lucataco / omnigen2
OmniGen2: a powerful and efficient unified multimodal model
Prediction
lucataco/omnigen2:5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502eIDdq4hgj1dc9rm80cqn1n88maknrStatusSucceededSourceWebHardwareL40STotal durationCreatedInput
- seed
- -1
- width
- 1024
- height
- 1024
- prompt
- Change the dress to blue
- scheduler
- euler
- max_pixels
- 1048576
- cfg_range_end
- 1
- cfg_range_start
- 0
- negative_prompt
- (((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar
- num_inference_steps
- 50
- text_guidance_scale
- 5
- image_guidance_scale
- 2
- max_input_image_side_length
- 2048
{ "seed": -1, "image": "https://replicate.delivery/pbxt/NFVLgKWVv48pYj7p8qCnKpeYDN5S46MlxYNaIEzRu03KG1xJ/yellow-dress.png", "width": 1024, "height": 1024, "prompt": "Change the dress to blue", "scheduler": "euler", "max_pixels": 1048576, "cfg_range_end": 1, "cfg_range_start": 0, "negative_prompt": "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar", "num_inference_steps": 50, "text_guidance_scale": 5, "image_guidance_scale": 2, "max_input_image_side_length": 2048 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run lucataco/omnigen2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/omnigen2:5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502e", { input: { seed: -1, image: "https://replicate.delivery/pbxt/NFVLgKWVv48pYj7p8qCnKpeYDN5S46MlxYNaIEzRu03KG1xJ/yellow-dress.png", width: 1024, height: 1024, prompt: "Change the dress to blue", scheduler: "euler", max_pixels: 1048576, cfg_range_end: 1, cfg_range_start: 0, negative_prompt: "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar", num_inference_steps: 50, text_guidance_scale: 5, image_guidance_scale: 2, max_input_image_side_length: 2048 } } ); // 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 lucataco/omnigen2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/omnigen2:5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502e", input={ "seed": -1, "image": "https://replicate.delivery/pbxt/NFVLgKWVv48pYj7p8qCnKpeYDN5S46MlxYNaIEzRu03KG1xJ/yellow-dress.png", "width": 1024, "height": 1024, "prompt": "Change the dress to blue", "scheduler": "euler", "max_pixels": 1048576, "cfg_range_end": 1, "cfg_range_start": 0, "negative_prompt": "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar", "num_inference_steps": 50, "text_guidance_scale": 5, "image_guidance_scale": 2, "max_input_image_side_length": 2048 } ) # To access the file URL: print(output.url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output.read())
To learn more, take a look at the guide on getting started with Python.
Run lucataco/omnigen2 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": "lucataco/omnigen2:5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502e", "input": { "seed": -1, "image": "https://replicate.delivery/pbxt/NFVLgKWVv48pYj7p8qCnKpeYDN5S46MlxYNaIEzRu03KG1xJ/yellow-dress.png", "width": 1024, "height": 1024, "prompt": "Change the dress to blue", "scheduler": "euler", "max_pixels": 1048576, "cfg_range_end": 1, "cfg_range_start": 0, "negative_prompt": "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar", "num_inference_steps": 50, "text_guidance_scale": 5, "image_guidance_scale": 2, "max_input_image_side_length": 2048 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cog
If you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/lucataco/omnigen2@sha256:5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502e \ -i 'seed=-1' \ -i 'image="https://replicate.delivery/pbxt/NFVLgKWVv48pYj7p8qCnKpeYDN5S46MlxYNaIEzRu03KG1xJ/yellow-dress.png"' \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="Change the dress to blue"' \ -i 'scheduler="euler"' \ -i 'max_pixels=1048576' \ -i 'cfg_range_end=1' \ -i 'cfg_range_start=0' \ -i 'negative_prompt="(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar"' \ -i 'num_inference_steps=50' \ -i 'text_guidance_scale=5' \ -i 'image_guidance_scale=2' \ -i 'max_input_image_side_length=2048'
To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/lucataco/omnigen2@sha256:5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502e
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "seed": -1, "image": "https://replicate.delivery/pbxt/NFVLgKWVv48pYj7p8qCnKpeYDN5S46MlxYNaIEzRu03KG1xJ/yellow-dress.png", "width": 1024, "height": 1024, "prompt": "Change the dress to blue", "scheduler": "euler", "max_pixels": 1048576, "cfg_range_end": 1, "cfg_range_start": 0, "negative_prompt": "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar", "num_inference_steps": 50, "text_guidance_scale": 5, "image_guidance_scale": 2, "max_input_image_side_length": 2048 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2025-06-25T18:50:20.838828Z", "created_at": "2025-06-25T18:47:00.194000Z", "data_removed": false, "error": null, "id": "dq4hgj1dc9rm80cqn1n88maknr", "input": { "seed": -1, "image": "https://replicate.delivery/pbxt/NFVLgKWVv48pYj7p8qCnKpeYDN5S46MlxYNaIEzRu03KG1xJ/yellow-dress.png", "width": 1024, "height": 1024, "prompt": "Change the dress to blue", "scheduler": "euler", "max_pixels": 1048576, "cfg_range_end": 1, "cfg_range_start": 0, "negative_prompt": "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar", "num_inference_steps": 50, "text_guidance_scale": 5, "image_guidance_scale": 2, "max_input_image_side_length": 2048 }, "logs": "0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:05<04:53, 5.99s/it]\n 4%|▍ | 2/50 [00:07<02:42, 3.39s/it]\n 6%|▌ | 3/50 [00:09<02:03, 2.64s/it]\n 8%|▊ | 4/50 [00:11<01:44, 2.28s/it]\n 10%|█ | 5/50 [00:12<01:33, 2.08s/it]\n 12%|█▏ | 6/50 [00:14<01:26, 1.97s/it]\n 14%|█▍ | 7/50 [00:16<01:21, 1.89s/it]\n 16%|█▌ | 8/50 [00:17<01:17, 1.84s/it]\n 18%|█▊ | 9/50 [00:19<01:14, 1.81s/it]\n 20%|██ | 10/50 [00:21<01:11, 1.79s/it]\n 22%|██▏ | 11/50 [00:23<01:09, 1.78s/it]\n 24%|██▍ | 12/50 [00:24<01:07, 1.77s/it]\n 26%|██▌ | 13/50 [00:26<01:05, 1.76s/it]\n 28%|██▊ | 14/50 [00:28<01:03, 1.76s/it]\n 30%|███ | 15/50 [00:30<01:01, 1.76s/it]\n 32%|███▏ | 16/50 [00:31<00:59, 1.75s/it]\n 34%|███▍ | 17/50 [00:33<00:57, 1.75s/it]\n 36%|███▌ | 18/50 [00:35<00:56, 1.75s/it]\n 38%|███▊ | 19/50 [00:37<00:54, 1.75s/it]\n 40%|████ | 20/50 [00:38<00:52, 1.75s/it]\n 42%|████▏ | 21/50 [00:40<00:50, 1.76s/it]\n 44%|████▍ | 22/50 [00:42<00:49, 1.76s/it]\n 46%|████▌ | 23/50 [00:44<00:47, 1.76s/it]\n 48%|████▊ | 24/50 [00:46<00:45, 1.76s/it]\n 50%|█████ | 25/50 [00:47<00:44, 1.76s/it]\n 52%|█████▏ | 26/50 [00:49<00:42, 1.76s/it]\n 54%|█████▍ | 27/50 [00:51<00:40, 1.76s/it]\n 56%|█████▌ | 28/50 [00:53<00:38, 1.76s/it]\n 58%|█████▊ | 29/50 [00:54<00:37, 1.76s/it]\n 60%|██████ | 30/50 [00:56<00:35, 1.76s/it]\n 62%|██████▏ | 31/50 [00:58<00:33, 1.77s/it]\n 64%|██████▍ | 32/50 [01:00<00:31, 1.77s/it]\n 66%|██████▌ | 33/50 [01:01<00:29, 1.76s/it]\n 68%|██████▊ | 34/50 [01:03<00:28, 1.76s/it]\n 70%|███████ | 35/50 [01:05<00:26, 1.76s/it]\n 72%|███████▏ | 36/50 [01:07<00:24, 1.76s/it]\n 74%|███████▍ | 37/50 [01:08<00:22, 1.76s/it]\n 76%|███████▌ | 38/50 [01:10<00:21, 1.76s/it]\n 78%|███████▊ | 39/50 [01:12<00:19, 1.76s/it]\n 80%|████████ | 40/50 [01:14<00:17, 1.76s/it]\n 82%|████████▏ | 41/50 [01:16<00:15, 1.76s/it]\n 84%|████████▍ | 42/50 [01:17<00:14, 1.76s/it]\n 86%|████████▌ | 43/50 [01:19<00:12, 1.76s/it]\n 88%|████████▊ | 44/50 [01:21<00:10, 1.76s/it]\n 90%|█████████ | 45/50 [01:23<00:08, 1.77s/it]\n 92%|█████████▏| 46/50 [01:24<00:07, 1.77s/it]\n 94%|█████████▍| 47/50 [01:26<00:05, 1.77s/it]\n 96%|█████████▌| 48/50 [01:28<00:03, 1.77s/it]\n 98%|█████████▊| 49/50 [01:30<00:01, 1.77s/it]\n100%|██████████| 50/50 [01:31<00:00, 1.77s/it]\n100%|██████████| 50/50 [01:31<00:00, 1.84s/it]", "metrics": { "predict_time": 93.168549308, "total_time": 200.644828 }, "output": "https://replicate.delivery/xezq/LcruS1mlR0p3NtjxKRJ8YZYMY2iZE1ro7drQKlKEiUI72nOF/output.png", "started_at": "2025-06-25T18:48:47.670279Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bcwr-osa6tqhwteevseuajcjngoz2to3lwzqz2oewg5mfwituui3aeevq", "get": "https://api.replicate.com/v1/predictions/dq4hgj1dc9rm80cqn1n88maknr", "cancel": "https://api.replicate.com/v1/predictions/dq4hgj1dc9rm80cqn1n88maknr/cancel" }, "version": "5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502e" }
Generated in0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:05<04:53, 5.99s/it] 4%|▍ | 2/50 [00:07<02:42, 3.39s/it] 6%|▌ | 3/50 [00:09<02:03, 2.64s/it] 8%|▊ | 4/50 [00:11<01:44, 2.28s/it] 10%|█ | 5/50 [00:12<01:33, 2.08s/it] 12%|█▏ | 6/50 [00:14<01:26, 1.97s/it] 14%|█▍ | 7/50 [00:16<01:21, 1.89s/it] 16%|█▌ | 8/50 [00:17<01:17, 1.84s/it] 18%|█▊ | 9/50 [00:19<01:14, 1.81s/it] 20%|██ | 10/50 [00:21<01:11, 1.79s/it] 22%|██▏ | 11/50 [00:23<01:09, 1.78s/it] 24%|██▍ | 12/50 [00:24<01:07, 1.77s/it] 26%|██▌ | 13/50 [00:26<01:05, 1.76s/it] 28%|██▊ | 14/50 [00:28<01:03, 1.76s/it] 30%|███ | 15/50 [00:30<01:01, 1.76s/it] 32%|███▏ | 16/50 [00:31<00:59, 1.75s/it] 34%|███▍ | 17/50 [00:33<00:57, 1.75s/it] 36%|███▌ | 18/50 [00:35<00:56, 1.75s/it] 38%|███▊ | 19/50 [00:37<00:54, 1.75s/it] 40%|████ | 20/50 [00:38<00:52, 1.75s/it] 42%|████▏ | 21/50 [00:40<00:50, 1.76s/it] 44%|████▍ | 22/50 [00:42<00:49, 1.76s/it] 46%|████▌ | 23/50 [00:44<00:47, 1.76s/it] 48%|████▊ | 24/50 [00:46<00:45, 1.76s/it] 50%|█████ | 25/50 [00:47<00:44, 1.76s/it] 52%|█████▏ | 26/50 [00:49<00:42, 1.76s/it] 54%|█████▍ | 27/50 [00:51<00:40, 1.76s/it] 56%|█████▌ | 28/50 [00:53<00:38, 1.76s/it] 58%|█████▊ | 29/50 [00:54<00:37, 1.76s/it] 60%|██████ | 30/50 [00:56<00:35, 1.76s/it] 62%|██████▏ | 31/50 [00:58<00:33, 1.77s/it] 64%|██████▍ | 32/50 [01:00<00:31, 1.77s/it] 66%|██████▌ | 33/50 [01:01<00:29, 1.76s/it] 68%|██████▊ | 34/50 [01:03<00:28, 1.76s/it] 70%|███████ | 35/50 [01:05<00:26, 1.76s/it] 72%|███████▏ | 36/50 [01:07<00:24, 1.76s/it] 74%|███████▍ | 37/50 [01:08<00:22, 1.76s/it] 76%|███████▌ | 38/50 [01:10<00:21, 1.76s/it] 78%|███████▊ | 39/50 [01:12<00:19, 1.76s/it] 80%|████████ | 40/50 [01:14<00:17, 1.76s/it] 82%|████████▏ | 41/50 [01:16<00:15, 1.76s/it] 84%|████████▍ | 42/50 [01:17<00:14, 1.76s/it] 86%|████████▌ | 43/50 [01:19<00:12, 1.76s/it] 88%|████████▊ | 44/50 [01:21<00:10, 1.76s/it] 90%|█████████ | 45/50 [01:23<00:08, 1.77s/it] 92%|█████████▏| 46/50 [01:24<00:07, 1.77s/it] 94%|█████████▍| 47/50 [01:26<00:05, 1.77s/it] 96%|█████████▌| 48/50 [01:28<00:03, 1.77s/it] 98%|█████████▊| 49/50 [01:30<00:01, 1.77s/it] 100%|██████████| 50/50 [01:31<00:00, 1.77s/it] 100%|██████████| 50/50 [01:31<00:00, 1.84s/it]
Prediction
lucataco/omnigen2:5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502eIDcf85e2yvb9rmc0cqn1pv28d868StatusSucceededSourceWebHardwareL40STotal durationCreatedInput
- seed
- -1
- width
- 1024
- height
- 1024
- prompt
- Generate a photo of an anime-style figurine placed on a desk. The figurine model should be based on the character photo provided in the attachment, accurately replicating the full-body pose, facial expression, and clothing style of the character in the photo, ensuring the entire figurine is fully presented. The overall design should be exquisite and detailed, soft gradient colors and a delicate texture, leaning towards a Japanese anime style, rich in details, with a realistic quality and beautiful visual appeal.
- scheduler
- euler
- max_pixels
- 1048576
- cfg_range_end
- 1
- cfg_range_start
- 0
- negative_prompt
- (((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar
- num_inference_steps
- 50
- text_guidance_scale
- 5
- image_guidance_scale
- 2
- max_input_image_side_length
- 2048
{ "seed": -1, "image": "https://replicate.delivery/pbxt/NFVPVUbcOTItiJCJrlnVpOVJpb9IaMQF5KJNpotYouJ0vAhh/woman-gloss.JPG", "width": 1024, "height": 1024, "prompt": "Generate a photo of an anime-style figurine placed on a desk. The figurine model should be based on the character photo provided in the attachment, accurately replicating the full-body pose, facial expression, and clothing style of the character in the photo, ensuring the entire figurine is fully presented. The overall design should be exquisite and detailed, soft gradient colors and a delicate texture, leaning towards a Japanese anime style, rich in details, with a realistic quality and beautiful visual appeal.", "scheduler": "euler", "max_pixels": 1048576, "cfg_range_end": 1, "cfg_range_start": 0, "negative_prompt": "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar", "num_inference_steps": 50, "text_guidance_scale": 5, "image_guidance_scale": 2, "max_input_image_side_length": 2048 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run lucataco/omnigen2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/omnigen2:5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502e", { input: { seed: -1, image: "https://replicate.delivery/pbxt/NFVPVUbcOTItiJCJrlnVpOVJpb9IaMQF5KJNpotYouJ0vAhh/woman-gloss.JPG", width: 1024, height: 1024, prompt: "Generate a photo of an anime-style figurine placed on a desk. The figurine model should be based on the character photo provided in the attachment, accurately replicating the full-body pose, facial expression, and clothing style of the character in the photo, ensuring the entire figurine is fully presented. The overall design should be exquisite and detailed, soft gradient colors and a delicate texture, leaning towards a Japanese anime style, rich in details, with a realistic quality and beautiful visual appeal.", scheduler: "euler", max_pixels: 1048576, cfg_range_end: 1, cfg_range_start: 0, negative_prompt: "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar", num_inference_steps: 50, text_guidance_scale: 5, image_guidance_scale: 2, max_input_image_side_length: 2048 } } ); // 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 lucataco/omnigen2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/omnigen2:5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502e", input={ "seed": -1, "image": "https://replicate.delivery/pbxt/NFVPVUbcOTItiJCJrlnVpOVJpb9IaMQF5KJNpotYouJ0vAhh/woman-gloss.JPG", "width": 1024, "height": 1024, "prompt": "Generate a photo of an anime-style figurine placed on a desk. The figurine model should be based on the character photo provided in the attachment, accurately replicating the full-body pose, facial expression, and clothing style of the character in the photo, ensuring the entire figurine is fully presented. The overall design should be exquisite and detailed, soft gradient colors and a delicate texture, leaning towards a Japanese anime style, rich in details, with a realistic quality and beautiful visual appeal.", "scheduler": "euler", "max_pixels": 1048576, "cfg_range_end": 1, "cfg_range_start": 0, "negative_prompt": "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar", "num_inference_steps": 50, "text_guidance_scale": 5, "image_guidance_scale": 2, "max_input_image_side_length": 2048 } ) # To access the file URL: print(output.url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output.read())
To learn more, take a look at the guide on getting started with Python.
Run lucataco/omnigen2 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": "lucataco/omnigen2:5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502e", "input": { "seed": -1, "image": "https://replicate.delivery/pbxt/NFVPVUbcOTItiJCJrlnVpOVJpb9IaMQF5KJNpotYouJ0vAhh/woman-gloss.JPG", "width": 1024, "height": 1024, "prompt": "Generate a photo of an anime-style figurine placed on a desk. The figurine model should be based on the character photo provided in the attachment, accurately replicating the full-body pose, facial expression, and clothing style of the character in the photo, ensuring the entire figurine is fully presented. The overall design should be exquisite and detailed, soft gradient colors and a delicate texture, leaning towards a Japanese anime style, rich in details, with a realistic quality and beautiful visual appeal.", "scheduler": "euler", "max_pixels": 1048576, "cfg_range_end": 1, "cfg_range_start": 0, "negative_prompt": "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar", "num_inference_steps": 50, "text_guidance_scale": 5, "image_guidance_scale": 2, "max_input_image_side_length": 2048 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cog
If you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/lucataco/omnigen2@sha256:5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502e \ -i 'seed=-1' \ -i 'image="https://replicate.delivery/pbxt/NFVPVUbcOTItiJCJrlnVpOVJpb9IaMQF5KJNpotYouJ0vAhh/woman-gloss.JPG"' \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="Generate a photo of an anime-style figurine placed on a desk. The figurine model should be based on the character photo provided in the attachment, accurately replicating the full-body pose, facial expression, and clothing style of the character in the photo, ensuring the entire figurine is fully presented. The overall design should be exquisite and detailed, soft gradient colors and a delicate texture, leaning towards a Japanese anime style, rich in details, with a realistic quality and beautiful visual appeal."' \ -i 'scheduler="euler"' \ -i 'max_pixels=1048576' \ -i 'cfg_range_end=1' \ -i 'cfg_range_start=0' \ -i 'negative_prompt="(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar"' \ -i 'num_inference_steps=50' \ -i 'text_guidance_scale=5' \ -i 'image_guidance_scale=2' \ -i 'max_input_image_side_length=2048'
To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/lucataco/omnigen2@sha256:5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502e
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "seed": -1, "image": "https://replicate.delivery/pbxt/NFVPVUbcOTItiJCJrlnVpOVJpb9IaMQF5KJNpotYouJ0vAhh/woman-gloss.JPG", "width": 1024, "height": 1024, "prompt": "Generate a photo of an anime-style figurine placed on a desk. The figurine model should be based on the character photo provided in the attachment, accurately replicating the full-body pose, facial expression, and clothing style of the character in the photo, ensuring the entire figurine is fully presented. The overall design should be exquisite and detailed, soft gradient colors and a delicate texture, leaning towards a Japanese anime style, rich in details, with a realistic quality and beautiful visual appeal.", "scheduler": "euler", "max_pixels": 1048576, "cfg_range_end": 1, "cfg_range_start": 0, "negative_prompt": "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar", "num_inference_steps": 50, "text_guidance_scale": 5, "image_guidance_scale": 2, "max_input_image_side_length": 2048 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2025-06-25T18:52:31.468005Z", "created_at": "2025-06-25T18:51:01.338000Z", "data_removed": false, "error": null, "id": "cf85e2yvb9rmc0cqn1pv28d868", "input": { "seed": -1, "image": "https://replicate.delivery/pbxt/NFVPVUbcOTItiJCJrlnVpOVJpb9IaMQF5KJNpotYouJ0vAhh/woman-gloss.JPG", "width": 1024, "height": 1024, "prompt": "Generate a photo of an anime-style figurine placed on a desk. The figurine model should be based on the character photo provided in the attachment, accurately replicating the full-body pose, facial expression, and clothing style of the character in the photo, ensuring the entire figurine is fully presented. The overall design should be exquisite and detailed, soft gradient colors and a delicate texture, leaning towards a Japanese anime style, rich in details, with a realistic quality and beautiful visual appeal.", "scheduler": "euler", "max_pixels": 1048576, "cfg_range_end": 1, "cfg_range_start": 0, "negative_prompt": "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar", "num_inference_steps": 50, "text_guidance_scale": 5, "image_guidance_scale": 2, "max_input_image_side_length": 2048 }, "logs": "0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:01<01:26, 1.77s/it]\n 4%|▍ | 2/50 [00:03<01:20, 1.68s/it]\n 6%|▌ | 3/50 [00:05<01:20, 1.72s/it]\n 8%|▊ | 4/50 [00:06<01:20, 1.74s/it]\n 10%|█ | 5/50 [00:08<01:18, 1.75s/it]\n 12%|█▏ | 6/50 [00:10<01:17, 1.76s/it]\n 14%|█▍ | 7/50 [00:12<01:15, 1.77s/it]\n 16%|█▌ | 8/50 [00:14<01:14, 1.77s/it]\n 18%|█▊ | 9/50 [00:15<01:12, 1.77s/it]\n 20%|██ | 10/50 [00:17<01:10, 1.77s/it]\n 22%|██▏ | 11/50 [00:19<01:09, 1.78s/it]\n 24%|██▍ | 12/50 [00:21<01:07, 1.78s/it]\n 26%|██▌ | 13/50 [00:22<01:05, 1.78s/it]\n 28%|██▊ | 14/50 [00:24<01:04, 1.78s/it]\n 30%|███ | 15/50 [00:26<01:02, 1.78s/it]\n 32%|███▏ | 16/50 [00:28<01:00, 1.78s/it]\n 34%|███▍ | 17/50 [00:30<00:58, 1.78s/it]\n 36%|███▌ | 18/50 [00:31<00:57, 1.78s/it]\n 38%|███▊ | 19/50 [00:33<00:55, 1.78s/it]\n 40%|████ | 20/50 [00:35<00:53, 1.78s/it]\n 42%|████▏ | 21/50 [00:37<00:51, 1.79s/it]\n 44%|████▍ | 22/50 [00:38<00:49, 1.79s/it]\n 46%|████▌ | 23/50 [00:40<00:48, 1.79s/it]\n 48%|████▊ | 24/50 [00:42<00:46, 1.79s/it]\n 50%|█████ | 25/50 [00:44<00:44, 1.79s/it]\n 52%|█████▏ | 26/50 [00:46<00:42, 1.79s/it]\n 54%|█████▍ | 27/50 [00:47<00:41, 1.79s/it]\n 56%|█████▌ | 28/50 [00:49<00:39, 1.79s/it]\n 58%|█████▊ | 29/50 [00:51<00:37, 1.79s/it]\n 60%|██████ | 30/50 [00:53<00:35, 1.79s/it]\n 62%|██████▏ | 31/50 [00:55<00:34, 1.79s/it]\n 64%|██████▍ | 32/50 [00:56<00:32, 1.79s/it]\n 66%|██████▌ | 33/50 [00:58<00:30, 1.79s/it]\n 68%|██████▊ | 34/50 [01:00<00:28, 1.79s/it]\n 70%|███████ | 35/50 [01:02<00:26, 1.79s/it]\n 72%|███████▏ | 36/50 [01:04<00:25, 1.79s/it]\n 74%|███████▍ | 37/50 [01:05<00:23, 1.79s/it]\n 76%|███████▌ | 38/50 [01:07<00:21, 1.79s/it]\n 78%|███████▊ | 39/50 [01:09<00:19, 1.79s/it]\n 80%|████████ | 40/50 [01:11<00:17, 1.79s/it]\n 82%|████████▏ | 41/50 [01:12<00:16, 1.79s/it]\n 84%|████████▍ | 42/50 [01:14<00:14, 1.79s/it]\n 86%|████████▌ | 43/50 [01:16<00:12, 1.79s/it]\n 88%|████████▊ | 44/50 [01:18<00:10, 1.79s/it]\n 90%|█████████ | 45/50 [01:20<00:08, 1.79s/it]\n 92%|█████████▏| 46/50 [01:21<00:07, 1.79s/it]\n 94%|█████████▍| 47/50 [01:23<00:05, 1.79s/it]\n 96%|█████████▌| 48/50 [01:25<00:03, 1.79s/it]\n 98%|█████████▊| 49/50 [01:27<00:01, 1.79s/it]\n100%|██████████| 50/50 [01:29<00:00, 1.79s/it]\n100%|██████████| 50/50 [01:29<00:00, 1.78s/it]", "metrics": { "predict_time": 90.12301522, "total_time": 90.130005 }, "output": "https://replicate.delivery/xezq/WOfJLixnOrVQPCxFePfDHQO3Tl6epLe5sUuF1LT7fjLzb3nOF/output.png", "started_at": "2025-06-25T18:51:01.344990Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bcwr-6tztonwlfumukt2qo4aiimipif2oy7sw7vnxrp344uhpzk22m4hq", "get": "https://api.replicate.com/v1/predictions/cf85e2yvb9rmc0cqn1pv28d868", "cancel": "https://api.replicate.com/v1/predictions/cf85e2yvb9rmc0cqn1pv28d868/cancel" }, "version": "5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502e" }
Generated in0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:01<01:26, 1.77s/it] 4%|▍ | 2/50 [00:03<01:20, 1.68s/it] 6%|▌ | 3/50 [00:05<01:20, 1.72s/it] 8%|▊ | 4/50 [00:06<01:20, 1.74s/it] 10%|█ | 5/50 [00:08<01:18, 1.75s/it] 12%|█▏ | 6/50 [00:10<01:17, 1.76s/it] 14%|█▍ | 7/50 [00:12<01:15, 1.77s/it] 16%|█▌ | 8/50 [00:14<01:14, 1.77s/it] 18%|█▊ | 9/50 [00:15<01:12, 1.77s/it] 20%|██ | 10/50 [00:17<01:10, 1.77s/it] 22%|██▏ | 11/50 [00:19<01:09, 1.78s/it] 24%|██▍ | 12/50 [00:21<01:07, 1.78s/it] 26%|██▌ | 13/50 [00:22<01:05, 1.78s/it] 28%|██▊ | 14/50 [00:24<01:04, 1.78s/it] 30%|███ | 15/50 [00:26<01:02, 1.78s/it] 32%|███▏ | 16/50 [00:28<01:00, 1.78s/it] 34%|███▍ | 17/50 [00:30<00:58, 1.78s/it] 36%|███▌ | 18/50 [00:31<00:57, 1.78s/it] 38%|███▊ | 19/50 [00:33<00:55, 1.78s/it] 40%|████ | 20/50 [00:35<00:53, 1.78s/it] 42%|████▏ | 21/50 [00:37<00:51, 1.79s/it] 44%|████▍ | 22/50 [00:38<00:49, 1.79s/it] 46%|████▌ | 23/50 [00:40<00:48, 1.79s/it] 48%|████▊ | 24/50 [00:42<00:46, 1.79s/it] 50%|█████ | 25/50 [00:44<00:44, 1.79s/it] 52%|█████▏ | 26/50 [00:46<00:42, 1.79s/it] 54%|█████▍ | 27/50 [00:47<00:41, 1.79s/it] 56%|█████▌ | 28/50 [00:49<00:39, 1.79s/it] 58%|█████▊ | 29/50 [00:51<00:37, 1.79s/it] 60%|██████ | 30/50 [00:53<00:35, 1.79s/it] 62%|██████▏ | 31/50 [00:55<00:34, 1.79s/it] 64%|██████▍ | 32/50 [00:56<00:32, 1.79s/it] 66%|██████▌ | 33/50 [00:58<00:30, 1.79s/it] 68%|██████▊ | 34/50 [01:00<00:28, 1.79s/it] 70%|███████ | 35/50 [01:02<00:26, 1.79s/it] 72%|███████▏ | 36/50 [01:04<00:25, 1.79s/it] 74%|███████▍ | 37/50 [01:05<00:23, 1.79s/it] 76%|███████▌ | 38/50 [01:07<00:21, 1.79s/it] 78%|███████▊ | 39/50 [01:09<00:19, 1.79s/it] 80%|████████ | 40/50 [01:11<00:17, 1.79s/it] 82%|████████▏ | 41/50 [01:12<00:16, 1.79s/it] 84%|████████▍ | 42/50 [01:14<00:14, 1.79s/it] 86%|████████▌ | 43/50 [01:16<00:12, 1.79s/it] 88%|████████▊ | 44/50 [01:18<00:10, 1.79s/it] 90%|█████████ | 45/50 [01:20<00:08, 1.79s/it] 92%|█████████▏| 46/50 [01:21<00:07, 1.79s/it] 94%|█████████▍| 47/50 [01:23<00:05, 1.79s/it] 96%|█████████▌| 48/50 [01:25<00:03, 1.79s/it] 98%|█████████▊| 49/50 [01:27<00:01, 1.79s/it] 100%|██████████| 50/50 [01:29<00:00, 1.79s/it] 100%|██████████| 50/50 [01:29<00:00, 1.78s/it]
Prediction
lucataco/omnigen2:5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502eIDwaxc5fkp4srm80cqn1qtqqhbncStatusSucceededSourceWebHardwareL40STotal durationCreatedInput
- seed
- -1
- width
- 1024
- height
- 1024
- prompt
- make him smile
- scheduler
- euler
- max_pixels
- 1048576
- cfg_range_end
- 1
- cfg_range_start
- 0
- negative_prompt
- (((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar
- num_inference_steps
- 50
- text_guidance_scale
- 5
- image_guidance_scale
- 2
- max_input_image_side_length
- 2048
{ "seed": -1, "image": "https://replicate.delivery/pbxt/NFVR9p4akEoTdlQBEanwi5Qg6JxpSewBiHvgvA46X1r6xYsO/man.jpg", "width": 1024, "height": 1024, "prompt": "make him smile", "scheduler": "euler", "max_pixels": 1048576, "cfg_range_end": 1, "cfg_range_start": 0, "negative_prompt": "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar", "num_inference_steps": 50, "text_guidance_scale": 5, "image_guidance_scale": 2, "max_input_image_side_length": 2048 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run lucataco/omnigen2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/omnigen2:5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502e", { input: { seed: -1, image: "https://replicate.delivery/pbxt/NFVR9p4akEoTdlQBEanwi5Qg6JxpSewBiHvgvA46X1r6xYsO/man.jpg", width: 1024, height: 1024, prompt: "make him smile", scheduler: "euler", max_pixels: 1048576, cfg_range_end: 1, cfg_range_start: 0, negative_prompt: "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar", num_inference_steps: 50, text_guidance_scale: 5, image_guidance_scale: 2, max_input_image_side_length: 2048 } } ); // 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 lucataco/omnigen2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/omnigen2:5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502e", input={ "seed": -1, "image": "https://replicate.delivery/pbxt/NFVR9p4akEoTdlQBEanwi5Qg6JxpSewBiHvgvA46X1r6xYsO/man.jpg", "width": 1024, "height": 1024, "prompt": "make him smile", "scheduler": "euler", "max_pixels": 1048576, "cfg_range_end": 1, "cfg_range_start": 0, "negative_prompt": "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar", "num_inference_steps": 50, "text_guidance_scale": 5, "image_guidance_scale": 2, "max_input_image_side_length": 2048 } ) # To access the file URL: print(output.url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output.read())
To learn more, take a look at the guide on getting started with Python.
Run lucataco/omnigen2 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": "lucataco/omnigen2:5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502e", "input": { "seed": -1, "image": "https://replicate.delivery/pbxt/NFVR9p4akEoTdlQBEanwi5Qg6JxpSewBiHvgvA46X1r6xYsO/man.jpg", "width": 1024, "height": 1024, "prompt": "make him smile", "scheduler": "euler", "max_pixels": 1048576, "cfg_range_end": 1, "cfg_range_start": 0, "negative_prompt": "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar", "num_inference_steps": 50, "text_guidance_scale": 5, "image_guidance_scale": 2, "max_input_image_side_length": 2048 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cog
If you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/lucataco/omnigen2@sha256:5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502e \ -i 'seed=-1' \ -i 'image="https://replicate.delivery/pbxt/NFVR9p4akEoTdlQBEanwi5Qg6JxpSewBiHvgvA46X1r6xYsO/man.jpg"' \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="make him smile"' \ -i 'scheduler="euler"' \ -i 'max_pixels=1048576' \ -i 'cfg_range_end=1' \ -i 'cfg_range_start=0' \ -i 'negative_prompt="(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar"' \ -i 'num_inference_steps=50' \ -i 'text_guidance_scale=5' \ -i 'image_guidance_scale=2' \ -i 'max_input_image_side_length=2048'
To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/lucataco/omnigen2@sha256:5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502e
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "seed": -1, "image": "https://replicate.delivery/pbxt/NFVR9p4akEoTdlQBEanwi5Qg6JxpSewBiHvgvA46X1r6xYsO/man.jpg", "width": 1024, "height": 1024, "prompt": "make him smile", "scheduler": "euler", "max_pixels": 1048576, "cfg_range_end": 1, "cfg_range_start": 0, "negative_prompt": "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar", "num_inference_steps": 50, "text_guidance_scale": 5, "image_guidance_scale": 2, "max_input_image_side_length": 2048 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2025-06-25T18:54:15.967588Z", "created_at": "2025-06-25T18:52:46.502000Z", "data_removed": false, "error": null, "id": "waxc5fkp4srm80cqn1qtqqhbnc", "input": { "seed": -1, "image": "https://replicate.delivery/pbxt/NFVR9p4akEoTdlQBEanwi5Qg6JxpSewBiHvgvA46X1r6xYsO/man.jpg", "width": 1024, "height": 1024, "prompt": "make him smile", "scheduler": "euler", "max_pixels": 1048576, "cfg_range_end": 1, "cfg_range_start": 0, "negative_prompt": "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar", "num_inference_steps": 50, "text_guidance_scale": 5, "image_guidance_scale": 2, "max_input_image_side_length": 2048 }, "logs": "0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:01<01:25, 1.75s/it]\n 4%|▍ | 2/50 [00:03<01:19, 1.66s/it]\n 6%|▌ | 3/50 [00:05<01:20, 1.71s/it]\n 8%|▊ | 4/50 [00:06<01:19, 1.73s/it]\n 10%|█ | 5/50 [00:08<01:18, 1.74s/it]\n 12%|█▏ | 6/50 [00:10<01:16, 1.75s/it]\n 14%|█▍ | 7/50 [00:12<01:15, 1.75s/it]\n 16%|█▌ | 8/50 [00:13<01:13, 1.76s/it]\n 18%|█▊ | 9/50 [00:15<01:12, 1.76s/it]\n 20%|██ | 10/50 [00:17<01:10, 1.76s/it]\n 22%|██▏ | 11/50 [00:19<01:08, 1.77s/it]\n 24%|██▍ | 12/50 [00:21<01:07, 1.77s/it]\n 26%|██▌ | 13/50 [00:22<01:05, 1.77s/it]\n 28%|██▊ | 14/50 [00:24<01:03, 1.77s/it]\n 30%|███ | 15/50 [00:26<01:01, 1.77s/it]\n 32%|███▏ | 16/50 [00:28<01:00, 1.77s/it]\n 34%|███▍ | 17/50 [00:29<00:58, 1.77s/it]\n 36%|███▌ | 18/50 [00:31<00:56, 1.77s/it]\n 38%|███▊ | 19/50 [00:33<00:54, 1.77s/it]\n 40%|████ | 20/50 [00:35<00:53, 1.77s/it]\n 42%|████▏ | 21/50 [00:36<00:51, 1.77s/it]\n 44%|████▍ | 22/50 [00:38<00:49, 1.77s/it]\n 46%|████▌ | 23/50 [00:40<00:47, 1.77s/it]\n 48%|████▊ | 24/50 [00:42<00:46, 1.77s/it]\n 50%|█████ | 25/50 [00:44<00:44, 1.77s/it]\n 52%|█████▏ | 26/50 [00:45<00:42, 1.77s/it]\n 54%|█████▍ | 27/50 [00:47<00:40, 1.77s/it]\n 56%|█████▌ | 28/50 [00:49<00:39, 1.77s/it]\n 58%|█████▊ | 29/50 [00:51<00:37, 1.77s/it]\n 60%|██████ | 30/50 [00:52<00:35, 1.78s/it]\n 62%|██████▏ | 31/50 [00:54<00:33, 1.78s/it]\n 64%|██████▍ | 32/50 [00:56<00:31, 1.78s/it]\n 66%|██████▌ | 33/50 [00:58<00:30, 1.78s/it]\n 68%|██████▊ | 34/50 [01:00<00:28, 1.78s/it]\n 70%|███████ | 35/50 [01:01<00:26, 1.78s/it]\n 72%|███████▏ | 36/50 [01:03<00:24, 1.78s/it]\n 74%|███████▍ | 37/50 [01:05<00:23, 1.78s/it]\n 76%|███████▌ | 38/50 [01:07<00:21, 1.78s/it]\n 78%|███████▊ | 39/50 [01:08<00:19, 1.78s/it]\n 80%|████████ | 40/50 [01:10<00:17, 1.78s/it]\n 82%|████████▏ | 41/50 [01:12<00:15, 1.78s/it]\n 84%|████████▍ | 42/50 [01:14<00:14, 1.78s/it]\n 86%|████████▌ | 43/50 [01:16<00:12, 1.78s/it]\n 88%|████████▊ | 44/50 [01:17<00:10, 1.78s/it]\n 90%|█████████ | 45/50 [01:19<00:08, 1.78s/it]\n 92%|█████████▏| 46/50 [01:21<00:07, 1.78s/it]\n 94%|█████████▍| 47/50 [01:23<00:05, 1.78s/it]\n 96%|█████████▌| 48/50 [01:24<00:03, 1.78s/it]\n 98%|█████████▊| 49/50 [01:26<00:01, 1.78s/it]\n100%|██████████| 50/50 [01:28<00:00, 1.78s/it]\n100%|██████████| 50/50 [01:28<00:00, 1.77s/it]", "metrics": { "predict_time": 89.454406565, "total_time": 89.465588 }, "output": "https://replicate.delivery/xezq/f9OPLzyIyUyvYy7mAb00Yt5ryyHpTNBoj8SKzQPC31fXfepTB/output.png", "started_at": "2025-06-25T18:52:46.513181Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bcwr-bmoqlvjkrwwmgatrc44qrqfxlna6bldgu23gatik2riyudgdxria", "get": "https://api.replicate.com/v1/predictions/waxc5fkp4srm80cqn1qtqqhbnc", "cancel": "https://api.replicate.com/v1/predictions/waxc5fkp4srm80cqn1qtqqhbnc/cancel" }, "version": "5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502e" }
Generated in0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:01<01:25, 1.75s/it] 4%|▍ | 2/50 [00:03<01:19, 1.66s/it] 6%|▌ | 3/50 [00:05<01:20, 1.71s/it] 8%|▊ | 4/50 [00:06<01:19, 1.73s/it] 10%|█ | 5/50 [00:08<01:18, 1.74s/it] 12%|█▏ | 6/50 [00:10<01:16, 1.75s/it] 14%|█▍ | 7/50 [00:12<01:15, 1.75s/it] 16%|█▌ | 8/50 [00:13<01:13, 1.76s/it] 18%|█▊ | 9/50 [00:15<01:12, 1.76s/it] 20%|██ | 10/50 [00:17<01:10, 1.76s/it] 22%|██▏ | 11/50 [00:19<01:08, 1.77s/it] 24%|██▍ | 12/50 [00:21<01:07, 1.77s/it] 26%|██▌ | 13/50 [00:22<01:05, 1.77s/it] 28%|██▊ | 14/50 [00:24<01:03, 1.77s/it] 30%|███ | 15/50 [00:26<01:01, 1.77s/it] 32%|███▏ | 16/50 [00:28<01:00, 1.77s/it] 34%|███▍ | 17/50 [00:29<00:58, 1.77s/it] 36%|███▌ | 18/50 [00:31<00:56, 1.77s/it] 38%|███▊ | 19/50 [00:33<00:54, 1.77s/it] 40%|████ | 20/50 [00:35<00:53, 1.77s/it] 42%|████▏ | 21/50 [00:36<00:51, 1.77s/it] 44%|████▍ | 22/50 [00:38<00:49, 1.77s/it] 46%|████▌ | 23/50 [00:40<00:47, 1.77s/it] 48%|████▊ | 24/50 [00:42<00:46, 1.77s/it] 50%|█████ | 25/50 [00:44<00:44, 1.77s/it] 52%|█████▏ | 26/50 [00:45<00:42, 1.77s/it] 54%|█████▍ | 27/50 [00:47<00:40, 1.77s/it] 56%|█████▌ | 28/50 [00:49<00:39, 1.77s/it] 58%|█████▊ | 29/50 [00:51<00:37, 1.77s/it] 60%|██████ | 30/50 [00:52<00:35, 1.78s/it] 62%|██████▏ | 31/50 [00:54<00:33, 1.78s/it] 64%|██████▍ | 32/50 [00:56<00:31, 1.78s/it] 66%|██████▌ | 33/50 [00:58<00:30, 1.78s/it] 68%|██████▊ | 34/50 [01:00<00:28, 1.78s/it] 70%|███████ | 35/50 [01:01<00:26, 1.78s/it] 72%|███████▏ | 36/50 [01:03<00:24, 1.78s/it] 74%|███████▍ | 37/50 [01:05<00:23, 1.78s/it] 76%|███████▌ | 38/50 [01:07<00:21, 1.78s/it] 78%|███████▊ | 39/50 [01:08<00:19, 1.78s/it] 80%|████████ | 40/50 [01:10<00:17, 1.78s/it] 82%|████████▏ | 41/50 [01:12<00:15, 1.78s/it] 84%|████████▍ | 42/50 [01:14<00:14, 1.78s/it] 86%|████████▌ | 43/50 [01:16<00:12, 1.78s/it] 88%|████████▊ | 44/50 [01:17<00:10, 1.78s/it] 90%|█████████ | 45/50 [01:19<00:08, 1.78s/it] 92%|█████████▏| 46/50 [01:21<00:07, 1.78s/it] 94%|█████████▍| 47/50 [01:23<00:05, 1.78s/it] 96%|█████████▌| 48/50 [01:24<00:03, 1.78s/it] 98%|█████████▊| 49/50 [01:26<00:01, 1.78s/it] 100%|██████████| 50/50 [01:28<00:00, 1.78s/it] 100%|██████████| 50/50 [01:28<00:00, 1.77s/it]
Prediction
lucataco/omnigen2:5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502eIDqhxhpa47j9rme0cqn1ssee1qq8StatusSucceededSourceWebHardwareL40STotal durationCreatedInput
- seed
- -1
- width
- 1024
- height
- 1024
- prompt
- Add a straw hat to the woman's head
- scheduler
- euler
- max_pixels
- 1048576
- cfg_range_end
- 1
- cfg_range_start
- 0
- negative_prompt
- (((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar
- num_inference_steps
- 50
- text_guidance_scale
- 5
- image_guidance_scale
- 2
- max_input_image_side_length
- 2048
{ "seed": -1, "image": "https://replicate.delivery/pbxt/NFVTnhnaQuj6AHmgtgS1X6TpHAolhS1oo9Rka4AvNyJgacVp/woman-field.png", "width": 1024, "height": 1024, "prompt": "Add a straw hat to the woman's head", "scheduler": "euler", "max_pixels": 1048576, "cfg_range_end": 1, "cfg_range_start": 0, "negative_prompt": "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar", "num_inference_steps": 50, "text_guidance_scale": 5, "image_guidance_scale": 2, "max_input_image_side_length": 2048 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run lucataco/omnigen2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/omnigen2:5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502e", { input: { seed: -1, image: "https://replicate.delivery/pbxt/NFVTnhnaQuj6AHmgtgS1X6TpHAolhS1oo9Rka4AvNyJgacVp/woman-field.png", width: 1024, height: 1024, prompt: "Add a straw hat to the woman's head", scheduler: "euler", max_pixels: 1048576, cfg_range_end: 1, cfg_range_start: 0, negative_prompt: "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar", num_inference_steps: 50, text_guidance_scale: 5, image_guidance_scale: 2, max_input_image_side_length: 2048 } } ); // 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 lucataco/omnigen2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/omnigen2:5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502e", input={ "seed": -1, "image": "https://replicate.delivery/pbxt/NFVTnhnaQuj6AHmgtgS1X6TpHAolhS1oo9Rka4AvNyJgacVp/woman-field.png", "width": 1024, "height": 1024, "prompt": "Add a straw hat to the woman's head", "scheduler": "euler", "max_pixels": 1048576, "cfg_range_end": 1, "cfg_range_start": 0, "negative_prompt": "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar", "num_inference_steps": 50, "text_guidance_scale": 5, "image_guidance_scale": 2, "max_input_image_side_length": 2048 } ) # To access the file URL: print(output.url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output.read())
To learn more, take a look at the guide on getting started with Python.
Run lucataco/omnigen2 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": "lucataco/omnigen2:5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502e", "input": { "seed": -1, "image": "https://replicate.delivery/pbxt/NFVTnhnaQuj6AHmgtgS1X6TpHAolhS1oo9Rka4AvNyJgacVp/woman-field.png", "width": 1024, "height": 1024, "prompt": "Add a straw hat to the woman\'s head", "scheduler": "euler", "max_pixels": 1048576, "cfg_range_end": 1, "cfg_range_start": 0, "negative_prompt": "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar", "num_inference_steps": 50, "text_guidance_scale": 5, "image_guidance_scale": 2, "max_input_image_side_length": 2048 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cog
If you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/lucataco/omnigen2@sha256:5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502e \ -i 'seed=-1' \ -i 'image="https://replicate.delivery/pbxt/NFVTnhnaQuj6AHmgtgS1X6TpHAolhS1oo9Rka4AvNyJgacVp/woman-field.png"' \ -i 'width=1024' \ -i 'height=1024' \ -i $'prompt="Add a straw hat to the woman\'s head"' \ -i 'scheduler="euler"' \ -i 'max_pixels=1048576' \ -i 'cfg_range_end=1' \ -i 'cfg_range_start=0' \ -i 'negative_prompt="(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar"' \ -i 'num_inference_steps=50' \ -i 'text_guidance_scale=5' \ -i 'image_guidance_scale=2' \ -i 'max_input_image_side_length=2048'
To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/lucataco/omnigen2@sha256:5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502e
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "seed": -1, "image": "https://replicate.delivery/pbxt/NFVTnhnaQuj6AHmgtgS1X6TpHAolhS1oo9Rka4AvNyJgacVp/woman-field.png", "width": 1024, "height": 1024, "prompt": "Add a straw hat to the woman\'s head", "scheduler": "euler", "max_pixels": 1048576, "cfg_range_end": 1, "cfg_range_start": 0, "negative_prompt": "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar", "num_inference_steps": 50, "text_guidance_scale": 5, "image_guidance_scale": 2, "max_input_image_side_length": 2048 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2025-06-25T18:58:42.660590Z", "created_at": "2025-06-25T18:57:13.106000Z", "data_removed": false, "error": null, "id": "qhxhpa47j9rme0cqn1ssee1qq8", "input": { "seed": -1, "image": "https://replicate.delivery/pbxt/NFVTnhnaQuj6AHmgtgS1X6TpHAolhS1oo9Rka4AvNyJgacVp/woman-field.png", "width": 1024, "height": 1024, "prompt": "Add a straw hat to the woman's head", "scheduler": "euler", "max_pixels": 1048576, "cfg_range_end": 1, "cfg_range_start": 0, "negative_prompt": "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar", "num_inference_steps": 50, "text_guidance_scale": 5, "image_guidance_scale": 2, "max_input_image_side_length": 2048 }, "logs": "0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:01<01:26, 1.76s/it]\n 4%|▍ | 2/50 [00:03<01:19, 1.67s/it]\n 6%|▌ | 3/50 [00:05<01:20, 1.71s/it]\n 8%|▊ | 4/50 [00:06<01:19, 1.73s/it]\n 10%|█ | 5/50 [00:08<01:18, 1.74s/it]\n 12%|█▏ | 6/50 [00:10<01:17, 1.75s/it]\n 14%|█▍ | 7/50 [00:12<01:15, 1.76s/it]\n 16%|█▌ | 8/50 [00:13<01:13, 1.76s/it]\n 18%|█▊ | 9/50 [00:15<01:12, 1.76s/it]\n 20%|██ | 10/50 [00:17<01:10, 1.76s/it]\n 22%|██▏ | 11/50 [00:19<01:08, 1.76s/it]\n 24%|██▍ | 12/50 [00:21<01:07, 1.77s/it]\n 26%|██▌ | 13/50 [00:22<01:05, 1.77s/it]\n 28%|██▊ | 14/50 [00:24<01:03, 1.77s/it]\n 30%|███ | 15/50 [00:26<01:01, 1.77s/it]\n 32%|███▏ | 16/50 [00:28<01:00, 1.77s/it]\n 34%|███▍ | 17/50 [00:29<00:58, 1.77s/it]\n 36%|███▌ | 18/50 [00:31<00:56, 1.77s/it]\n 38%|███▊ | 19/50 [00:33<00:54, 1.77s/it]\n 40%|████ | 20/50 [00:35<00:53, 1.77s/it]\n 42%|████▏ | 21/50 [00:36<00:51, 1.77s/it]\n 44%|████▍ | 22/50 [00:38<00:49, 1.77s/it]\n 46%|████▌ | 23/50 [00:40<00:47, 1.77s/it]\n 48%|████▊ | 24/50 [00:42<00:46, 1.77s/it]\n 50%|█████ | 25/50 [00:44<00:44, 1.77s/it]\n 52%|█████▏ | 26/50 [00:45<00:42, 1.77s/it]\n 54%|█████▍ | 27/50 [00:47<00:40, 1.77s/it]\n 56%|█████▌ | 28/50 [00:49<00:39, 1.77s/it]\n 58%|█████▊ | 29/50 [00:51<00:37, 1.77s/it]\n 60%|██████ | 30/50 [00:52<00:35, 1.77s/it]\n 62%|██████▏ | 31/50 [00:54<00:33, 1.78s/it]\n 64%|██████▍ | 32/50 [00:56<00:31, 1.78s/it]\n 66%|██████▌ | 33/50 [00:58<00:30, 1.78s/it]\n 68%|██████▊ | 34/50 [01:00<00:28, 1.78s/it]\n 70%|███████ | 35/50 [01:01<00:26, 1.78s/it]\n 72%|███████▏ | 36/50 [01:03<00:24, 1.78s/it]\n 74%|███████▍ | 37/50 [01:05<00:23, 1.78s/it]\n 76%|███████▌ | 38/50 [01:07<00:21, 1.78s/it]\n 78%|███████▊ | 39/50 [01:08<00:19, 1.78s/it]\n 80%|████████ | 40/50 [01:10<00:17, 1.78s/it]\n 82%|████████▏ | 41/50 [01:12<00:15, 1.78s/it]\n 84%|████████▍ | 42/50 [01:14<00:14, 1.78s/it]\n 86%|████████▌ | 43/50 [01:16<00:12, 1.78s/it]\n 88%|████████▊ | 44/50 [01:17<00:10, 1.78s/it]\n 90%|█████████ | 45/50 [01:19<00:08, 1.78s/it]\n 92%|█████████▏| 46/50 [01:21<00:07, 1.78s/it]\n 94%|█████████▍| 47/50 [01:23<00:05, 1.78s/it]\n 96%|█████████▌| 48/50 [01:24<00:03, 1.78s/it]\n 98%|█████████▊| 49/50 [01:26<00:01, 1.78s/it]\n100%|██████████| 50/50 [01:28<00:00, 1.78s/it]\n100%|██████████| 50/50 [01:28<00:00, 1.77s/it]", "metrics": { "predict_time": 89.546186564, "total_time": 89.55459 }, "output": "https://replicate.delivery/xezq/COeCHIGVYGx4ZKUGSH139wn3UVKdyooSun3y5FMOCmCxxPdKA/output.png", "started_at": "2025-06-25T18:57:13.114403Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bcwr-37obanuagoitssp7aau6lgkstcyzufhudxmqjtshmzby4dplhlua", "get": "https://api.replicate.com/v1/predictions/qhxhpa47j9rme0cqn1ssee1qq8", "cancel": "https://api.replicate.com/v1/predictions/qhxhpa47j9rme0cqn1ssee1qq8/cancel" }, "version": "5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502e" }
Generated in0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:01<01:26, 1.76s/it] 4%|▍ | 2/50 [00:03<01:19, 1.67s/it] 6%|▌ | 3/50 [00:05<01:20, 1.71s/it] 8%|▊ | 4/50 [00:06<01:19, 1.73s/it] 10%|█ | 5/50 [00:08<01:18, 1.74s/it] 12%|█▏ | 6/50 [00:10<01:17, 1.75s/it] 14%|█▍ | 7/50 [00:12<01:15, 1.76s/it] 16%|█▌ | 8/50 [00:13<01:13, 1.76s/it] 18%|█▊ | 9/50 [00:15<01:12, 1.76s/it] 20%|██ | 10/50 [00:17<01:10, 1.76s/it] 22%|██▏ | 11/50 [00:19<01:08, 1.76s/it] 24%|██▍ | 12/50 [00:21<01:07, 1.77s/it] 26%|██▌ | 13/50 [00:22<01:05, 1.77s/it] 28%|██▊ | 14/50 [00:24<01:03, 1.77s/it] 30%|███ | 15/50 [00:26<01:01, 1.77s/it] 32%|███▏ | 16/50 [00:28<01:00, 1.77s/it] 34%|███▍ | 17/50 [00:29<00:58, 1.77s/it] 36%|███▌ | 18/50 [00:31<00:56, 1.77s/it] 38%|███▊ | 19/50 [00:33<00:54, 1.77s/it] 40%|████ | 20/50 [00:35<00:53, 1.77s/it] 42%|████▏ | 21/50 [00:36<00:51, 1.77s/it] 44%|████▍ | 22/50 [00:38<00:49, 1.77s/it] 46%|████▌ | 23/50 [00:40<00:47, 1.77s/it] 48%|████▊ | 24/50 [00:42<00:46, 1.77s/it] 50%|█████ | 25/50 [00:44<00:44, 1.77s/it] 52%|█████▏ | 26/50 [00:45<00:42, 1.77s/it] 54%|█████▍ | 27/50 [00:47<00:40, 1.77s/it] 56%|█████▌ | 28/50 [00:49<00:39, 1.77s/it] 58%|█████▊ | 29/50 [00:51<00:37, 1.77s/it] 60%|██████ | 30/50 [00:52<00:35, 1.77s/it] 62%|██████▏ | 31/50 [00:54<00:33, 1.78s/it] 64%|██████▍ | 32/50 [00:56<00:31, 1.78s/it] 66%|██████▌ | 33/50 [00:58<00:30, 1.78s/it] 68%|██████▊ | 34/50 [01:00<00:28, 1.78s/it] 70%|███████ | 35/50 [01:01<00:26, 1.78s/it] 72%|███████▏ | 36/50 [01:03<00:24, 1.78s/it] 74%|███████▍ | 37/50 [01:05<00:23, 1.78s/it] 76%|███████▌ | 38/50 [01:07<00:21, 1.78s/it] 78%|███████▊ | 39/50 [01:08<00:19, 1.78s/it] 80%|████████ | 40/50 [01:10<00:17, 1.78s/it] 82%|████████▏ | 41/50 [01:12<00:15, 1.78s/it] 84%|████████▍ | 42/50 [01:14<00:14, 1.78s/it] 86%|████████▌ | 43/50 [01:16<00:12, 1.78s/it] 88%|████████▊ | 44/50 [01:17<00:10, 1.78s/it] 90%|█████████ | 45/50 [01:19<00:08, 1.78s/it] 92%|█████████▏| 46/50 [01:21<00:07, 1.78s/it] 94%|█████████▍| 47/50 [01:23<00:05, 1.78s/it] 96%|█████████▌| 48/50 [01:24<00:03, 1.78s/it] 98%|█████████▊| 49/50 [01:26<00:01, 1.78s/it] 100%|██████████| 50/50 [01:28<00:00, 1.78s/it] 100%|██████████| 50/50 [01:28<00:00, 1.77s/it]
Prediction
lucataco/omnigen2:5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502eID6pr3ztrjkxrm80cqn1wvnh2egcStatusSucceededSourceWebHardwareL40STotal durationCreatedInput
- seed
- -1
- width
- 1024
- height
- 1024
- prompt
- replace the sword with a hammer
- scheduler
- euler
- max_pixels
- 1048576
- cfg_range_end
- 1
- cfg_range_start
- 0
- negative_prompt
- (((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar
- num_inference_steps
- 50
- text_guidance_scale
- 5
- image_guidance_scale
- 2
- max_input_image_side_length
- 2048
{ "seed": -1, "image": "https://replicate.delivery/pbxt/NFVZYQi8xmHzWy2wH0FYGoIC366rDdXNvvh8hqBPPG6Kx69f/game-character.png", "width": 1024, "height": 1024, "prompt": " replace the sword with a hammer", "scheduler": "euler", "max_pixels": 1048576, "cfg_range_end": 1, "cfg_range_start": 0, "negative_prompt": "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar", "num_inference_steps": 50, "text_guidance_scale": 5, "image_guidance_scale": 2, "max_input_image_side_length": 2048 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run lucataco/omnigen2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/omnigen2:5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502e", { input: { seed: -1, image: "https://replicate.delivery/pbxt/NFVZYQi8xmHzWy2wH0FYGoIC366rDdXNvvh8hqBPPG6Kx69f/game-character.png", width: 1024, height: 1024, prompt: " replace the sword with a hammer", scheduler: "euler", max_pixels: 1048576, cfg_range_end: 1, cfg_range_start: 0, negative_prompt: "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar", num_inference_steps: 50, text_guidance_scale: 5, image_guidance_scale: 2, max_input_image_side_length: 2048 } } ); // 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 lucataco/omnigen2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/omnigen2:5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502e", input={ "seed": -1, "image": "https://replicate.delivery/pbxt/NFVZYQi8xmHzWy2wH0FYGoIC366rDdXNvvh8hqBPPG6Kx69f/game-character.png", "width": 1024, "height": 1024, "prompt": " replace the sword with a hammer", "scheduler": "euler", "max_pixels": 1048576, "cfg_range_end": 1, "cfg_range_start": 0, "negative_prompt": "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar", "num_inference_steps": 50, "text_guidance_scale": 5, "image_guidance_scale": 2, "max_input_image_side_length": 2048 } ) # To access the file URL: print(output.url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output.read())
To learn more, take a look at the guide on getting started with Python.
Run lucataco/omnigen2 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": "lucataco/omnigen2:5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502e", "input": { "seed": -1, "image": "https://replicate.delivery/pbxt/NFVZYQi8xmHzWy2wH0FYGoIC366rDdXNvvh8hqBPPG6Kx69f/game-character.png", "width": 1024, "height": 1024, "prompt": " replace the sword with a hammer", "scheduler": "euler", "max_pixels": 1048576, "cfg_range_end": 1, "cfg_range_start": 0, "negative_prompt": "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar", "num_inference_steps": 50, "text_guidance_scale": 5, "image_guidance_scale": 2, "max_input_image_side_length": 2048 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cog
If you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/lucataco/omnigen2@sha256:5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502e \ -i 'seed=-1' \ -i 'image="https://replicate.delivery/pbxt/NFVZYQi8xmHzWy2wH0FYGoIC366rDdXNvvh8hqBPPG6Kx69f/game-character.png"' \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt=" replace the sword with a hammer"' \ -i 'scheduler="euler"' \ -i 'max_pixels=1048576' \ -i 'cfg_range_end=1' \ -i 'cfg_range_start=0' \ -i 'negative_prompt="(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar"' \ -i 'num_inference_steps=50' \ -i 'text_guidance_scale=5' \ -i 'image_guidance_scale=2' \ -i 'max_input_image_side_length=2048'
To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/lucataco/omnigen2@sha256:5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502e
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "seed": -1, "image": "https://replicate.delivery/pbxt/NFVZYQi8xmHzWy2wH0FYGoIC366rDdXNvvh8hqBPPG6Kx69f/game-character.png", "width": 1024, "height": 1024, "prompt": " replace the sword with a hammer", "scheduler": "euler", "max_pixels": 1048576, "cfg_range_end": 1, "cfg_range_start": 0, "negative_prompt": "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar", "num_inference_steps": 50, "text_guidance_scale": 5, "image_guidance_scale": 2, "max_input_image_side_length": 2048 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2025-06-25T19:04:46.115672Z", "created_at": "2025-06-25T19:03:16.383000Z", "data_removed": false, "error": null, "id": "6pr3ztrjkxrm80cqn1wvnh2egc", "input": { "seed": -1, "image": "https://replicate.delivery/pbxt/NFVZYQi8xmHzWy2wH0FYGoIC366rDdXNvvh8hqBPPG6Kx69f/game-character.png", "width": 1024, "height": 1024, "prompt": " replace the sword with a hammer", "scheduler": "euler", "max_pixels": 1048576, "cfg_range_end": 1, "cfg_range_start": 0, "negative_prompt": "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar", "num_inference_steps": 50, "text_guidance_scale": 5, "image_guidance_scale": 2, "max_input_image_side_length": 2048 }, "logs": "0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:01<01:26, 1.76s/it]\n 4%|▍ | 2/50 [00:03<01:20, 1.67s/it]\n 6%|▌ | 3/50 [00:05<01:20, 1.71s/it]\n 8%|▊ | 4/50 [00:06<01:19, 1.73s/it]\n 10%|█ | 5/50 [00:08<01:18, 1.75s/it]\n 12%|█▏ | 6/50 [00:10<01:17, 1.75s/it]\n 14%|█▍ | 7/50 [00:12<01:15, 1.76s/it]\n 16%|█▌ | 8/50 [00:13<01:14, 1.76s/it]\n 18%|█▊ | 9/50 [00:15<01:12, 1.77s/it]\n 20%|██ | 10/50 [00:17<01:10, 1.77s/it]\n 22%|██▏ | 11/50 [00:19<01:09, 1.77s/it]\n 24%|██▍ | 12/50 [00:21<01:07, 1.77s/it]\n 26%|██▌ | 13/50 [00:22<01:05, 1.77s/it]\n 28%|██▊ | 14/50 [00:24<01:03, 1.77s/it]\n 30%|███ | 15/50 [00:26<01:02, 1.77s/it]\n 32%|███▏ | 16/50 [00:28<01:00, 1.77s/it]\n 34%|███▍ | 17/50 [00:29<00:58, 1.78s/it]\n 36%|███▌ | 18/50 [00:31<00:56, 1.77s/it]\n 38%|███▊ | 19/50 [00:33<00:55, 1.78s/it]\n 40%|████ | 20/50 [00:35<00:53, 1.77s/it]\n 42%|████▏ | 21/50 [00:37<00:51, 1.78s/it]\n 44%|████▍ | 22/50 [00:38<00:49, 1.78s/it]\n 46%|████▌ | 23/50 [00:40<00:47, 1.78s/it]\n 48%|████▊ | 24/50 [00:42<00:46, 1.78s/it]\n 50%|█████ | 25/50 [00:44<00:44, 1.78s/it]\n 52%|█████▏ | 26/50 [00:45<00:42, 1.78s/it]\n 54%|█████▍ | 27/50 [00:47<00:40, 1.78s/it]\n 56%|█████▌ | 28/50 [00:49<00:39, 1.78s/it]\n 58%|█████▊ | 29/50 [00:51<00:37, 1.78s/it]\n 60%|██████ | 30/50 [00:53<00:35, 1.78s/it]\n 62%|██████▏ | 31/50 [00:54<00:33, 1.78s/it]\n 64%|██████▍ | 32/50 [00:56<00:31, 1.78s/it]\n 66%|██████▌ | 33/50 [00:58<00:30, 1.78s/it]\n 68%|██████▊ | 34/50 [01:00<00:28, 1.78s/it]\n 70%|███████ | 35/50 [01:01<00:26, 1.78s/it]\n 72%|███████▏ | 36/50 [01:03<00:24, 1.78s/it]\n 74%|███████▍ | 37/50 [01:05<00:23, 1.78s/it]\n 76%|███████▌ | 38/50 [01:07<00:21, 1.78s/it]\n 78%|███████▊ | 39/50 [01:09<00:19, 1.78s/it]\n 80%|████████ | 40/50 [01:10<00:17, 1.78s/it]\n 82%|████████▏ | 41/50 [01:12<00:16, 1.78s/it]\n 84%|████████▍ | 42/50 [01:14<00:14, 1.78s/it]\n 86%|████████▌ | 43/50 [01:16<00:12, 1.78s/it]\n 88%|████████▊ | 44/50 [01:17<00:10, 1.78s/it]\n 90%|█████████ | 45/50 [01:19<00:08, 1.78s/it]\n 92%|█████████▏| 46/50 [01:21<00:07, 1.78s/it]\n 94%|█████████▍| 47/50 [01:23<00:05, 1.78s/it]\n 96%|█████████▌| 48/50 [01:25<00:03, 1.78s/it]\n 98%|█████████▊| 49/50 [01:26<00:01, 1.78s/it]\n100%|██████████| 50/50 [01:28<00:00, 1.78s/it]\n100%|██████████| 50/50 [01:28<00:00, 1.77s/it]", "metrics": { "predict_time": 89.724441757, "total_time": 89.732672 }, "output": "https://replicate.delivery/xezq/4WJWQ1GuJhKSHtBYUOdQdec2GNaejBnffAXU1vVWDu85keTnC/output.png", "started_at": "2025-06-25T19:03:16.391231Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bcwr-fxow6wbupwti6cte24hprgygrftj7fsa4s4nrc2vau6vhdsik7uq", "get": "https://api.replicate.com/v1/predictions/6pr3ztrjkxrm80cqn1wvnh2egc", "cancel": "https://api.replicate.com/v1/predictions/6pr3ztrjkxrm80cqn1wvnh2egc/cancel" }, "version": "5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502e" }
Generated in0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:01<01:26, 1.76s/it] 4%|▍ | 2/50 [00:03<01:20, 1.67s/it] 6%|▌ | 3/50 [00:05<01:20, 1.71s/it] 8%|▊ | 4/50 [00:06<01:19, 1.73s/it] 10%|█ | 5/50 [00:08<01:18, 1.75s/it] 12%|█▏ | 6/50 [00:10<01:17, 1.75s/it] 14%|█▍ | 7/50 [00:12<01:15, 1.76s/it] 16%|█▌ | 8/50 [00:13<01:14, 1.76s/it] 18%|█▊ | 9/50 [00:15<01:12, 1.77s/it] 20%|██ | 10/50 [00:17<01:10, 1.77s/it] 22%|██▏ | 11/50 [00:19<01:09, 1.77s/it] 24%|██▍ | 12/50 [00:21<01:07, 1.77s/it] 26%|██▌ | 13/50 [00:22<01:05, 1.77s/it] 28%|██▊ | 14/50 [00:24<01:03, 1.77s/it] 30%|███ | 15/50 [00:26<01:02, 1.77s/it] 32%|███▏ | 16/50 [00:28<01:00, 1.77s/it] 34%|███▍ | 17/50 [00:29<00:58, 1.78s/it] 36%|███▌ | 18/50 [00:31<00:56, 1.77s/it] 38%|███▊ | 19/50 [00:33<00:55, 1.78s/it] 40%|████ | 20/50 [00:35<00:53, 1.77s/it] 42%|████▏ | 21/50 [00:37<00:51, 1.78s/it] 44%|████▍ | 22/50 [00:38<00:49, 1.78s/it] 46%|████▌ | 23/50 [00:40<00:47, 1.78s/it] 48%|████▊ | 24/50 [00:42<00:46, 1.78s/it] 50%|█████ | 25/50 [00:44<00:44, 1.78s/it] 52%|█████▏ | 26/50 [00:45<00:42, 1.78s/it] 54%|█████▍ | 27/50 [00:47<00:40, 1.78s/it] 56%|█████▌ | 28/50 [00:49<00:39, 1.78s/it] 58%|█████▊ | 29/50 [00:51<00:37, 1.78s/it] 60%|██████ | 30/50 [00:53<00:35, 1.78s/it] 62%|██████▏ | 31/50 [00:54<00:33, 1.78s/it] 64%|██████▍ | 32/50 [00:56<00:31, 1.78s/it] 66%|██████▌ | 33/50 [00:58<00:30, 1.78s/it] 68%|██████▊ | 34/50 [01:00<00:28, 1.78s/it] 70%|███████ | 35/50 [01:01<00:26, 1.78s/it] 72%|███████▏ | 36/50 [01:03<00:24, 1.78s/it] 74%|███████▍ | 37/50 [01:05<00:23, 1.78s/it] 76%|███████▌ | 38/50 [01:07<00:21, 1.78s/it] 78%|███████▊ | 39/50 [01:09<00:19, 1.78s/it] 80%|████████ | 40/50 [01:10<00:17, 1.78s/it] 82%|████████▏ | 41/50 [01:12<00:16, 1.78s/it] 84%|████████▍ | 42/50 [01:14<00:14, 1.78s/it] 86%|████████▌ | 43/50 [01:16<00:12, 1.78s/it] 88%|████████▊ | 44/50 [01:17<00:10, 1.78s/it] 90%|█████████ | 45/50 [01:19<00:08, 1.78s/it] 92%|█████████▏| 46/50 [01:21<00:07, 1.78s/it] 94%|█████████▍| 47/50 [01:23<00:05, 1.78s/it] 96%|█████████▌| 48/50 [01:25<00:03, 1.78s/it] 98%|█████████▊| 49/50 [01:26<00:01, 1.78s/it] 100%|██████████| 50/50 [01:28<00:00, 1.78s/it] 100%|██████████| 50/50 [01:28<00:00, 1.77s/it]
Prediction
lucataco/omnigen2:5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502eID026kfreed5rmc0cqn1x9zvkxtrStatusSucceededSourceWebHardwareL40STotal durationCreatedInput
- seed
- -1
- width
- 1024
- height
- 1024
- prompt
- Extract the character from the picture and fill the rest of the background with white
- scheduler
- euler
- max_pixels
- 1048576
- cfg_range_end
- 1
- cfg_range_start
- 0
- negative_prompt
- (((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar
- num_inference_steps
- 50
- text_guidance_scale
- 5
- image_guidance_scale
- 2
- max_input_image_side_length
- 2048
{ "seed": -1, "image": "https://replicate.delivery/pbxt/NFVcsyiluPUsH7EKQbYlhvrEX5TvqRKpi9TWEuN66BSLSAFS/anime-maid.png", "width": 1024, "height": 1024, "prompt": "Extract the character from the picture and fill the rest of the background with white", "scheduler": "euler", "max_pixels": 1048576, "cfg_range_end": 1, "cfg_range_start": 0, "negative_prompt": "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar", "num_inference_steps": 50, "text_guidance_scale": 5, "image_guidance_scale": 2, "max_input_image_side_length": 2048 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run lucataco/omnigen2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/omnigen2:5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502e", { input: { seed: -1, image: "https://replicate.delivery/pbxt/NFVcsyiluPUsH7EKQbYlhvrEX5TvqRKpi9TWEuN66BSLSAFS/anime-maid.png", width: 1024, height: 1024, prompt: "Extract the character from the picture and fill the rest of the background with white", scheduler: "euler", max_pixels: 1048576, cfg_range_end: 1, cfg_range_start: 0, negative_prompt: "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar", num_inference_steps: 50, text_guidance_scale: 5, image_guidance_scale: 2, max_input_image_side_length: 2048 } } ); // 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 lucataco/omnigen2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/omnigen2:5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502e", input={ "seed": -1, "image": "https://replicate.delivery/pbxt/NFVcsyiluPUsH7EKQbYlhvrEX5TvqRKpi9TWEuN66BSLSAFS/anime-maid.png", "width": 1024, "height": 1024, "prompt": "Extract the character from the picture and fill the rest of the background with white", "scheduler": "euler", "max_pixels": 1048576, "cfg_range_end": 1, "cfg_range_start": 0, "negative_prompt": "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar", "num_inference_steps": 50, "text_guidance_scale": 5, "image_guidance_scale": 2, "max_input_image_side_length": 2048 } ) # To access the file URL: print(output.url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output.read())
To learn more, take a look at the guide on getting started with Python.
Run lucataco/omnigen2 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": "lucataco/omnigen2:5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502e", "input": { "seed": -1, "image": "https://replicate.delivery/pbxt/NFVcsyiluPUsH7EKQbYlhvrEX5TvqRKpi9TWEuN66BSLSAFS/anime-maid.png", "width": 1024, "height": 1024, "prompt": "Extract the character from the picture and fill the rest of the background with white", "scheduler": "euler", "max_pixels": 1048576, "cfg_range_end": 1, "cfg_range_start": 0, "negative_prompt": "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar", "num_inference_steps": 50, "text_guidance_scale": 5, "image_guidance_scale": 2, "max_input_image_side_length": 2048 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cog
If you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/lucataco/omnigen2@sha256:5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502e \ -i 'seed=-1' \ -i 'image="https://replicate.delivery/pbxt/NFVcsyiluPUsH7EKQbYlhvrEX5TvqRKpi9TWEuN66BSLSAFS/anime-maid.png"' \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="Extract the character from the picture and fill the rest of the background with white"' \ -i 'scheduler="euler"' \ -i 'max_pixels=1048576' \ -i 'cfg_range_end=1' \ -i 'cfg_range_start=0' \ -i 'negative_prompt="(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar"' \ -i 'num_inference_steps=50' \ -i 'text_guidance_scale=5' \ -i 'image_guidance_scale=2' \ -i 'max_input_image_side_length=2048'
To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/lucataco/omnigen2@sha256:5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502e
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "seed": -1, "image": "https://replicate.delivery/pbxt/NFVcsyiluPUsH7EKQbYlhvrEX5TvqRKpi9TWEuN66BSLSAFS/anime-maid.png", "width": 1024, "height": 1024, "prompt": "Extract the character from the picture and fill the rest of the background with white", "scheduler": "euler", "max_pixels": 1048576, "cfg_range_end": 1, "cfg_range_start": 0, "negative_prompt": "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar", "num_inference_steps": 50, "text_guidance_scale": 5, "image_guidance_scale": 2, "max_input_image_side_length": 2048 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2025-06-25T19:06:39.276396Z", "created_at": "2025-06-25T19:05:09.993000Z", "data_removed": false, "error": null, "id": "026kfreed5rmc0cqn1x9zvkxtr", "input": { "seed": -1, "image": "https://replicate.delivery/pbxt/NFVcsyiluPUsH7EKQbYlhvrEX5TvqRKpi9TWEuN66BSLSAFS/anime-maid.png", "width": 1024, "height": 1024, "prompt": "Extract the character from the picture and fill the rest of the background with white", "scheduler": "euler", "max_pixels": 1048576, "cfg_range_end": 1, "cfg_range_start": 0, "negative_prompt": "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar", "num_inference_steps": 50, "text_guidance_scale": 5, "image_guidance_scale": 2, "max_input_image_side_length": 2048 }, "logs": "0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:01<01:26, 1.76s/it]\n 4%|▍ | 2/50 [00:03<01:19, 1.66s/it]\n 6%|▌ | 3/50 [00:05<01:20, 1.71s/it]\n 8%|▊ | 4/50 [00:06<01:19, 1.73s/it]\n 10%|█ | 5/50 [00:08<01:18, 1.74s/it]\n 12%|█▏ | 6/50 [00:10<01:16, 1.75s/it]\n 14%|█▍ | 7/50 [00:12<01:15, 1.75s/it]\n 16%|█▌ | 8/50 [00:13<01:13, 1.76s/it]\n 18%|█▊ | 9/50 [00:15<01:12, 1.76s/it]\n 20%|██ | 10/50 [00:17<01:10, 1.76s/it]\n 22%|██▏ | 11/50 [00:19<01:08, 1.76s/it]\n 24%|██▍ | 12/50 [00:20<01:07, 1.76s/it]\n 26%|██▌ | 13/50 [00:22<01:05, 1.77s/it]\n 28%|██▊ | 14/50 [00:24<01:03, 1.77s/it]\n 30%|███ | 15/50 [00:26<01:01, 1.77s/it]\n 32%|███▏ | 16/50 [00:28<01:00, 1.77s/it]\n 34%|███▍ | 17/50 [00:29<00:58, 1.77s/it]\n 36%|███▌ | 18/50 [00:31<00:56, 1.77s/it]\n 38%|███▊ | 19/50 [00:33<00:54, 1.77s/it]\n 40%|████ | 20/50 [00:35<00:53, 1.77s/it]\n 42%|████▏ | 21/50 [00:36<00:51, 1.77s/it]\n 44%|████▍ | 22/50 [00:38<00:49, 1.77s/it]\n 46%|████▌ | 23/50 [00:40<00:47, 1.77s/it]\n 48%|████▊ | 24/50 [00:42<00:46, 1.77s/it]\n 50%|█████ | 25/50 [00:44<00:44, 1.77s/it]\n 52%|█████▏ | 26/50 [00:45<00:42, 1.78s/it]\n 54%|█████▍ | 27/50 [00:47<00:40, 1.78s/it]\n 56%|█████▌ | 28/50 [00:49<00:39, 1.78s/it]\n 58%|█████▊ | 29/50 [00:51<00:37, 1.78s/it]\n 60%|██████ | 30/50 [00:52<00:35, 1.78s/it]\n 62%|██████▏ | 31/50 [00:54<00:33, 1.78s/it]\n 64%|██████▍ | 32/50 [00:56<00:31, 1.78s/it]\n 66%|██████▌ | 33/50 [00:58<00:30, 1.78s/it]\n 68%|██████▊ | 34/50 [01:00<00:28, 1.78s/it]\n 70%|███████ | 35/50 [01:01<00:26, 1.78s/it]\n 72%|███████▏ | 36/50 [01:03<00:24, 1.78s/it]\n 74%|███████▍ | 37/50 [01:05<00:23, 1.78s/it]\n 76%|███████▌ | 38/50 [01:07<00:21, 1.78s/it]\n 78%|███████▊ | 39/50 [01:08<00:19, 1.78s/it]\n 80%|████████ | 40/50 [01:10<00:17, 1.78s/it]\n 82%|████████▏ | 41/50 [01:12<00:16, 1.78s/it]\n 84%|████████▍ | 42/50 [01:14<00:14, 1.78s/it]\n 86%|████████▌ | 43/50 [01:16<00:12, 1.78s/it]\n 88%|████████▊ | 44/50 [01:17<00:10, 1.78s/it]\n 90%|█████████ | 45/50 [01:19<00:08, 1.78s/it]\n 92%|█████████▏| 46/50 [01:21<00:07, 1.78s/it]\n 94%|█████████▍| 47/50 [01:23<00:05, 1.78s/it]\n 96%|█████████▌| 48/50 [01:24<00:03, 1.78s/it]\n 98%|█████████▊| 49/50 [01:26<00:01, 1.78s/it]\n100%|██████████| 50/50 [01:28<00:00, 1.78s/it]\n100%|██████████| 50/50 [01:28<00:00, 1.77s/it]", "metrics": { "predict_time": 89.276458055, "total_time": 89.283396 }, "output": "https://replicate.delivery/xezq/2TWpUkHVeGWzeEUhZcY2vnksehlQI8faD2ElEPGr4ecev6nOF/output.png", "started_at": "2025-06-25T19:05:09.999938Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bcwr-cow3k3ihygjz4gghfve4orfu5ra6torchw446onuoiujwpb3ep2a", "get": "https://api.replicate.com/v1/predictions/026kfreed5rmc0cqn1x9zvkxtr", "cancel": "https://api.replicate.com/v1/predictions/026kfreed5rmc0cqn1x9zvkxtr/cancel" }, "version": "5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502e" }
Generated in0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:01<01:26, 1.76s/it] 4%|▍ | 2/50 [00:03<01:19, 1.66s/it] 6%|▌ | 3/50 [00:05<01:20, 1.71s/it] 8%|▊ | 4/50 [00:06<01:19, 1.73s/it] 10%|█ | 5/50 [00:08<01:18, 1.74s/it] 12%|█▏ | 6/50 [00:10<01:16, 1.75s/it] 14%|█▍ | 7/50 [00:12<01:15, 1.75s/it] 16%|█▌ | 8/50 [00:13<01:13, 1.76s/it] 18%|█▊ | 9/50 [00:15<01:12, 1.76s/it] 20%|██ | 10/50 [00:17<01:10, 1.76s/it] 22%|██▏ | 11/50 [00:19<01:08, 1.76s/it] 24%|██▍ | 12/50 [00:20<01:07, 1.76s/it] 26%|██▌ | 13/50 [00:22<01:05, 1.77s/it] 28%|██▊ | 14/50 [00:24<01:03, 1.77s/it] 30%|███ | 15/50 [00:26<01:01, 1.77s/it] 32%|███▏ | 16/50 [00:28<01:00, 1.77s/it] 34%|███▍ | 17/50 [00:29<00:58, 1.77s/it] 36%|███▌ | 18/50 [00:31<00:56, 1.77s/it] 38%|███▊ | 19/50 [00:33<00:54, 1.77s/it] 40%|████ | 20/50 [00:35<00:53, 1.77s/it] 42%|████▏ | 21/50 [00:36<00:51, 1.77s/it] 44%|████▍ | 22/50 [00:38<00:49, 1.77s/it] 46%|████▌ | 23/50 [00:40<00:47, 1.77s/it] 48%|████▊ | 24/50 [00:42<00:46, 1.77s/it] 50%|█████ | 25/50 [00:44<00:44, 1.77s/it] 52%|█████▏ | 26/50 [00:45<00:42, 1.78s/it] 54%|█████▍ | 27/50 [00:47<00:40, 1.78s/it] 56%|█████▌ | 28/50 [00:49<00:39, 1.78s/it] 58%|█████▊ | 29/50 [00:51<00:37, 1.78s/it] 60%|██████ | 30/50 [00:52<00:35, 1.78s/it] 62%|██████▏ | 31/50 [00:54<00:33, 1.78s/it] 64%|██████▍ | 32/50 [00:56<00:31, 1.78s/it] 66%|██████▌ | 33/50 [00:58<00:30, 1.78s/it] 68%|██████▊ | 34/50 [01:00<00:28, 1.78s/it] 70%|███████ | 35/50 [01:01<00:26, 1.78s/it] 72%|███████▏ | 36/50 [01:03<00:24, 1.78s/it] 74%|███████▍ | 37/50 [01:05<00:23, 1.78s/it] 76%|███████▌ | 38/50 [01:07<00:21, 1.78s/it] 78%|███████▊ | 39/50 [01:08<00:19, 1.78s/it] 80%|████████ | 40/50 [01:10<00:17, 1.78s/it] 82%|████████▏ | 41/50 [01:12<00:16, 1.78s/it] 84%|████████▍ | 42/50 [01:14<00:14, 1.78s/it] 86%|████████▌ | 43/50 [01:16<00:12, 1.78s/it] 88%|████████▊ | 44/50 [01:17<00:10, 1.78s/it] 90%|█████████ | 45/50 [01:19<00:08, 1.78s/it] 92%|█████████▏| 46/50 [01:21<00:07, 1.78s/it] 94%|█████████▍| 47/50 [01:23<00:05, 1.78s/it] 96%|█████████▌| 48/50 [01:24<00:03, 1.78s/it] 98%|█████████▊| 49/50 [01:26<00:01, 1.78s/it] 100%|██████████| 50/50 [01:28<00:00, 1.78s/it] 100%|██████████| 50/50 [01:28<00:00, 1.77s/it]
Prediction
lucataco/omnigen2:5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502eIDvzm2zh9krsrm80cqn2dtvve9ycStatusSucceededSourceWebHardwareL40STotal durationCreatedInput
- seed
- -1
- width
- 1024
- height
- 1024
- prompt
- Have the woman in image 1 hold the toy from image 2 in a parking lot
- scheduler
- euler
- max_pixels
- 1048576
- cfg_range_end
- 1
- cfg_range_start
- 0
- negative_prompt
- (((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar
- num_inference_steps
- 50
- text_guidance_scale
- 5
- image_guidance_scale
- 2
- max_input_image_side_length
- 2048
{ "seed": -1, "image": "https://replicate.delivery/pbxt/NFWAPnaQncexIZvj8jiMcfbfSPzmSppKextJ2y1RORp3GkCO/woman-phone.jpg", "width": 1024, "height": 1024, "prompt": "Have the woman in image 1 hold the toy from image 2 in a parking lot", "image_2": "https://replicate.delivery/pbxt/NFWAQ4XlfvP1hivIuuWqm2krzyEgE2LOUZM6LrC9bJhrp9nJ/red-toy.jpg", "scheduler": "euler", "max_pixels": 1048576, "cfg_range_end": 1, "cfg_range_start": 0, "negative_prompt": "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar", "num_inference_steps": 50, "text_guidance_scale": 5, "image_guidance_scale": 2, "max_input_image_side_length": 2048 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run lucataco/omnigen2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/omnigen2:5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502e", { input: { seed: -1, image: "https://replicate.delivery/pbxt/NFWAPnaQncexIZvj8jiMcfbfSPzmSppKextJ2y1RORp3GkCO/woman-phone.jpg", width: 1024, height: 1024, prompt: "Have the woman in image 1 hold the toy from image 2 in a parking lot", image_2: "https://replicate.delivery/pbxt/NFWAQ4XlfvP1hivIuuWqm2krzyEgE2LOUZM6LrC9bJhrp9nJ/red-toy.jpg", scheduler: "euler", max_pixels: 1048576, cfg_range_end: 1, cfg_range_start: 0, negative_prompt: "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar", num_inference_steps: 50, text_guidance_scale: 5, image_guidance_scale: 2, max_input_image_side_length: 2048 } } ); // 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 lucataco/omnigen2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/omnigen2:5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502e", input={ "seed": -1, "image": "https://replicate.delivery/pbxt/NFWAPnaQncexIZvj8jiMcfbfSPzmSppKextJ2y1RORp3GkCO/woman-phone.jpg", "width": 1024, "height": 1024, "prompt": "Have the woman in image 1 hold the toy from image 2 in a parking lot", "image_2": "https://replicate.delivery/pbxt/NFWAQ4XlfvP1hivIuuWqm2krzyEgE2LOUZM6LrC9bJhrp9nJ/red-toy.jpg", "scheduler": "euler", "max_pixels": 1048576, "cfg_range_end": 1, "cfg_range_start": 0, "negative_prompt": "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar", "num_inference_steps": 50, "text_guidance_scale": 5, "image_guidance_scale": 2, "max_input_image_side_length": 2048 } ) # To access the file URL: print(output.url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output.read())
To learn more, take a look at the guide on getting started with Python.
Run lucataco/omnigen2 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": "lucataco/omnigen2:5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502e", "input": { "seed": -1, "image": "https://replicate.delivery/pbxt/NFWAPnaQncexIZvj8jiMcfbfSPzmSppKextJ2y1RORp3GkCO/woman-phone.jpg", "width": 1024, "height": 1024, "prompt": "Have the woman in image 1 hold the toy from image 2 in a parking lot", "image_2": "https://replicate.delivery/pbxt/NFWAQ4XlfvP1hivIuuWqm2krzyEgE2LOUZM6LrC9bJhrp9nJ/red-toy.jpg", "scheduler": "euler", "max_pixels": 1048576, "cfg_range_end": 1, "cfg_range_start": 0, "negative_prompt": "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar", "num_inference_steps": 50, "text_guidance_scale": 5, "image_guidance_scale": 2, "max_input_image_side_length": 2048 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cog
If you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/lucataco/omnigen2@sha256:5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502e \ -i 'seed=-1' \ -i 'image="https://replicate.delivery/pbxt/NFWAPnaQncexIZvj8jiMcfbfSPzmSppKextJ2y1RORp3GkCO/woman-phone.jpg"' \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="Have the woman in image 1 hold the toy from image 2 in a parking lot"' \ -i 'image_2="https://replicate.delivery/pbxt/NFWAQ4XlfvP1hivIuuWqm2krzyEgE2LOUZM6LrC9bJhrp9nJ/red-toy.jpg"' \ -i 'scheduler="euler"' \ -i 'max_pixels=1048576' \ -i 'cfg_range_end=1' \ -i 'cfg_range_start=0' \ -i 'negative_prompt="(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar"' \ -i 'num_inference_steps=50' \ -i 'text_guidance_scale=5' \ -i 'image_guidance_scale=2' \ -i 'max_input_image_side_length=2048'
To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/lucataco/omnigen2@sha256:5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502e
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "seed": -1, "image": "https://replicate.delivery/pbxt/NFWAPnaQncexIZvj8jiMcfbfSPzmSppKextJ2y1RORp3GkCO/woman-phone.jpg", "width": 1024, "height": 1024, "prompt": "Have the woman in image 1 hold the toy from image 2 in a parking lot", "image_2": "https://replicate.delivery/pbxt/NFWAQ4XlfvP1hivIuuWqm2krzyEgE2LOUZM6LrC9bJhrp9nJ/red-toy.jpg", "scheduler": "euler", "max_pixels": 1048576, "cfg_range_end": 1, "cfg_range_start": 0, "negative_prompt": "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar", "num_inference_steps": 50, "text_guidance_scale": 5, "image_guidance_scale": 2, "max_input_image_side_length": 2048 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2025-06-25T19:43:03.077335Z", "created_at": "2025-06-25T19:40:33.094000Z", "data_removed": false, "error": null, "id": "vzm2zh9krsrm80cqn2dtvve9yc", "input": { "seed": -1, "image": "https://replicate.delivery/pbxt/NFWAPnaQncexIZvj8jiMcfbfSPzmSppKextJ2y1RORp3GkCO/woman-phone.jpg", "width": 1024, "height": 1024, "prompt": "Have the woman in image 1 hold the toy from image 2 in a parking lot", "image_2": "https://replicate.delivery/pbxt/NFWAQ4XlfvP1hivIuuWqm2krzyEgE2LOUZM6LrC9bJhrp9nJ/red-toy.jpg", "scheduler": "euler", "max_pixels": 1048576, "cfg_range_end": 1, "cfg_range_start": 0, "negative_prompt": "(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar", "num_inference_steps": 50, "text_guidance_scale": 5, "image_guidance_scale": 2, "max_input_image_side_length": 2048 }, "logs": "0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:02<02:25, 2.97s/it]\n 4%|▍ | 2/50 [00:05<02:18, 2.88s/it]\n 6%|▌ | 3/50 [00:08<02:17, 2.93s/it]\n 8%|▊ | 4/50 [00:11<02:15, 2.95s/it]\n 10%|█ | 5/50 [00:14<02:13, 2.96s/it]\n 12%|█▏ | 6/50 [00:17<02:10, 2.97s/it]\n 14%|█▍ | 7/50 [00:20<02:07, 2.97s/it]\n 16%|█▌ | 8/50 [00:23<02:04, 2.97s/it]\n 18%|█▊ | 9/50 [00:26<02:01, 2.97s/it]\n 20%|██ | 10/50 [00:29<01:59, 2.98s/it]\n 22%|██▏ | 11/50 [00:32<01:56, 2.98s/it]\n 24%|██▍ | 12/50 [00:35<01:53, 2.98s/it]\n 26%|██▌ | 13/50 [00:38<01:50, 2.98s/it]\n 28%|██▊ | 14/50 [00:41<01:47, 2.98s/it]\n 30%|███ | 15/50 [00:44<01:44, 2.98s/it]\n 32%|███▏ | 16/50 [00:47<01:41, 2.98s/it]\n 34%|███▍ | 17/50 [00:50<01:38, 2.98s/it]\n 36%|███▌ | 18/50 [00:53<01:35, 2.98s/it]\n 38%|███▊ | 19/50 [00:56<01:32, 2.98s/it]\n 40%|████ | 20/50 [00:59<01:29, 2.98s/it]\n 42%|████▏ | 21/50 [01:02<01:26, 2.98s/it]\n 44%|████▍ | 22/50 [01:05<01:23, 2.98s/it]\n 46%|████▌ | 23/50 [01:08<01:20, 2.98s/it]\n 48%|████▊ | 24/50 [01:11<01:17, 2.98s/it]\n 50%|█████ | 25/50 [01:14<01:14, 2.98s/it]\n 52%|█████▏ | 26/50 [01:17<01:11, 2.98s/it]\n 54%|█████▍ | 27/50 [01:20<01:08, 2.98s/it]\n 56%|█████▌ | 28/50 [01:23<01:05, 2.98s/it]\n 58%|█████▊ | 29/50 [01:26<01:02, 2.98s/it]\n 60%|██████ | 30/50 [01:29<00:59, 2.98s/it]\n 62%|██████▏ | 31/50 [01:32<00:56, 2.98s/it]\n 64%|██████▍ | 32/50 [01:35<00:53, 2.98s/it]\n 66%|██████▌ | 33/50 [01:38<00:50, 2.98s/it]\n 68%|██████▊ | 34/50 [01:41<00:47, 2.98s/it]\n 70%|███████ | 35/50 [01:44<00:44, 2.98s/it]\n 72%|███████▏ | 36/50 [01:47<00:41, 2.98s/it]\n 74%|███████▍ | 37/50 [01:50<00:38, 2.98s/it]\n 76%|███████▌ | 38/50 [01:53<00:35, 2.98s/it]\n 78%|███████▊ | 39/50 [01:56<00:32, 2.98s/it]\n 80%|████████ | 40/50 [01:58<00:29, 2.98s/it]\n 82%|████████▏ | 41/50 [02:01<00:26, 2.98s/it]\n 84%|████████▍ | 42/50 [02:04<00:23, 2.98s/it]\n 86%|████████▌ | 43/50 [02:07<00:20, 2.98s/it]\n 88%|████████▊ | 44/50 [02:10<00:17, 2.98s/it]\n 90%|█████████ | 45/50 [02:13<00:14, 2.98s/it]\n 92%|█████████▏| 46/50 [02:16<00:11, 2.98s/it]\n 94%|█████████▍| 47/50 [02:19<00:08, 2.98s/it]\n 96%|█████████▌| 48/50 [02:22<00:05, 2.98s/it]\n 98%|█████████▊| 49/50 [02:25<00:02, 2.98s/it]\n100%|██████████| 50/50 [02:28<00:00, 2.98s/it]\n100%|██████████| 50/50 [02:28<00:00, 2.98s/it]", "metrics": { "predict_time": 149.97379779, "total_time": 149.983335 }, "output": "https://replicate.delivery/xezq/6FZdUljf1Zx8FSFq25KEFVtwGE6QJuB1ixxyhAQD6vyjGQdKA/output.png", "started_at": "2025-06-25T19:40:33.103537Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bcwr-vulv5lllmumnu5aza4ek2dtcab5alurm7lldojitqe7mm5fq3bxa", "get": "https://api.replicate.com/v1/predictions/vzm2zh9krsrm80cqn2dtvve9yc", "cancel": "https://api.replicate.com/v1/predictions/vzm2zh9krsrm80cqn2dtvve9yc/cancel" }, "version": "5b9ea1d0821a60be9c861ebfc3513d121ecd8cab1932d3aa8d703e517988502e" }
Generated in0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:02<02:25, 2.97s/it] 4%|▍ | 2/50 [00:05<02:18, 2.88s/it] 6%|▌ | 3/50 [00:08<02:17, 2.93s/it] 8%|▊ | 4/50 [00:11<02:15, 2.95s/it] 10%|█ | 5/50 [00:14<02:13, 2.96s/it] 12%|█▏ | 6/50 [00:17<02:10, 2.97s/it] 14%|█▍ | 7/50 [00:20<02:07, 2.97s/it] 16%|█▌ | 8/50 [00:23<02:04, 2.97s/it] 18%|█▊ | 9/50 [00:26<02:01, 2.97s/it] 20%|██ | 10/50 [00:29<01:59, 2.98s/it] 22%|██▏ | 11/50 [00:32<01:56, 2.98s/it] 24%|██▍ | 12/50 [00:35<01:53, 2.98s/it] 26%|██▌ | 13/50 [00:38<01:50, 2.98s/it] 28%|██▊ | 14/50 [00:41<01:47, 2.98s/it] 30%|███ | 15/50 [00:44<01:44, 2.98s/it] 32%|███▏ | 16/50 [00:47<01:41, 2.98s/it] 34%|███▍ | 17/50 [00:50<01:38, 2.98s/it] 36%|███▌ | 18/50 [00:53<01:35, 2.98s/it] 38%|███▊ | 19/50 [00:56<01:32, 2.98s/it] 40%|████ | 20/50 [00:59<01:29, 2.98s/it] 42%|████▏ | 21/50 [01:02<01:26, 2.98s/it] 44%|████▍ | 22/50 [01:05<01:23, 2.98s/it] 46%|████▌ | 23/50 [01:08<01:20, 2.98s/it] 48%|████▊ | 24/50 [01:11<01:17, 2.98s/it] 50%|█████ | 25/50 [01:14<01:14, 2.98s/it] 52%|█████▏ | 26/50 [01:17<01:11, 2.98s/it] 54%|█████▍ | 27/50 [01:20<01:08, 2.98s/it] 56%|█████▌ | 28/50 [01:23<01:05, 2.98s/it] 58%|█████▊ | 29/50 [01:26<01:02, 2.98s/it] 60%|██████ | 30/50 [01:29<00:59, 2.98s/it] 62%|██████▏ | 31/50 [01:32<00:56, 2.98s/it] 64%|██████▍ | 32/50 [01:35<00:53, 2.98s/it] 66%|██████▌ | 33/50 [01:38<00:50, 2.98s/it] 68%|██████▊ | 34/50 [01:41<00:47, 2.98s/it] 70%|███████ | 35/50 [01:44<00:44, 2.98s/it] 72%|███████▏ | 36/50 [01:47<00:41, 2.98s/it] 74%|███████▍ | 37/50 [01:50<00:38, 2.98s/it] 76%|███████▌ | 38/50 [01:53<00:35, 2.98s/it] 78%|███████▊ | 39/50 [01:56<00:32, 2.98s/it] 80%|████████ | 40/50 [01:58<00:29, 2.98s/it] 82%|████████▏ | 41/50 [02:01<00:26, 2.98s/it] 84%|████████▍ | 42/50 [02:04<00:23, 2.98s/it] 86%|████████▌ | 43/50 [02:07<00:20, 2.98s/it] 88%|████████▊ | 44/50 [02:10<00:17, 2.98s/it] 90%|█████████ | 45/50 [02:13<00:14, 2.98s/it] 92%|█████████▏| 46/50 [02:16<00:11, 2.98s/it] 94%|█████████▍| 47/50 [02:19<00:08, 2.98s/it] 96%|█████████▌| 48/50 [02:22<00:05, 2.98s/it] 98%|█████████▊| 49/50 [02:25<00:02, 2.98s/it] 100%|██████████| 50/50 [02:28<00:00, 2.98s/it] 100%|██████████| 50/50 [02:28<00:00, 2.98s/it]
Want to make some of these yourself?
Run this model