70/100 [00:06<00:02, 11.71it/s] 72%|███████▏ | 72/100 [00:06<00:02, 11.73it/s] 74%|███████▍ | 74/100 [00:06<00:02, 11.60it/s] 76%|███████▌ | 76/100 [00:06<00:02, 11.57it/s] 78%|███████▊ | 78/100 [00:06<00:01, 11.61it/s] 80%|████████ | 80/100 [00:06<00:01, 11.61it/s] 82%|████████▏ | 82/100 [00:07<00:01, 11.66it/s] 84%|████████▍ | 84/100 [00:07<00:01, 11.67it/s] 86%|████████▌ | 86/100 [00:07<00:01, 11.60it/s] 88%|████████▊ | 88/100 [00:07<00:01, 11.54it/s] 90%|█████████ | 90/100 [00:07<00:00, 11.59it/s] 92%|█████████▏| 92/100 [00:07<00:00, 11.58it/s] 94%|█████████▍| 94/100 [00:08<00:00, 11.62it/s] 96%|█████████▌| 96/100 [00:08<00:00, 11.62it/s] 98%|█████████▊| 98/100 [00:08<00:00, 11.60it/s] 100%|██████████| 100/100 [00:08<00:00, 11.64it/s] 100%|██████████| 100/100 [00:08<00:00, 11.57it/s]
Prediction
ai-forever/kandinsky-2:65a15f6e3c538ee4adf5142411455308926714f7d3f5c940d9f7bc519e0e5c1aInput
- prompt
- a portrait photo of a woman in sunglasses, garden city, summer dress, street photography, detailed, 8k, morning, soft light, bokeh, cool tones, blue sky
- scheduler
- p_sampler
- prior_steps
- 5
- guidance_scale
- 4
- prior_cf_scale
- 4
- num_inference_steps
- 100
{ "prompt": "a portrait photo of a woman in sunglasses, garden city, summer dress, street photography, detailed, 8k, morning, soft light, bokeh, cool tones, blue sky", "scheduler": "p_sampler", "prior_steps": "5", "guidance_scale": 4, "prior_cf_scale": 4, "num_inference_steps": 100 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run ai-forever/kandinsky-2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "ai-forever/kandinsky-2:65a15f6e3c538ee4adf5142411455308926714f7d3f5c940d9f7bc519e0e5c1a", { input: { prompt: "a portrait photo of a woman in sunglasses, garden city, summer dress, street photography, detailed, 8k, morning, soft light, bokeh, cool tones, blue sky", scheduler: "p_sampler", prior_steps: "5", guidance_scale: 4, prior_cf_scale: 4, num_inference_steps: 100 } } ); // To access the file URL: console.log(output.url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Import the client:import replicate
Run ai-forever/kandinsky-2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "ai-forever/kandinsky-2:65a15f6e3c538ee4adf5142411455308926714f7d3f5c940d9f7bc519e0e5c1a", input={ "prompt": "a portrait photo of a woman in sunglasses, garden city, summer dress, street photography, detailed, 8k, morning, soft light, bokeh, cool tones, blue sky", "scheduler": "p_sampler", "prior_steps": "5", "guidance_scale": 4, "prior_cf_scale": 4, "num_inference_steps": 100 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run ai-forever/kandinsky-2 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": "ai-forever/kandinsky-2:65a15f6e3c538ee4adf5142411455308926714f7d3f5c940d9f7bc519e0e5c1a", "input": { "prompt": "a portrait photo of a woman in sunglasses, garden city, summer dress, street photography, detailed, 8k, morning, soft light, bokeh, cool tones, blue sky", "scheduler": "p_sampler", "prior_steps": "5", "guidance_scale": 4, "prior_cf_scale": 4, "num_inference_steps": 100 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-04-13T16:16:28.059383Z", "created_at": "2023-04-13T16:16:15.571639Z", "data_removed": false, "error": null, "id": "e5qdtqldyndinbujbovxwbujga", "input": { "prompt": "a portrait photo of a woman in sunglasses, garden city, summer dress, street photography, detailed, 8k, morning, soft light, bokeh, cool tones, blue sky", "scheduler": "p_sampler", "prior_steps": "5", "guidance_scale": 4, "prior_cf_scale": 4, "num_inference_steps": 100 }, "logs": "0%| | 0/100 [00:00<?, ?it/s]\n 2%|▏ | 2/100 [00:00<00:08, 11.01it/s]\n 4%|▍ | 4/100 [00:00<00:08, 11.41it/s]\n 6%|▌ | 6/100 [00:00<00:08, 11.57it/s]\n 8%|▊ | 8/100 [00:00<00:07, 11.63it/s]\n 10%|█ | 10/100 [00:00<00:07, 11.72it/s]\n 12%|█▏ | 12/100 [00:01<00:07, 11.76it/s]\n 14%|█▍ | 14/100 [00:01<00:07, 11.69it/s]\n 16%|█▌ | 16/100 [00:01<00:07, 11.50it/s]\n 18%|█▊ | 18/100 [00:01<00:07, 11.52it/s]\n 20%|██ | 20/100 [00:01<00:06, 11.53it/s]\n 22%|██▏ | 22/100 [00:01<00:06, 11.59it/s]\n 24%|██▍ | 24/100 [00:02<00:06, 11.59it/s]\n 26%|██▌ | 26/100 [00:02<00:06, 11.41it/s]\n 28%|██▊ | 28/100 [00:02<00:06, 11.49it/s]\n 30%|███ | 30/100 [00:02<00:06, 11.58it/s]\n 32%|███▏ | 32/100 [00:02<00:05, 11.64it/s]\n 34%|███▍ | 34/100 [00:02<00:05, 11.67it/s]\n 36%|███▌ | 36/100 [00:03<00:05, 11.69it/s]\n 38%|███▊ | 38/100 [00:03<00:05, 11.62it/s]\n 40%|████ | 40/100 [00:03<00:05, 11.59it/s]\n 42%|████▏ | 42/100 [00:03<00:04, 11.64it/s]\n 44%|████▍ | 44/100 [00:03<00:04, 11.68it/s]\n 46%|████▌ | 46/100 [00:03<00:04, 11.70it/s]\n 48%|████▊ | 48/100 [00:04<00:04, 11.61it/s]\n 50%|█████ | 50/100 [00:04<00:04, 11.60it/s]\n 52%|█████▏ | 52/100 [00:04<00:04, 11.64it/s]\n 54%|█████▍ | 54/100 [00:04<00:03, 11.68it/s]\n 56%|█████▌ | 56/100 [00:04<00:03, 11.70it/s]\n 58%|█████▊ | 58/100 [00:04<00:03, 11.72it/s]\n 60%|██████ | 60/100 [00:05<00:03, 11.67it/s]\n 62%|██████▏ | 62/100 [00:05<00:03, 11.67it/s]\n 64%|██████▍ | 64/100 [00:05<00:03, 11.69it/s]\n 66%|██████▌ | 66/100 [00:05<00:02, 11.72it/s]\n 68%|██████▊ | 68/100 [00:05<00:02, 11.73it/s]\n 70%|███████ | 70/100 [00:06<00:02, 11.74it/s]\n 72%|███████▏ | 72/100 [00:06<00:02, 11.69it/s]\n 74%|███████▍ | 74/100 [00:06<00:02, 11.59it/s]\n 76%|███████▌ | 76/100 [00:06<00:02, 11.61it/s]\n 78%|███████▊ | 78/100 [00:06<00:01, 11.61it/s]\n 80%|████████ | 80/100 [00:06<00:01, 11.65it/s]\n 82%|████████▏ | 82/100 [00:07<00:01, 11.52it/s]\n 84%|████████▍ | 84/100 [00:07<00:01, 11.49it/s]\n 86%|████████▌ | 86/100 [00:07<00:01, 11.54it/s]\n 88%|████████▊ | 88/100 [00:07<00:01, 11.57it/s]\n 90%|█████████ | 90/100 [00:07<00:00, 11.60it/s]\n 92%|█████████▏| 92/100 [00:07<00:00, 11.53it/s]\n 94%|█████████▍| 94/100 [00:08<00:00, 11.56it/s]\n 96%|█████████▌| 96/100 [00:08<00:00, 11.45it/s]\n 98%|█████████▊| 98/100 [00:08<00:00, 11.58it/s]\n100%|██████████| 100/100 [00:08<00:00, 11.65it/s]\n100%|██████████| 100/100 [00:08<00:00, 11.61it/s]", "metrics": { "predict_time": 9.883997, "total_time": 12.487744 }, "output": "https://replicate.delivery/pbxt/4uctuMgkSg7SJt8uaOuvGnSQmKkuEJlClh8pjkRTpc22cXME/out.png", "started_at": "2023-04-13T16:16:18.175386Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/e5qdtqldyndinbujbovxwbujga", "cancel": "https://api.replicate.com/v1/predictions/e5qdtqldyndinbujbovxwbujga/cancel" }, "version": "65a15f6e3c538ee4adf5142411455308926714f7d3f5c940d9f7bc519e0e5c1a" }
Generated in0%| | 0/100 [00:00<?, ?it/s] 2%|▏ | 2/100 [00:00<00:08, 11.01it/s] 4%|▍ | 4/100 [00:00<00:08, 11.41it/s] 6%|▌ | 6/100 [00:00<00:08, 11.57it/s] 8%|▊ | 8/100 [00:00<00:07, 11.63it/s] 10%|█ | 10/100 [00:00<00:07, 11.72it/s] 12%|█▏ | 12/100 [00:01<00:07, 11.76it/s] 14%|█▍ | 14/100 [00:01<00:07, 11.69it/s] 16%|█▌ | 16/100 [00:01<00:07, 11.50it/s] 18%|█▊ | 18/100 [00:01<00:07, 11.52it/s] 20%|██ | 20/100 [00:01<00:06, 11.53it/s] 22%|██▏ | 22/100 [00:01<00:06, 11.59it/s] 24%|██▍ | 24/100 [00:02<00:06, 11.59it/s] 26%|██▌ | 26/100 [00:02<00:06, 11.41it/s] 28%|██▊ | 28/100 [00:02<00:06, 11.49it/s] 30%|███ | 30/100 [00:02<00:06, 11.58it/s] 32%|███▏ | 32/100 [00:02<00:05, 11.64it/s] 34%|███▍ | 34/100 [00:02<00:05, 11.67it/s] 36%|███▌ | 36/100 [00:03<00:05, 11.69it/s] 38%|███▊ | 38/100 [00:03<00:05, 11.62it/s] 40%|████ | 40/100 [00:03<00:05, 11.59it/s] 42%|████▏ | 42/100 [00:03<00:04, 11.64it/s] 44%|████▍ | 44/100 [00:03<00:04, 11.68it/s] 46%|████▌ | 46/100 [00:03<00:04, 11.70it/s] 48%|████▊ | 48/100 [00:04<00:04, 11.61it/s] 50%|█████ | 50/100 [00:04<00:04, 11.60it/s] 52%|█████▏ | 52/100 [00:04<00:04, 11.64it/s] 54%|█████▍ | 54/100 [00:04<00:03, 11.68it/s] 56%|█████▌ | 56/100 [00:04<00:03, 11.70it/s] 58%|█████▊ | 58/100 [00:04<00:03, 11.72it/s] 60%|██████ | 60/100 [00:05<00:03, 11.67it/s] 62%|██████▏ | 62/100 [00:05<00:03, 11.67it/s] 64%|██████▍ | 64/100 [00:05<00:03, 11.69it/s] 66%|██████▌ | 66/100 [00:05<00:02, 11.72it/s] 68%|██████▊ | 68/100 [00:05<00:02, 11.73it/s] 70%|███████ | 70/100 [00:06<00:02, 11.74it/s] 72%|███████▏ | 72/100 [00:06<00:02, 11.69it/s] 74%|███████▍ | 74/100 [00:06<00:02, 11.59it/s] 76%|███████▌ | 76/100 [00:06<00:02, 11.61it/s] 78%|███████▊ | 78/100 [00:06<00:01, 11.61it/s] 80%|████████ | 80/100 [00:06<00:01, 11.65it/s] 82%|████████▏ | 82/100 [00:07<00:01, 11.52it/s] 84%|████████▍ | 84/100 [00:07<00:01, 11.49it/s] 86%|████████▌ | 86/100 [00:07<00:01, 11.54it/s] 88%|████████▊ | 88/100 [00:07<00:01, 11.57it/s] 90%|█████████ | 90/100 [00:07<00:00, 11.60it/s] 92%|█████████▏| 92/100 [00:07<00:00, 11.53it/s] 94%|█████████▍| 94/100 [00:08<00:00, 11.56it/s] 96%|█████████▌| 96/100 [00:08<00:00, 11.45it/s] 98%|█████████▊| 98/100 [00:08<00:00, 11.58it/s] 100%|██████████| 100/100 [00:08<00:00, 11.65it/s] 100%|██████████| 100/100 [00:08<00:00, 11.61it/s]
Prediction
ai-forever/kandinsky-2:65a15f6e3c538ee4adf5142411455308926714f7d3f5c940d9f7bc519e0e5c1aInput
- prompt
- An illustration of a quaint garden, watercolor, green and blue, white background
- scheduler
- p_sampler
- prior_steps
- 5
- guidance_scale
- 4
- prior_cf_scale
- 4
- num_inference_steps
- 100
{ "prompt": "An illustration of a quaint garden, watercolor, green and blue, white background", "scheduler": "p_sampler", "prior_steps": "5", "guidance_scale": 4, "prior_cf_scale": 4, "num_inference_steps": 100 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run ai-forever/kandinsky-2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "ai-forever/kandinsky-2:65a15f6e3c538ee4adf5142411455308926714f7d3f5c940d9f7bc519e0e5c1a", { input: { prompt: "An illustration of a quaint garden, watercolor, green and blue, white background", scheduler: "p_sampler", prior_steps: "5", guidance_scale: 4, prior_cf_scale: 4, num_inference_steps: 100 } } ); // To access the file URL: console.log(output.url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Import the client:import replicate
Run ai-forever/kandinsky-2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "ai-forever/kandinsky-2:65a15f6e3c538ee4adf5142411455308926714f7d3f5c940d9f7bc519e0e5c1a", input={ "prompt": "An illustration of a quaint garden, watercolor, green and blue, white background", "scheduler": "p_sampler", "prior_steps": "5", "guidance_scale": 4, "prior_cf_scale": 4, "num_inference_steps": 100 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run ai-forever/kandinsky-2 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": "ai-forever/kandinsky-2:65a15f6e3c538ee4adf5142411455308926714f7d3f5c940d9f7bc519e0e5c1a", "input": { "prompt": "An illustration of a quaint garden, watercolor, green and blue, white background", "scheduler": "p_sampler", "prior_steps": "5", "guidance_scale": 4, "prior_cf_scale": 4, "num_inference_steps": 100 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-04-13T16:38:55.327879Z", "created_at": "2023-04-13T16:38:25.761784Z", "data_removed": false, "error": null, "id": "u225e7n6kvfy7dee4j4rwcx4aq", "input": { "prompt": "An illustration of a quaint garden, watercolor, green and blue, white background", "scheduler": "p_sampler", "prior_steps": "5", "guidance_scale": 4, "prior_cf_scale": 4, "num_inference_steps": 100 }, "logs": "0%| | 0/100 [00:00<?, ?it/s]\n 2%|▏ | 2/100 [00:00<00:08, 11.83it/s]\n 4%|▍ | 4/100 [00:00<00:08, 11.88it/s]\n 6%|▌ | 6/100 [00:00<00:08, 11.63it/s]\n 8%|▊ | 8/100 [00:00<00:07, 11.69it/s]\n 10%|█ | 10/100 [00:00<00:07, 11.72it/s]\n 12%|█▏ | 12/100 [00:01<00:07, 11.79it/s]\n 14%|█▍ | 14/100 [00:01<00:07, 11.86it/s]\n 16%|█▌ | 16/100 [00:01<00:07, 11.90it/s]\n 18%|█▊ | 18/100 [00:01<00:06, 11.95it/s]\n 20%|██ | 20/100 [00:01<00:06, 11.98it/s]\n 22%|██▏ | 22/100 [00:01<00:06, 11.89it/s]\n 24%|██▍ | 24/100 [00:02<00:06, 11.91it/s]\n 26%|██▌ | 26/100 [00:02<00:06, 11.92it/s]\n 28%|██▊ | 28/100 [00:02<00:06, 11.94it/s]\n 30%|███ | 30/100 [00:02<00:05, 11.98it/s]\n 32%|███▏ | 32/100 [00:02<00:05, 11.98it/s]\n 34%|███▍ | 34/100 [00:02<00:05, 11.96it/s]\n 36%|███▌ | 36/100 [00:03<00:05, 12.02it/s]\n 38%|███▊ | 38/100 [00:03<00:05, 12.05it/s]\n 40%|████ | 40/100 [00:03<00:04, 12.06it/s]\n 42%|████▏ | 42/100 [00:03<00:04, 12.05it/s]\n 44%|████▍ | 44/100 [00:03<00:04, 12.04it/s]\n 46%|████▌ | 46/100 [00:03<00:04, 11.98it/s]\n 48%|████▊ | 48/100 [00:04<00:04, 12.04it/s]\n 50%|█████ | 50/100 [00:04<00:04, 12.08it/s]\n 52%|█████▏ | 52/100 [00:04<00:03, 12.06it/s]\n 54%|█████▍ | 54/100 [00:04<00:03, 12.05it/s]\n 56%|█████▌ | 56/100 [00:04<00:03, 12.00it/s]\n 58%|█████▊ | 58/100 [00:04<00:03, 11.97it/s]\n 60%|██████ | 60/100 [00:05<00:03, 11.99it/s]\n 62%|██████▏ | 62/100 [00:05<00:03, 12.02it/s]\n 64%|██████▍ | 64/100 [00:05<00:02, 12.05it/s]\n 66%|██████▌ | 66/100 [00:05<00:02, 12.07it/s]\n 68%|██████▊ | 68/100 [00:05<00:02, 12.02it/s]\n 70%|███████ | 70/100 [00:05<00:02, 11.95it/s]\n 72%|███████▏ | 72/100 [00:06<00:02, 11.93it/s]\n 74%|███████▍ | 74/100 [00:06<00:02, 11.92it/s]\n 76%|███████▌ | 76/100 [00:06<00:02, 11.96it/s]\n 78%|███████▊ | 78/100 [00:06<00:01, 12.00it/s]\n 80%|████████ | 80/100 [00:06<00:01, 11.99it/s]\n 82%|████████▏ | 82/100 [00:06<00:01, 11.95it/s]\n 84%|████████▍ | 84/100 [00:07<00:01, 11.99it/s]\n 86%|████████▌ | 86/100 [00:07<00:01, 11.99it/s]\n 88%|████████▊ | 88/100 [00:07<00:00, 12.00it/s]\n 90%|█████████ | 90/100 [00:07<00:00, 12.03it/s]\n 92%|█████████▏| 92/100 [00:07<00:00, 12.01it/s]\n 94%|█████████▍| 94/100 [00:07<00:00, 11.89it/s]\n 96%|█████████▌| 96/100 [00:08<00:00, 11.94it/s]\n 98%|█████████▊| 98/100 [00:08<00:00, 11.94it/s]\n100%|██████████| 100/100 [00:08<00:00, 11.90it/s]\n100%|██████████| 100/100 [00:08<00:00, 11.96it/s]", "metrics": { "predict_time": 9.455861, "total_time": 29.566095 }, "output": "https://replicate.delivery/pbxt/jopPv3SSXgorLlN3wuQqsQJUtKetMfiGvyQ1e43d4wi9Q8ihA/out.png", "started_at": "2023-04-13T16:38:45.872018Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/u225e7n6kvfy7dee4j4rwcx4aq", "cancel": "https://api.replicate.com/v1/predictions/u225e7n6kvfy7dee4j4rwcx4aq/cancel" }, "version": "65a15f6e3c538ee4adf5142411455308926714f7d3f5c940d9f7bc519e0e5c1a" }
Generated in0%| | 0/100 [00:00<?, ?it/s] 2%|▏ | 2/100 [00:00<00:08, 11.83it/s] 4%|▍ | 4/100 [00:00<00:08, 11.88it/s] 6%|▌ | 6/100 [00:00<00:08, 11.63it/s] 8%|▊ | 8/100 [00:00<00:07, 11.69it/s] 10%|█ | 10/100 [00:00<00:07, 11.72it/s] 12%|█▏ | 12/100 [00:01<00:07, 11.79it/s] 14%|█▍ | 14/100 [00:01<00:07, 11.86it/s] 16%|█▌ | 16/100 [00:01<00:07, 11.90it/s] 18%|█▊ | 18/100 [00:01<00:06, 11.95it/s] 20%|██ | 20/100 [00:01<00:06, 11.98it/s] 22%|██▏ | 22/100 [00:01<00:06, 11.89it/s] 24%|██▍ | 24/100 [00:02<00:06, 11.91it/s] 26%|██▌ | 26/100 [00:02<00:06, 11.92it/s] 28%|██▊ | 28/100 [00:02<00:06, 11.94it/s] 30%|███ | 30/100 [00:02<00:05, 11.98it/s] 32%|███▏ | 32/100 [00:02<00:05, 11.98it/s] 34%|███▍ | 34/100 [00:02<00:05, 11.96it/s] 36%|███▌ | 36/100 [00:03<00:05, 12.02it/s] 38%|███▊ | 38/100 [00:03<00:05, 12.05it/s] 40%|████ | 40/100 [00:03<00:04, 12.06it/s] 42%|████▏ | 42/100 [00:03<00:04, 12.05it/s] 44%|████▍ | 44/100 [00:03<00:04, 12.04it/s] 46%|████▌ | 46/100 [00:03<00:04, 11.98it/s] 48%|████▊ | 48/100 [00:04<00:04, 12.04it/s] 50%|█████ | 50/100 [00:04<00:04, 12.08it/s] 52%|█████▏ | 52/100 [00:04<00:03, 12.06it/s] 54%|█████▍ | 54/100 [00:04<00:03, 12.05it/s] 56%|█████▌ | 56/100 [00:04<00:03, 12.00it/s] 58%|█████▊ | 58/100 [00:04<00:03, 11.97it/s] 60%|██████ | 60/100 [00:05<00:03, 11.99it/s] 62%|██████▏ | 62/100 [00:05<00:03, 12.02it/s] 64%|██████▍ | 64/100 [00:05<00:02, 12.05it/s] 66%|██████▌ | 66/100 [00:05<00:02, 12.07it/s] 68%|██████▊ | 68/100 [00:05<00:02, 12.02it/s] 70%|███████ | 70/100 [00:05<00:02, 11.95it/s] 72%|███████▏ | 72/100 [00:06<00:02, 11.93it/s] 74%|███████▍ | 74/100 [00:06<00:02, 11.92it/s] 76%|███████▌ | 76/100 [00:06<00:02, 11.96it/s] 78%|███████▊ | 78/100 [00:06<00:01, 12.00it/s] 80%|████████ | 80/100 [00:06<00:01, 11.99it/s] 82%|████████▏ | 82/100 [00:06<00:01, 11.95it/s] 84%|████████▍ | 84/100 [00:07<00:01, 11.99it/s] 86%|████████▌ | 86/100 [00:07<00:01, 11.99it/s] 88%|████████▊ | 88/100 [00:07<00:00, 12.00it/s] 90%|█████████ | 90/100 [00:07<00:00, 12.03it/s] 92%|█████████▏| 92/100 [00:07<00:00, 12.01it/s] 94%|█████████▍| 94/100 [00:07<00:00, 11.89it/s] 96%|█████████▌| 96/100 [00:08<00:00, 11.94it/s] 98%|█████████▊| 98/100 [00:08<00:00, 11.94it/s] 100%|██████████| 100/100 [00:08<00:00, 11.90it/s] 100%|██████████| 100/100 [00:08<00:00, 11.96it/s]
Want to make some of these yourself?
Run this model