chenxwh
/
onediffusion
One Diffusion to Generate Them All
Prediction
chenxwh/onediffusion:f69674f4ID9xn5mqc06srm80cm2zavj34x30StatusSucceededSourceWebHardwareL40STotal durationCreatedInput
- task
- deblurring
- width
- 1024
- height
- 1024
- prompt
- butterfly
- azimuth
- 0
- distance
- 1.5
- elevation
- 0
- focal_length
- 1.3887
- guidance_scale
- 4
- negative_prompt
- monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation
- num_inference_steps
- 50
- use_input_image_size
{ "task": "deblurring", "width": 1024, "height": 1024, "image1": "https://replicate.delivery/pbxt/MEbX6nnL8Eip806Wl6VzjxptZpGDNvTholK4Mt3ACclp4s6M/butterfly.jpeg", "prompt": "butterfly", "azimuth": "0", "distance": "1.5", "elevation": "0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": false }
npm install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run chenxwh/onediffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "chenxwh/onediffusion:f69674f4fc4fb6f6b085b7cd6a00a4ee5d7014d8f5b2dea7bc551cc996129307", { input: { task: "deblurring", width: 1024, height: 1024, image1: "https://replicate.delivery/pbxt/MEbX6nnL8Eip806Wl6VzjxptZpGDNvTholK4Mt3ACclp4s6M/butterfly.jpeg", prompt: "butterfly", azimuth: "0", distance: "1.5", elevation: "0", focal_length: 1.3887, guidance_scale: 4, negative_prompt: "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", num_inference_steps: 50, use_input_image_size: false } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the clientimport replicate
Run chenxwh/onediffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "chenxwh/onediffusion:f69674f4fc4fb6f6b085b7cd6a00a4ee5d7014d8f5b2dea7bc551cc996129307", input={ "task": "deblurring", "width": 1024, "height": 1024, "image1": "https://replicate.delivery/pbxt/MEbX6nnL8Eip806Wl6VzjxptZpGDNvTholK4Mt3ACclp4s6M/butterfly.jpeg", "prompt": "butterfly", "azimuth": "0", "distance": "1.5", "elevation": "0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": False } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run chenxwh/onediffusion 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": "f69674f4fc4fb6f6b085b7cd6a00a4ee5d7014d8f5b2dea7bc551cc996129307", "input": { "task": "deblurring", "width": 1024, "height": 1024, "image1": "https://replicate.delivery/pbxt/MEbX6nnL8Eip806Wl6VzjxptZpGDNvTholK4Mt3ACclp4s6M/butterfly.jpeg", "prompt": "butterfly", "azimuth": "0", "distance": "1.5", "elevation": "0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": false } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-12-30T13:53:14.631840Z", "created_at": "2024-12-30T13:50:55.542000Z", "data_removed": false, "error": null, "id": "9xn5mqc06srm80cm2zavj34x30", "input": { "task": "deblurring", "width": 1024, "height": 1024, "image1": "https://replicate.delivery/pbxt/MEbX6nnL8Eip806Wl6VzjxptZpGDNvTholK4Mt3ACclp4s6M/butterfly.jpeg", "prompt": "butterfly", "azimuth": "0", "distance": "1.5", "elevation": "0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": false }, "logs": "Using width, height: 1024, 1024\nUsing seed: 37636\nUsing prompt: [[deblurring]] butterfly\n/src/onediffusion/diffusion/pipelines/image_processor.py:572: FutureWarning: Passing `image` as torch tensor with value range in [-1,1] is deprecated. The expected value range for image tensor is [0,1] when passing as pytorch tensor or numpy Array. You passed `image` with value range [-0.9979166388511658,0.9479167461395264]\nwarnings.warn(\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:01<00:54, 1.10s/it]\n 4%|▍ | 2/50 [00:02<00:50, 1.06s/it]\n 6%|▌ | 3/50 [00:03<00:50, 1.08s/it]\n 8%|▊ | 4/50 [00:04<00:49, 1.08s/it]\n 10%|█ | 5/50 [00:05<00:48, 1.08s/it]\n 12%|█▏ | 6/50 [00:06<00:47, 1.09s/it]\n 14%|█▍ | 7/50 [00:07<00:46, 1.09s/it]\n 16%|█▌ | 8/50 [00:08<00:45, 1.09s/it]\n 18%|█▊ | 9/50 [00:09<00:44, 1.09s/it]\n 20%|██ | 10/50 [00:10<00:43, 1.09s/it]\n 22%|██▏ | 11/50 [00:11<00:42, 1.09s/it]\n 24%|██▍ | 12/50 [00:13<00:41, 1.09s/it]\n 26%|██▌ | 13/50 [00:14<00:40, 1.09s/it]\n 28%|██▊ | 14/50 [00:15<00:39, 1.09s/it]\n 30%|███ | 15/50 [00:16<00:38, 1.09s/it]\n 32%|███▏ | 16/50 [00:17<00:37, 1.09s/it]\n 34%|███▍ | 17/50 [00:18<00:36, 1.10s/it]\n 36%|███▌ | 18/50 [00:19<00:35, 1.10s/it]\n 38%|███▊ | 19/50 [00:20<00:33, 1.10s/it]\n 40%|████ | 20/50 [00:21<00:32, 1.10s/it]\n 42%|████▏ | 21/50 [00:22<00:31, 1.10s/it]\n 44%|████▍ | 22/50 [00:24<00:30, 1.10s/it]\n 46%|████▌ | 23/50 [00:25<00:29, 1.10s/it]\n 48%|████▊ | 24/50 [00:26<00:28, 1.10s/it]\n 50%|█████ | 25/50 [00:27<00:27, 1.10s/it]\n 52%|█████▏ | 26/50 [00:28<00:26, 1.10s/it]\n 54%|█████▍ | 27/50 [00:29<00:25, 1.10s/it]\n 56%|█████▌ | 28/50 [00:30<00:24, 1.10s/it]\n 58%|█████▊ | 29/50 [00:31<00:23, 1.10s/it]\n 60%|██████ | 30/50 [00:32<00:22, 1.10s/it]\n 62%|██████▏ | 31/50 [00:33<00:20, 1.10s/it]\n 64%|██████▍ | 32/50 [00:35<00:19, 1.10s/it]\n 66%|██████▌ | 33/50 [00:36<00:18, 1.10s/it]\n 68%|██████▊ | 34/50 [00:37<00:17, 1.10s/it]\n 70%|███████ | 35/50 [00:38<00:16, 1.10s/it]\n 72%|███████▏ | 36/50 [00:39<00:15, 1.10s/it]\n 74%|███████▍ | 37/50 [00:40<00:14, 1.11s/it]\n 76%|███████▌ | 38/50 [00:41<00:13, 1.11s/it]\n 78%|███████▊ | 39/50 [00:42<00:12, 1.11s/it]\n 80%|████████ | 40/50 [00:43<00:11, 1.11s/it]\n 82%|████████▏ | 41/50 [00:45<00:09, 1.11s/it]\n 84%|████████▍ | 42/50 [00:46<00:08, 1.11s/it]\n 86%|████████▌ | 43/50 [00:47<00:07, 1.11s/it]\n 88%|████████▊ | 44/50 [00:48<00:06, 1.11s/it]\n 90%|█████████ | 45/50 [00:49<00:05, 1.11s/it]\n 92%|█████████▏| 46/50 [00:50<00:04, 1.11s/it]\n 94%|█████████▍| 47/50 [00:51<00:03, 1.11s/it]\n 96%|█████████▌| 48/50 [00:52<00:02, 1.11s/it]\n 98%|█████████▊| 49/50 [00:53<00:01, 1.11s/it]\n100%|██████████| 50/50 [00:55<00:00, 1.11s/it]\n100%|██████████| 50/50 [00:55<00:00, 1.10s/it]", "metrics": { "predict_time": 56.066002, "total_time": 139.08984 }, "output": [ "https://replicate.delivery/xezq/D0lQhUK97dIXMxVfpMlhVGebzjeiFq5CAWVq2lGmNRBUeVAQB/out_0.png" ], "started_at": "2024-12-30T13:52:18.565838Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bcwr-xthvnpsavykswxtyqko23gk5yj5xm4prqmlq6gg25c6gxmz6tieq", "get": "https://api.replicate.com/v1/predictions/9xn5mqc06srm80cm2zavj34x30", "cancel": "https://api.replicate.com/v1/predictions/9xn5mqc06srm80cm2zavj34x30/cancel" }, "version": "ca6eb28dc33f2f85969c8b0c7c26e10bc94a586c221b373c78095e44bcae94d8" }
Generated inUsing width, height: 1024, 1024 Using seed: 37636 Using prompt: [[deblurring]] butterfly /src/onediffusion/diffusion/pipelines/image_processor.py:572: FutureWarning: Passing `image` as torch tensor with value range in [-1,1] is deprecated. The expected value range for image tensor is [0,1] when passing as pytorch tensor or numpy Array. You passed `image` with value range [-0.9979166388511658,0.9479167461395264] warnings.warn( 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:01<00:54, 1.10s/it] 4%|▍ | 2/50 [00:02<00:50, 1.06s/it] 6%|▌ | 3/50 [00:03<00:50, 1.08s/it] 8%|▊ | 4/50 [00:04<00:49, 1.08s/it] 10%|█ | 5/50 [00:05<00:48, 1.08s/it] 12%|█▏ | 6/50 [00:06<00:47, 1.09s/it] 14%|█▍ | 7/50 [00:07<00:46, 1.09s/it] 16%|█▌ | 8/50 [00:08<00:45, 1.09s/it] 18%|█▊ | 9/50 [00:09<00:44, 1.09s/it] 20%|██ | 10/50 [00:10<00:43, 1.09s/it] 22%|██▏ | 11/50 [00:11<00:42, 1.09s/it] 24%|██▍ | 12/50 [00:13<00:41, 1.09s/it] 26%|██▌ | 13/50 [00:14<00:40, 1.09s/it] 28%|██▊ | 14/50 [00:15<00:39, 1.09s/it] 30%|███ | 15/50 [00:16<00:38, 1.09s/it] 32%|███▏ | 16/50 [00:17<00:37, 1.09s/it] 34%|███▍ | 17/50 [00:18<00:36, 1.10s/it] 36%|███▌ | 18/50 [00:19<00:35, 1.10s/it] 38%|███▊ | 19/50 [00:20<00:33, 1.10s/it] 40%|████ | 20/50 [00:21<00:32, 1.10s/it] 42%|████▏ | 21/50 [00:22<00:31, 1.10s/it] 44%|████▍ | 22/50 [00:24<00:30, 1.10s/it] 46%|████▌ | 23/50 [00:25<00:29, 1.10s/it] 48%|████▊ | 24/50 [00:26<00:28, 1.10s/it] 50%|█████ | 25/50 [00:27<00:27, 1.10s/it] 52%|█████▏ | 26/50 [00:28<00:26, 1.10s/it] 54%|█████▍ | 27/50 [00:29<00:25, 1.10s/it] 56%|█████▌ | 28/50 [00:30<00:24, 1.10s/it] 58%|█████▊ | 29/50 [00:31<00:23, 1.10s/it] 60%|██████ | 30/50 [00:32<00:22, 1.10s/it] 62%|██████▏ | 31/50 [00:33<00:20, 1.10s/it] 64%|██████▍ | 32/50 [00:35<00:19, 1.10s/it] 66%|██████▌ | 33/50 [00:36<00:18, 1.10s/it] 68%|██████▊ | 34/50 [00:37<00:17, 1.10s/it] 70%|███████ | 35/50 [00:38<00:16, 1.10s/it] 72%|███████▏ | 36/50 [00:39<00:15, 1.10s/it] 74%|███████▍ | 37/50 [00:40<00:14, 1.11s/it] 76%|███████▌ | 38/50 [00:41<00:13, 1.11s/it] 78%|███████▊ | 39/50 [00:42<00:12, 1.11s/it] 80%|████████ | 40/50 [00:43<00:11, 1.11s/it] 82%|████████▏ | 41/50 [00:45<00:09, 1.11s/it] 84%|████████▍ | 42/50 [00:46<00:08, 1.11s/it] 86%|████████▌ | 43/50 [00:47<00:07, 1.11s/it] 88%|████████▊ | 44/50 [00:48<00:06, 1.11s/it] 90%|█████████ | 45/50 [00:49<00:05, 1.11s/it] 92%|█████████▏| 46/50 [00:50<00:04, 1.11s/it] 94%|█████████▍| 47/50 [00:51<00:03, 1.11s/it] 96%|█████████▌| 48/50 [00:52<00:02, 1.11s/it] 98%|█████████▊| 49/50 [00:53<00:01, 1.11s/it] 100%|██████████| 50/50 [00:55<00:00, 1.11s/it] 100%|██████████| 50/50 [00:55<00:00, 1.10s/it]
Prediction
chenxwh/onediffusion:f69674f4IDnazjcmn5zhrmc0cm2zbsg5983rStatusSucceededSourceWebHardwareL40STotal durationCreatedInput
- task
- image_inpainting
- width
- 1024
- height
- 1024
- azimuth
- 0
- distance
- 1.5
- elevation
- 0
- focal_length
- 1.3887
- guidance_scale
- 4
- negative_prompt
- monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation
- num_inference_steps
- 50
- use_input_image_size
{ "task": "image_inpainting", "width": 1024, "height": 1024, "image1": "https://replicate.delivery/pbxt/MEbZL7acKZPzVobWWhSEIdVboyNV9gyWSKuhPTEMpHTD00dI/giorno.webp", "azimuth": "0", "distance": "1.5", "elevation": "0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": true }
npm install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run chenxwh/onediffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "chenxwh/onediffusion:f69674f4fc4fb6f6b085b7cd6a00a4ee5d7014d8f5b2dea7bc551cc996129307", { input: { task: "image_inpainting", width: 1024, height: 1024, image1: "https://replicate.delivery/pbxt/MEbZL7acKZPzVobWWhSEIdVboyNV9gyWSKuhPTEMpHTD00dI/giorno.webp", azimuth: "0", distance: "1.5", elevation: "0", focal_length: 1.3887, guidance_scale: 4, negative_prompt: "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", num_inference_steps: 50, use_input_image_size: true } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the clientimport replicate
Run chenxwh/onediffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "chenxwh/onediffusion:f69674f4fc4fb6f6b085b7cd6a00a4ee5d7014d8f5b2dea7bc551cc996129307", input={ "task": "image_inpainting", "width": 1024, "height": 1024, "image1": "https://replicate.delivery/pbxt/MEbZL7acKZPzVobWWhSEIdVboyNV9gyWSKuhPTEMpHTD00dI/giorno.webp", "azimuth": "0", "distance": "1.5", "elevation": "0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": True } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run chenxwh/onediffusion 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": "f69674f4fc4fb6f6b085b7cd6a00a4ee5d7014d8f5b2dea7bc551cc996129307", "input": { "task": "image_inpainting", "width": 1024, "height": 1024, "image1": "https://replicate.delivery/pbxt/MEbZL7acKZPzVobWWhSEIdVboyNV9gyWSKuhPTEMpHTD00dI/giorno.webp", "azimuth": "0", "distance": "1.5", "elevation": "0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": true } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-12-30T13:53:26.439885Z", "created_at": "2024-12-30T13:53:16.284000Z", "data_removed": false, "error": null, "id": "nazjcmn5zhrmc0cm2zbsg5983r", "input": { "task": "image_inpainting", "width": 1024, "height": 1024, "image1": "https://replicate.delivery/pbxt/MEbZL7acKZPzVobWWhSEIdVboyNV9gyWSKuhPTEMpHTD00dI/giorno.webp", "azimuth": "0", "distance": "1.5", "elevation": "0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": true }, "logs": "Using width, height: 576, 416\nUsing seed: 54648\nUsing prompt: [[image_inpainting]] A bipedal black cat wearing a huge oversized witch hat, a wizards robe, casting a spell,in an enchanted forest. The scene is filled with fireflies and moss on surrounding rocks and trees\n/src/onediffusion/diffusion/pipelines/image_processor.py:572: FutureWarning: Passing `image` as torch tensor with value range in [-1,1] is deprecated. The expected value range for image tensor is [0,1] when passing as pytorch tensor or numpy Array. You passed `image` with value range [-1.0,1.0]\nwarnings.warn(\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:09, 5.10it/s]\n 4%|▍ | 2/50 [00:00<00:09, 5.22it/s]\n 6%|▌ | 3/50 [00:00<00:09, 5.16it/s]\n 8%|▊ | 4/50 [00:00<00:08, 5.12it/s]\n 10%|█ | 5/50 [00:00<00:08, 5.11it/s]\n 12%|█▏ | 6/50 [00:01<00:08, 5.09it/s]\n 14%|█▍ | 7/50 [00:01<00:08, 5.08it/s]\n 16%|█▌ | 8/50 [00:01<00:08, 5.08it/s]\n 18%|█▊ | 9/50 [00:01<00:08, 5.08it/s]\n 20%|██ | 10/50 [00:01<00:07, 5.07it/s]\n 22%|██▏ | 11/50 [00:02<00:07, 5.07it/s]\n 24%|██▍ | 12/50 [00:02<00:07, 5.07it/s]\n 26%|██▌ | 13/50 [00:02<00:07, 5.06it/s]\n 28%|██▊ | 14/50 [00:02<00:07, 5.06it/s]\n 30%|███ | 15/50 [00:02<00:06, 5.06it/s]\n 32%|███▏ | 16/50 [00:03<00:06, 5.05it/s]\n 34%|███▍ | 17/50 [00:03<00:06, 5.06it/s]\n 36%|███▌ | 18/50 [00:03<00:06, 5.06it/s]\n 38%|███▊ | 19/50 [00:03<00:06, 5.06it/s]\n 40%|████ | 20/50 [00:03<00:05, 5.06it/s]\n 42%|████▏ | 21/50 [00:04<00:05, 5.06it/s]\n 44%|████▍ | 22/50 [00:04<00:05, 5.06it/s]\n 46%|████▌ | 23/50 [00:04<00:05, 5.06it/s]\n 48%|████▊ | 24/50 [00:04<00:05, 5.06it/s]\n 50%|█████ | 25/50 [00:04<00:04, 5.06it/s]\n 52%|█████▏ | 26/50 [00:05<00:04, 5.06it/s]\n 54%|█████▍ | 27/50 [00:05<00:04, 5.06it/s]\n 56%|█████▌ | 28/50 [00:05<00:04, 5.06it/s]\n 58%|█████▊ | 29/50 [00:05<00:04, 5.06it/s]\n 60%|██████ | 30/50 [00:05<00:03, 5.06it/s]\n 62%|██████▏ | 31/50 [00:06<00:03, 5.06it/s]\n 64%|██████▍ | 32/50 [00:06<00:03, 5.06it/s]\n 66%|██████▌ | 33/50 [00:06<00:03, 5.06it/s]\n 68%|██████▊ | 34/50 [00:06<00:03, 5.05it/s]\n 70%|███████ | 35/50 [00:06<00:02, 5.05it/s]\n 72%|███████▏ | 36/50 [00:07<00:02, 5.05it/s]\n 74%|███████▍ | 37/50 [00:07<00:02, 5.05it/s]\n 76%|███████▌ | 38/50 [00:07<00:02, 5.05it/s]\n 78%|███████▊ | 39/50 [00:07<00:02, 5.05it/s]\n 80%|████████ | 40/50 [00:07<00:01, 5.05it/s]\n 82%|████████▏ | 41/50 [00:08<00:01, 5.05it/s]\n 84%|████████▍ | 42/50 [00:08<00:01, 5.05it/s]\n 86%|████████▌ | 43/50 [00:08<00:01, 5.05it/s]\n 88%|████████▊ | 44/50 [00:08<00:01, 5.06it/s]\n 90%|█████████ | 45/50 [00:08<00:00, 5.06it/s]\n 92%|█████████▏| 46/50 [00:09<00:00, 5.07it/s]\n 94%|█████████▍| 47/50 [00:09<00:00, 5.07it/s]\n 96%|█████████▌| 48/50 [00:09<00:00, 5.07it/s]\n 98%|█████████▊| 49/50 [00:09<00:00, 5.07it/s]\n100%|██████████| 50/50 [00:09<00:00, 5.07it/s]\n100%|██████████| 50/50 [00:09<00:00, 5.07it/s]", "metrics": { "predict_time": 10.147526536, "total_time": 10.155885 }, "output": [ "https://replicate.delivery/xezq/S3aTVdUsFm4iMFOlXf8Lj3y7486kRYjD3DwCD0O6lfAWfKAoA/out_0.png" ], "started_at": "2024-12-30T13:53:16.292358Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bcwr-3iisstfmobrrdaqb3cq7lgyyza3exczwiv2t4wz62rr36yzmbbxq", "get": "https://api.replicate.com/v1/predictions/nazjcmn5zhrmc0cm2zbsg5983r", "cancel": "https://api.replicate.com/v1/predictions/nazjcmn5zhrmc0cm2zbsg5983r/cancel" }, "version": "ca6eb28dc33f2f85969c8b0c7c26e10bc94a586c221b373c78095e44bcae94d8" }
Generated inUsing width, height: 576, 416 Using seed: 54648 Using prompt: [[image_inpainting]] A bipedal black cat wearing a huge oversized witch hat, a wizards robe, casting a spell,in an enchanted forest. The scene is filled with fireflies and moss on surrounding rocks and trees /src/onediffusion/diffusion/pipelines/image_processor.py:572: FutureWarning: Passing `image` as torch tensor with value range in [-1,1] is deprecated. The expected value range for image tensor is [0,1] when passing as pytorch tensor or numpy Array. You passed `image` with value range [-1.0,1.0] warnings.warn( 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:09, 5.10it/s] 4%|▍ | 2/50 [00:00<00:09, 5.22it/s] 6%|▌ | 3/50 [00:00<00:09, 5.16it/s] 8%|▊ | 4/50 [00:00<00:08, 5.12it/s] 10%|█ | 5/50 [00:00<00:08, 5.11it/s] 12%|█▏ | 6/50 [00:01<00:08, 5.09it/s] 14%|█▍ | 7/50 [00:01<00:08, 5.08it/s] 16%|█▌ | 8/50 [00:01<00:08, 5.08it/s] 18%|█▊ | 9/50 [00:01<00:08, 5.08it/s] 20%|██ | 10/50 [00:01<00:07, 5.07it/s] 22%|██▏ | 11/50 [00:02<00:07, 5.07it/s] 24%|██▍ | 12/50 [00:02<00:07, 5.07it/s] 26%|██▌ | 13/50 [00:02<00:07, 5.06it/s] 28%|██▊ | 14/50 [00:02<00:07, 5.06it/s] 30%|███ | 15/50 [00:02<00:06, 5.06it/s] 32%|███▏ | 16/50 [00:03<00:06, 5.05it/s] 34%|███▍ | 17/50 [00:03<00:06, 5.06it/s] 36%|███▌ | 18/50 [00:03<00:06, 5.06it/s] 38%|███▊ | 19/50 [00:03<00:06, 5.06it/s] 40%|████ | 20/50 [00:03<00:05, 5.06it/s] 42%|████▏ | 21/50 [00:04<00:05, 5.06it/s] 44%|████▍ | 22/50 [00:04<00:05, 5.06it/s] 46%|████▌ | 23/50 [00:04<00:05, 5.06it/s] 48%|████▊ | 24/50 [00:04<00:05, 5.06it/s] 50%|█████ | 25/50 [00:04<00:04, 5.06it/s] 52%|█████▏ | 26/50 [00:05<00:04, 5.06it/s] 54%|█████▍ | 27/50 [00:05<00:04, 5.06it/s] 56%|█████▌ | 28/50 [00:05<00:04, 5.06it/s] 58%|█████▊ | 29/50 [00:05<00:04, 5.06it/s] 60%|██████ | 30/50 [00:05<00:03, 5.06it/s] 62%|██████▏ | 31/50 [00:06<00:03, 5.06it/s] 64%|██████▍ | 32/50 [00:06<00:03, 5.06it/s] 66%|██████▌ | 33/50 [00:06<00:03, 5.06it/s] 68%|██████▊ | 34/50 [00:06<00:03, 5.05it/s] 70%|███████ | 35/50 [00:06<00:02, 5.05it/s] 72%|███████▏ | 36/50 [00:07<00:02, 5.05it/s] 74%|███████▍ | 37/50 [00:07<00:02, 5.05it/s] 76%|███████▌ | 38/50 [00:07<00:02, 5.05it/s] 78%|███████▊ | 39/50 [00:07<00:02, 5.05it/s] 80%|████████ | 40/50 [00:07<00:01, 5.05it/s] 82%|████████▏ | 41/50 [00:08<00:01, 5.05it/s] 84%|████████▍ | 42/50 [00:08<00:01, 5.05it/s] 86%|████████▌ | 43/50 [00:08<00:01, 5.05it/s] 88%|████████▊ | 44/50 [00:08<00:01, 5.06it/s] 90%|█████████ | 45/50 [00:08<00:00, 5.06it/s] 92%|█████████▏| 46/50 [00:09<00:00, 5.07it/s] 94%|█████████▍| 47/50 [00:09<00:00, 5.07it/s] 96%|█████████▌| 48/50 [00:09<00:00, 5.07it/s] 98%|█████████▊| 49/50 [00:09<00:00, 5.07it/s] 100%|██████████| 50/50 [00:09<00:00, 5.07it/s] 100%|██████████| 50/50 [00:09<00:00, 5.07it/s]
Prediction
chenxwh/onediffusion:f69674f4ID6trmn7p9qdrma0cm2zc8s9vtzcStatusSucceededSourceWebHardwareL40STotal durationCreatedInput
- task
- depth2image
- width
- 1024
- height
- 1024
- prompt
- The image depicts a futuristic astronaut standing on a rocky terrain with orange flowers. The astronaut is wearing a yellow suit with a helmet and is equipped with a backpack. The astronaut is looking up at a large, circular, glowing portal in the sky, which is surrounded by a halo of light. The portal is emitting a warm glow and is surrounded by a few butterflies. The sky is dark with stars, and there are distant mountains visible. The overall atmosphere of the image is one of exploration and wonder.
- azimuth
- 0
- distance
- 1.5
- elevation
- 0
- focal_length
- 1.3887
- guidance_scale
- 4
- negative_prompt
- monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation
- num_inference_steps
- 50
- use_input_image_size
{ "task": "depth2image", "width": 1024, "height": 1024, "image1": "https://replicate.delivery/pbxt/MEbaVgKE3z4ktO1hofUrhCTp23PNx1NNmR7jTRGPItHiGjeU/astronaut.webp", "prompt": "The image depicts a futuristic astronaut standing on a rocky terrain with orange flowers. The astronaut is wearing a yellow suit with a helmet and is equipped with a backpack. The astronaut is looking up at a large, circular, glowing portal in the sky, which is surrounded by a halo of light. The portal is emitting a warm glow and is surrounded by a few butterflies. The sky is dark with stars, and there are distant mountains visible. The overall atmosphere of the image is one of exploration and wonder.", "azimuth": "0", "distance": "1.5", "elevation": "0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": true }
npm install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run chenxwh/onediffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "chenxwh/onediffusion:f69674f4fc4fb6f6b085b7cd6a00a4ee5d7014d8f5b2dea7bc551cc996129307", { input: { task: "depth2image", width: 1024, height: 1024, image1: "https://replicate.delivery/pbxt/MEbaVgKE3z4ktO1hofUrhCTp23PNx1NNmR7jTRGPItHiGjeU/astronaut.webp", prompt: "The image depicts a futuristic astronaut standing on a rocky terrain with orange flowers. The astronaut is wearing a yellow suit with a helmet and is equipped with a backpack. The astronaut is looking up at a large, circular, glowing portal in the sky, which is surrounded by a halo of light. The portal is emitting a warm glow and is surrounded by a few butterflies. The sky is dark with stars, and there are distant mountains visible. The overall atmosphere of the image is one of exploration and wonder.", azimuth: "0", distance: "1.5", elevation: "0", focal_length: 1.3887, guidance_scale: 4, negative_prompt: "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", num_inference_steps: 50, use_input_image_size: true } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the clientimport replicate
Run chenxwh/onediffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "chenxwh/onediffusion:f69674f4fc4fb6f6b085b7cd6a00a4ee5d7014d8f5b2dea7bc551cc996129307", input={ "task": "depth2image", "width": 1024, "height": 1024, "image1": "https://replicate.delivery/pbxt/MEbaVgKE3z4ktO1hofUrhCTp23PNx1NNmR7jTRGPItHiGjeU/astronaut.webp", "prompt": "The image depicts a futuristic astronaut standing on a rocky terrain with orange flowers. The astronaut is wearing a yellow suit with a helmet and is equipped with a backpack. The astronaut is looking up at a large, circular, glowing portal in the sky, which is surrounded by a halo of light. The portal is emitting a warm glow and is surrounded by a few butterflies. The sky is dark with stars, and there are distant mountains visible. The overall atmosphere of the image is one of exploration and wonder.", "azimuth": "0", "distance": "1.5", "elevation": "0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": True } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run chenxwh/onediffusion 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": "f69674f4fc4fb6f6b085b7cd6a00a4ee5d7014d8f5b2dea7bc551cc996129307", "input": { "task": "depth2image", "width": 1024, "height": 1024, "image1": "https://replicate.delivery/pbxt/MEbaVgKE3z4ktO1hofUrhCTp23PNx1NNmR7jTRGPItHiGjeU/astronaut.webp", "prompt": "The image depicts a futuristic astronaut standing on a rocky terrain with orange flowers. The astronaut is wearing a yellow suit with a helmet and is equipped with a backpack. The astronaut is looking up at a large, circular, glowing portal in the sky, which is surrounded by a halo of light. The portal is emitting a warm glow and is surrounded by a few butterflies. The sky is dark with stars, and there are distant mountains visible. The overall atmosphere of the image is one of exploration and wonder.", "azimuth": "0", "distance": "1.5", "elevation": "0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": true } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-12-30T13:54:41.756469Z", "created_at": "2024-12-30T13:54:30.971000Z", "data_removed": false, "error": null, "id": "6trmn7p9qdrma0cm2zc8s9vtzc", "input": { "task": "depth2image", "width": 1024, "height": 1024, "image1": "https://replicate.delivery/pbxt/MEbaVgKE3z4ktO1hofUrhCTp23PNx1NNmR7jTRGPItHiGjeU/astronaut.webp", "prompt": "The image depicts a futuristic astronaut standing on a rocky terrain with orange flowers. The astronaut is wearing a yellow suit with a helmet and is equipped with a backpack. The astronaut is looking up at a large, circular, glowing portal in the sky, which is surrounded by a halo of light. The portal is emitting a warm glow and is surrounded by a few butterflies. The sky is dark with stars, and there are distant mountains visible. The overall atmosphere of the image is one of exploration and wonder.", "azimuth": "0", "distance": "1.5", "elevation": "0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": true }, "logs": "Using width, height: 416, 608\nUsing seed: 23222\nUsing prompt: [[depth2image]] The image depicts a futuristic astronaut standing on a rocky terrain with orange flowers. The astronaut is wearing a yellow suit with a helmet and is equipped with a backpack. The astronaut is looking up at a large, circular, glowing portal in the sky, which is surrounded by a halo of light. The portal is emitting a warm glow and is surrounded by a few butterflies. The sky is dark with stars, and there are distant mountains visible. The overall atmosphere of the image is one of exploration and wonder.\n/src/onediffusion/diffusion/pipelines/image_processor.py:572: FutureWarning: Passing `image` as torch tensor with value range in [-1,1] is deprecated. The expected value range for image tensor is [0,1] when passing as pytorch tensor or numpy Array. You passed `image` with value range [-1.0,0.9764705896377563]\nwarnings.warn(\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:10, 4.87it/s]\n 4%|▍ | 2/50 [00:00<00:09, 4.96it/s]\n 6%|▌ | 3/50 [00:00<00:09, 4.90it/s]\n 8%|▊ | 4/50 [00:00<00:09, 4.88it/s]\n 10%|█ | 5/50 [00:01<00:09, 4.86it/s]\n 12%|█▏ | 6/50 [00:01<00:09, 4.84it/s]\n 14%|█▍ | 7/50 [00:01<00:08, 4.83it/s]\n 16%|█▌ | 8/50 [00:01<00:08, 4.83it/s]\n 18%|█▊ | 9/50 [00:01<00:08, 4.83it/s]\n 20%|██ | 10/50 [00:02<00:08, 4.82it/s]\n 22%|██▏ | 11/50 [00:02<00:08, 4.82it/s]\n 24%|██▍ | 12/50 [00:02<00:07, 4.82it/s]\n 26%|██▌ | 13/50 [00:02<00:07, 4.82it/s]\n 28%|██▊ | 14/50 [00:02<00:07, 4.82it/s]\n 30%|███ | 15/50 [00:03<00:07, 4.81it/s]\n 32%|███▏ | 16/50 [00:03<00:07, 4.81it/s]\n 34%|███▍ | 17/50 [00:03<00:06, 4.81it/s]\n 36%|███▌ | 18/50 [00:03<00:06, 4.81it/s]\n 38%|███▊ | 19/50 [00:03<00:06, 4.81it/s]\n 40%|████ | 20/50 [00:04<00:06, 4.81it/s]\n 42%|████▏ | 21/50 [00:04<00:06, 4.80it/s]\n 44%|████▍ | 22/50 [00:04<00:05, 4.80it/s]\n 46%|████▌ | 23/50 [00:04<00:05, 4.80it/s]\n 48%|████▊ | 24/50 [00:04<00:05, 4.81it/s]\n 50%|█████ | 25/50 [00:05<00:05, 4.80it/s]\n 52%|█████▏ | 26/50 [00:05<00:05, 4.80it/s]\n 54%|█████▍ | 27/50 [00:05<00:04, 4.80it/s]\n 56%|█████▌ | 28/50 [00:05<00:04, 4.80it/s]\n 58%|█████▊ | 29/50 [00:06<00:04, 4.80it/s]\n 60%|██████ | 30/50 [00:06<00:04, 4.80it/s]\n 62%|██████▏ | 31/50 [00:06<00:03, 4.80it/s]\n 64%|██████▍ | 32/50 [00:06<00:03, 4.80it/s]\n 66%|██████▌ | 33/50 [00:06<00:03, 4.80it/s]\n 68%|██████▊ | 34/50 [00:07<00:03, 4.80it/s]\n 70%|███████ | 35/50 [00:07<00:03, 4.80it/s]\n 72%|███████▏ | 36/50 [00:07<00:02, 4.80it/s]\n 74%|███████▍ | 37/50 [00:07<00:02, 4.80it/s]\n 76%|███████▌ | 38/50 [00:07<00:02, 4.80it/s]\n 78%|███████▊ | 39/50 [00:08<00:02, 4.79it/s]\n 80%|████████ | 40/50 [00:08<00:02, 4.79it/s]\n 82%|████████▏ | 41/50 [00:08<00:01, 4.79it/s]\n 84%|████████▍ | 42/50 [00:08<00:01, 4.79it/s]\n 86%|████████▌ | 43/50 [00:08<00:01, 4.79it/s]\n 88%|████████▊ | 44/50 [00:09<00:01, 4.80it/s]\n 90%|█████████ | 45/50 [00:09<00:01, 4.80it/s]\n 92%|█████████▏| 46/50 [00:09<00:00, 4.80it/s]\n 94%|█████████▍| 47/50 [00:09<00:00, 4.79it/s]\n 96%|█████████▌| 48/50 [00:09<00:00, 4.79it/s]\n 98%|█████████▊| 49/50 [00:10<00:00, 4.79it/s]\n100%|██████████| 50/50 [00:10<00:00, 4.79it/s]\n100%|██████████| 50/50 [00:10<00:00, 4.81it/s]", "metrics": { "predict_time": 10.764862584, "total_time": 10.785469 }, "output": [ "https://replicate.delivery/xezq/BMIPvxUOdVLjLVvvW7Em0FJTiNjCaKuIx0wqCjG6SqQIYBAF/out_0.png", "https://replicate.delivery/xezq/fkRgfT1wXvoE0Eyq4uINmBcbpLbLJ2zZemS9askN0U1CBLAoA/out_1.png" ], "started_at": "2024-12-30T13:54:30.991606Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bcwr-lwwbgu6xqcx3rl46vhx53b3nhdi6536lfuyof2bmjewcy5dhyb5a", "get": "https://api.replicate.com/v1/predictions/6trmn7p9qdrma0cm2zc8s9vtzc", "cancel": "https://api.replicate.com/v1/predictions/6trmn7p9qdrma0cm2zc8s9vtzc/cancel" }, "version": "ca6eb28dc33f2f85969c8b0c7c26e10bc94a586c221b373c78095e44bcae94d8" }
Generated inUsing width, height: 416, 608 Using seed: 23222 Using prompt: [[depth2image]] The image depicts a futuristic astronaut standing on a rocky terrain with orange flowers. The astronaut is wearing a yellow suit with a helmet and is equipped with a backpack. The astronaut is looking up at a large, circular, glowing portal in the sky, which is surrounded by a halo of light. The portal is emitting a warm glow and is surrounded by a few butterflies. The sky is dark with stars, and there are distant mountains visible. The overall atmosphere of the image is one of exploration and wonder. /src/onediffusion/diffusion/pipelines/image_processor.py:572: FutureWarning: Passing `image` as torch tensor with value range in [-1,1] is deprecated. The expected value range for image tensor is [0,1] when passing as pytorch tensor or numpy Array. You passed `image` with value range [-1.0,0.9764705896377563] warnings.warn( 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:10, 4.87it/s] 4%|▍ | 2/50 [00:00<00:09, 4.96it/s] 6%|▌ | 3/50 [00:00<00:09, 4.90it/s] 8%|▊ | 4/50 [00:00<00:09, 4.88it/s] 10%|█ | 5/50 [00:01<00:09, 4.86it/s] 12%|█▏ | 6/50 [00:01<00:09, 4.84it/s] 14%|█▍ | 7/50 [00:01<00:08, 4.83it/s] 16%|█▌ | 8/50 [00:01<00:08, 4.83it/s] 18%|█▊ | 9/50 [00:01<00:08, 4.83it/s] 20%|██ | 10/50 [00:02<00:08, 4.82it/s] 22%|██▏ | 11/50 [00:02<00:08, 4.82it/s] 24%|██▍ | 12/50 [00:02<00:07, 4.82it/s] 26%|██▌ | 13/50 [00:02<00:07, 4.82it/s] 28%|██▊ | 14/50 [00:02<00:07, 4.82it/s] 30%|███ | 15/50 [00:03<00:07, 4.81it/s] 32%|███▏ | 16/50 [00:03<00:07, 4.81it/s] 34%|███▍ | 17/50 [00:03<00:06, 4.81it/s] 36%|███▌ | 18/50 [00:03<00:06, 4.81it/s] 38%|███▊ | 19/50 [00:03<00:06, 4.81it/s] 40%|████ | 20/50 [00:04<00:06, 4.81it/s] 42%|████▏ | 21/50 [00:04<00:06, 4.80it/s] 44%|████▍ | 22/50 [00:04<00:05, 4.80it/s] 46%|████▌ | 23/50 [00:04<00:05, 4.80it/s] 48%|████▊ | 24/50 [00:04<00:05, 4.81it/s] 50%|█████ | 25/50 [00:05<00:05, 4.80it/s] 52%|█████▏ | 26/50 [00:05<00:05, 4.80it/s] 54%|█████▍ | 27/50 [00:05<00:04, 4.80it/s] 56%|█████▌ | 28/50 [00:05<00:04, 4.80it/s] 58%|█████▊ | 29/50 [00:06<00:04, 4.80it/s] 60%|██████ | 30/50 [00:06<00:04, 4.80it/s] 62%|██████▏ | 31/50 [00:06<00:03, 4.80it/s] 64%|██████▍ | 32/50 [00:06<00:03, 4.80it/s] 66%|██████▌ | 33/50 [00:06<00:03, 4.80it/s] 68%|██████▊ | 34/50 [00:07<00:03, 4.80it/s] 70%|███████ | 35/50 [00:07<00:03, 4.80it/s] 72%|███████▏ | 36/50 [00:07<00:02, 4.80it/s] 74%|███████▍ | 37/50 [00:07<00:02, 4.80it/s] 76%|███████▌ | 38/50 [00:07<00:02, 4.80it/s] 78%|███████▊ | 39/50 [00:08<00:02, 4.79it/s] 80%|████████ | 40/50 [00:08<00:02, 4.79it/s] 82%|████████▏ | 41/50 [00:08<00:01, 4.79it/s] 84%|████████▍ | 42/50 [00:08<00:01, 4.79it/s] 86%|████████▌ | 43/50 [00:08<00:01, 4.79it/s] 88%|████████▊ | 44/50 [00:09<00:01, 4.80it/s] 90%|█████████ | 45/50 [00:09<00:01, 4.80it/s] 92%|█████████▏| 46/50 [00:09<00:00, 4.80it/s] 94%|█████████▍| 47/50 [00:09<00:00, 4.79it/s] 96%|█████████▌| 48/50 [00:09<00:00, 4.79it/s] 98%|█████████▊| 49/50 [00:10<00:00, 4.79it/s] 100%|██████████| 50/50 [00:10<00:00, 4.79it/s] 100%|██████████| 50/50 [00:10<00:00, 4.81it/s]
Prediction
chenxwh/onediffusion:f69674f4IDb5c68tks7srmc0cm2zda7jz73gStatusSucceededSourceWebHardwareL40STotal durationCreatedInput
- task
- semanticmap2image
- width
- 1024
- height
- 1024
- prompt
- <#00ffff Cyan mask: dragon> <#ff0000 yellow mask: bird> <#800080 purple mask: woman> A woman in a red dress with gold floral patterns stands in a traditional Japanese-style building. She has black hair and wears a gold choker and earrings. Behind her, a large orange and white dragon coils around the structure. Two white birds fly near her. The building features paper windows and a wooden roof with lanterns. The scene blends traditional Japanese architecture with fantastical elements, creating a mystical atmosphere.
- azimuth
- 0
- distance
- 1.5
- elevation
- 0
- focal_length
- 1.3887
- guidance_scale
- 4
- negative_prompt
- monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation
- num_inference_steps
- 50
- use_input_image_size
{ "task": "semanticmap2image", "width": 1024, "height": 1024, "image1": "https://replicate.delivery/pbxt/MEbcFwvOhBNZCpw8OVMO6e4yjxHH1tg81sAO0IrM0sjLeX77/dragon_birds_woman.webp", "prompt": "<#00ffff Cyan mask: dragon> <#ff0000 yellow mask: bird> <#800080 purple mask: woman> A woman in a red dress with gold floral patterns stands in a traditional Japanese-style building. She has black hair and wears a gold choker and earrings. Behind her, a large orange and white dragon coils around the structure. Two white birds fly near her. The building features paper windows and a wooden roof with lanterns. The scene blends traditional Japanese architecture with fantastical elements, creating a mystical atmosphere.", "azimuth": "0", "distance": "1.5", "elevation": "0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": true }
npm install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run chenxwh/onediffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "chenxwh/onediffusion:f69674f4fc4fb6f6b085b7cd6a00a4ee5d7014d8f5b2dea7bc551cc996129307", { input: { task: "semanticmap2image", width: 1024, height: 1024, image1: "https://replicate.delivery/pbxt/MEbcFwvOhBNZCpw8OVMO6e4yjxHH1tg81sAO0IrM0sjLeX77/dragon_birds_woman.webp", prompt: "<#00ffff Cyan mask: dragon> <#ff0000 yellow mask: bird> <#800080 purple mask: woman> A woman in a red dress with gold floral patterns stands in a traditional Japanese-style building. She has black hair and wears a gold choker and earrings. Behind her, a large orange and white dragon coils around the structure. Two white birds fly near her. The building features paper windows and a wooden roof with lanterns. The scene blends traditional Japanese architecture with fantastical elements, creating a mystical atmosphere.", azimuth: "0", distance: "1.5", elevation: "0", focal_length: 1.3887, guidance_scale: 4, negative_prompt: "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", num_inference_steps: 50, use_input_image_size: true } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the clientimport replicate
Run chenxwh/onediffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "chenxwh/onediffusion:f69674f4fc4fb6f6b085b7cd6a00a4ee5d7014d8f5b2dea7bc551cc996129307", input={ "task": "semanticmap2image", "width": 1024, "height": 1024, "image1": "https://replicate.delivery/pbxt/MEbcFwvOhBNZCpw8OVMO6e4yjxHH1tg81sAO0IrM0sjLeX77/dragon_birds_woman.webp", "prompt": "<#00ffff Cyan mask: dragon> <#ff0000 yellow mask: bird> <#800080 purple mask: woman> A woman in a red dress with gold floral patterns stands in a traditional Japanese-style building. She has black hair and wears a gold choker and earrings. Behind her, a large orange and white dragon coils around the structure. Two white birds fly near her. The building features paper windows and a wooden roof with lanterns. The scene blends traditional Japanese architecture with fantastical elements, creating a mystical atmosphere.", "azimuth": "0", "distance": "1.5", "elevation": "0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": True } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run chenxwh/onediffusion 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": "f69674f4fc4fb6f6b085b7cd6a00a4ee5d7014d8f5b2dea7bc551cc996129307", "input": { "task": "semanticmap2image", "width": 1024, "height": 1024, "image1": "https://replicate.delivery/pbxt/MEbcFwvOhBNZCpw8OVMO6e4yjxHH1tg81sAO0IrM0sjLeX77/dragon_birds_woman.webp", "prompt": "<#00ffff Cyan mask: dragon> <#ff0000 yellow mask: bird> <#800080 purple mask: woman> A woman in a red dress with gold floral patterns stands in a traditional Japanese-style building. She has black hair and wears a gold choker and earrings. Behind her, a large orange and white dragon coils around the structure. Two white birds fly near her. The building features paper windows and a wooden roof with lanterns. The scene blends traditional Japanese architecture with fantastical elements, creating a mystical atmosphere.", "azimuth": "0", "distance": "1.5", "elevation": "0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": true } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-12-30T13:56:32.673872Z", "created_at": "2024-12-30T13:56:21.438000Z", "data_removed": false, "error": null, "id": "b5c68tks7srmc0cm2zda7jz73g", "input": { "task": "semanticmap2image", "width": 1024, "height": 1024, "image1": "https://replicate.delivery/pbxt/MEbcFwvOhBNZCpw8OVMO6e4yjxHH1tg81sAO0IrM0sjLeX77/dragon_birds_woman.webp", "prompt": "<#00ffff Cyan mask: dragon> <#ff0000 yellow mask: bird> <#800080 purple mask: woman> A woman in a red dress with gold floral patterns stands in a traditional Japanese-style building. She has black hair and wears a gold choker and earrings. Behind her, a large orange and white dragon coils around the structure. Two white birds fly near her. The building features paper windows and a wooden roof with lanterns. The scene blends traditional Japanese architecture with fantastical elements, creating a mystical atmosphere.", "azimuth": "0", "distance": "1.5", "elevation": "0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": true }, "logs": "Using width, height: 384, 672\nUsing seed: 12623\nUsing prompt: [[semanticmap2image]] <#00ffff Cyan mask: dragon> <#ff0000 yellow mask: bird> <#800080 purple mask: woman> A woman in a red dress with gold floral patterns stands in a traditional Japanese-style building. She has black hair and wears a gold choker and earrings. Behind her, a large orange and white dragon coils around the structure. Two white birds fly near her. The building features paper windows and a wooden roof with lanterns. The scene blends traditional Japanese architecture with fantastical elements, creating a mystical atmosphere.\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:10, 4.66it/s]\n 4%|▍ | 2/50 [00:00<00:10, 4.76it/s]\n 6%|▌ | 3/50 [00:00<00:10, 4.69it/s]\n 8%|▊ | 4/50 [00:00<00:09, 4.65it/s]\n 10%|█ | 5/50 [00:01<00:09, 4.64it/s]\n 12%|█▏ | 6/50 [00:01<00:09, 4.63it/s]\n 14%|█▍ | 7/50 [00:01<00:09, 4.62it/s]\n 16%|█▌ | 8/50 [00:01<00:09, 4.62it/s]\n 18%|█▊ | 9/50 [00:01<00:08, 4.62it/s]\n 20%|██ | 10/50 [00:02<00:08, 4.61it/s]\n 22%|██▏ | 11/50 [00:02<00:08, 4.61it/s]\n 24%|██▍ | 12/50 [00:02<00:08, 4.61it/s]\n 26%|██▌ | 13/50 [00:02<00:08, 4.61it/s]\n 28%|██▊ | 14/50 [00:03<00:07, 4.60it/s]\n 30%|███ | 15/50 [00:03<00:07, 4.60it/s]\n 32%|███▏ | 16/50 [00:03<00:07, 4.60it/s]\n 34%|███▍ | 17/50 [00:03<00:07, 4.60it/s]\n 36%|███▌ | 18/50 [00:03<00:06, 4.60it/s]\n 38%|███▊ | 19/50 [00:04<00:06, 4.61it/s]\n 40%|████ | 20/50 [00:04<00:06, 4.61it/s]\n 42%|████▏ | 21/50 [00:04<00:06, 4.61it/s]\n 44%|████▍ | 22/50 [00:04<00:06, 4.62it/s]\n 46%|████▌ | 23/50 [00:04<00:05, 4.62it/s]\n 48%|████▊ | 24/50 [00:05<00:05, 4.62it/s]\n 50%|█████ | 25/50 [00:05<00:05, 4.62it/s]\n 52%|█████▏ | 26/50 [00:05<00:05, 4.62it/s]\n 54%|█████▍ | 27/50 [00:05<00:04, 4.62it/s]\n 56%|█████▌ | 28/50 [00:06<00:04, 4.62it/s]\n 58%|█████▊ | 29/50 [00:06<00:04, 4.62it/s]\n 60%|██████ | 30/50 [00:06<00:04, 4.62it/s]\n 62%|██████▏ | 31/50 [00:06<00:04, 4.62it/s]\n 64%|██████▍ | 32/50 [00:06<00:03, 4.62it/s]\n 66%|██████▌ | 33/50 [00:07<00:03, 4.62it/s]\n 68%|██████▊ | 34/50 [00:07<00:03, 4.62it/s]\n 70%|███████ | 35/50 [00:07<00:03, 4.62it/s]\n 72%|███████▏ | 36/50 [00:07<00:03, 4.62it/s]\n 74%|███████▍ | 37/50 [00:08<00:02, 4.62it/s]\n 76%|███████▌ | 38/50 [00:08<00:02, 4.62it/s]\n 78%|███████▊ | 39/50 [00:08<00:02, 4.62it/s]\n 80%|████████ | 40/50 [00:08<00:02, 4.62it/s]\n 82%|████████▏ | 41/50 [00:08<00:01, 4.62it/s]\n 84%|████████▍ | 42/50 [00:09<00:01, 4.62it/s]\n 86%|████████▌ | 43/50 [00:09<00:01, 4.54it/s]\n 88%|████████▊ | 44/50 [00:09<00:01, 4.56it/s]\n 90%|█████████ | 45/50 [00:09<00:01, 4.58it/s]\n 92%|█████████▏| 46/50 [00:09<00:00, 4.59it/s]\n 94%|█████████▍| 47/50 [00:10<00:00, 4.59it/s]\n 96%|█████████▌| 48/50 [00:10<00:00, 4.60it/s]\n 98%|█████████▊| 49/50 [00:10<00:00, 4.52it/s]\n100%|██████████| 50/50 [00:10<00:00, 4.55it/s]\n100%|██████████| 50/50 [00:10<00:00, 4.61it/s]", "metrics": { "predict_time": 11.228616622, "total_time": 11.235872 }, "output": [ "https://replicate.delivery/xezq/3r924iXBkIbuPV7cikq5iYRG9pxGsibP7koIZGWgJ5NkYBAF/out_0.png", "https://replicate.delivery/xezq/qvDuSVscEfyITae8fyNaTpXiepf8Dhi45chepaTWleWFIxCAKA/out_1.png" ], "started_at": "2024-12-30T13:56:21.445256Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bcwr-anpih7nbhyjmvtwlueg26xrxojp7ihqg3riktduzykcmvbtcznba", "get": "https://api.replicate.com/v1/predictions/b5c68tks7srmc0cm2zda7jz73g", "cancel": "https://api.replicate.com/v1/predictions/b5c68tks7srmc0cm2zda7jz73g/cancel" }, "version": "ca6eb28dc33f2f85969c8b0c7c26e10bc94a586c221b373c78095e44bcae94d8" }
Generated inUsing width, height: 384, 672 Using seed: 12623 Using prompt: [[semanticmap2image]] <#00ffff Cyan mask: dragon> <#ff0000 yellow mask: bird> <#800080 purple mask: woman> A woman in a red dress with gold floral patterns stands in a traditional Japanese-style building. She has black hair and wears a gold choker and earrings. Behind her, a large orange and white dragon coils around the structure. Two white birds fly near her. The building features paper windows and a wooden roof with lanterns. The scene blends traditional Japanese architecture with fantastical elements, creating a mystical atmosphere. 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:10, 4.66it/s] 4%|▍ | 2/50 [00:00<00:10, 4.76it/s] 6%|▌ | 3/50 [00:00<00:10, 4.69it/s] 8%|▊ | 4/50 [00:00<00:09, 4.65it/s] 10%|█ | 5/50 [00:01<00:09, 4.64it/s] 12%|█▏ | 6/50 [00:01<00:09, 4.63it/s] 14%|█▍ | 7/50 [00:01<00:09, 4.62it/s] 16%|█▌ | 8/50 [00:01<00:09, 4.62it/s] 18%|█▊ | 9/50 [00:01<00:08, 4.62it/s] 20%|██ | 10/50 [00:02<00:08, 4.61it/s] 22%|██▏ | 11/50 [00:02<00:08, 4.61it/s] 24%|██▍ | 12/50 [00:02<00:08, 4.61it/s] 26%|██▌ | 13/50 [00:02<00:08, 4.61it/s] 28%|██▊ | 14/50 [00:03<00:07, 4.60it/s] 30%|███ | 15/50 [00:03<00:07, 4.60it/s] 32%|███▏ | 16/50 [00:03<00:07, 4.60it/s] 34%|███▍ | 17/50 [00:03<00:07, 4.60it/s] 36%|███▌ | 18/50 [00:03<00:06, 4.60it/s] 38%|███▊ | 19/50 [00:04<00:06, 4.61it/s] 40%|████ | 20/50 [00:04<00:06, 4.61it/s] 42%|████▏ | 21/50 [00:04<00:06, 4.61it/s] 44%|████▍ | 22/50 [00:04<00:06, 4.62it/s] 46%|████▌ | 23/50 [00:04<00:05, 4.62it/s] 48%|████▊ | 24/50 [00:05<00:05, 4.62it/s] 50%|█████ | 25/50 [00:05<00:05, 4.62it/s] 52%|█████▏ | 26/50 [00:05<00:05, 4.62it/s] 54%|█████▍ | 27/50 [00:05<00:04, 4.62it/s] 56%|█████▌ | 28/50 [00:06<00:04, 4.62it/s] 58%|█████▊ | 29/50 [00:06<00:04, 4.62it/s] 60%|██████ | 30/50 [00:06<00:04, 4.62it/s] 62%|██████▏ | 31/50 [00:06<00:04, 4.62it/s] 64%|██████▍ | 32/50 [00:06<00:03, 4.62it/s] 66%|██████▌ | 33/50 [00:07<00:03, 4.62it/s] 68%|██████▊ | 34/50 [00:07<00:03, 4.62it/s] 70%|███████ | 35/50 [00:07<00:03, 4.62it/s] 72%|███████▏ | 36/50 [00:07<00:03, 4.62it/s] 74%|███████▍ | 37/50 [00:08<00:02, 4.62it/s] 76%|███████▌ | 38/50 [00:08<00:02, 4.62it/s] 78%|███████▊ | 39/50 [00:08<00:02, 4.62it/s] 80%|████████ | 40/50 [00:08<00:02, 4.62it/s] 82%|████████▏ | 41/50 [00:08<00:01, 4.62it/s] 84%|████████▍ | 42/50 [00:09<00:01, 4.62it/s] 86%|████████▌ | 43/50 [00:09<00:01, 4.54it/s] 88%|████████▊ | 44/50 [00:09<00:01, 4.56it/s] 90%|█████████ | 45/50 [00:09<00:01, 4.58it/s] 92%|█████████▏| 46/50 [00:09<00:00, 4.59it/s] 94%|█████████▍| 47/50 [00:10<00:00, 4.59it/s] 96%|█████████▌| 48/50 [00:10<00:00, 4.60it/s] 98%|█████████▊| 49/50 [00:10<00:00, 4.52it/s] 100%|██████████| 50/50 [00:10<00:00, 4.55it/s] 100%|██████████| 50/50 [00:10<00:00, 4.61it/s]
Prediction
chenxwh/onediffusion:f69674f4IDcch61wvr6hrmc0cm2zcvjzzp2rStatusSucceededSourceWebHardwareL40STotal durationCreatedInput
- task
- depth2image
- width
- 1024
- height
- 1024
- prompt
- A kitten sits in a small boat on a rainy lake. The kitten wears a pink sweater and hat with a pom-pom. It has orange and white fur, and its paws are visible. The scene is misty and atmospheric, with trees and mountains in the background.
- azimuth
- 0
- distance
- 1.5
- elevation
- 0
- focal_length
- 1.3887
- guidance_scale
- 4
- negative_prompt
- monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation
- num_inference_steps
- 50
- use_input_image_size
{ "task": "depth2image", "width": 1024, "height": 1024, "image1": "https://replicate.delivery/pbxt/MEbbDp1lgfMWfXKRUKnE1RZLsiJuzRIGNr5PGrt9zNJh1yjR/cat.webp", "prompt": "A kitten sits in a small boat on a rainy lake. The kitten wears a pink sweater and hat with a pom-pom. It has orange and white fur, and its paws are visible. The scene is misty and atmospheric, with trees and mountains in the background.", "azimuth": "0", "distance": "1.5", "elevation": "0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": true }
npm install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run chenxwh/onediffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "chenxwh/onediffusion:f69674f4fc4fb6f6b085b7cd6a00a4ee5d7014d8f5b2dea7bc551cc996129307", { input: { task: "depth2image", width: 1024, height: 1024, image1: "https://replicate.delivery/pbxt/MEbbDp1lgfMWfXKRUKnE1RZLsiJuzRIGNr5PGrt9zNJh1yjR/cat.webp", prompt: "A kitten sits in a small boat on a rainy lake. The kitten wears a pink sweater and hat with a pom-pom. It has orange and white fur, and its paws are visible. The scene is misty and atmospheric, with trees and mountains in the background.", azimuth: "0", distance: "1.5", elevation: "0", focal_length: 1.3887, guidance_scale: 4, negative_prompt: "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", num_inference_steps: 50, use_input_image_size: true } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the clientimport replicate
Run chenxwh/onediffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "chenxwh/onediffusion:f69674f4fc4fb6f6b085b7cd6a00a4ee5d7014d8f5b2dea7bc551cc996129307", input={ "task": "depth2image", "width": 1024, "height": 1024, "image1": "https://replicate.delivery/pbxt/MEbbDp1lgfMWfXKRUKnE1RZLsiJuzRIGNr5PGrt9zNJh1yjR/cat.webp", "prompt": "A kitten sits in a small boat on a rainy lake. The kitten wears a pink sweater and hat with a pom-pom. It has orange and white fur, and its paws are visible. The scene is misty and atmospheric, with trees and mountains in the background.", "azimuth": "0", "distance": "1.5", "elevation": "0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": True } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run chenxwh/onediffusion 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": "f69674f4fc4fb6f6b085b7cd6a00a4ee5d7014d8f5b2dea7bc551cc996129307", "input": { "task": "depth2image", "width": 1024, "height": 1024, "image1": "https://replicate.delivery/pbxt/MEbbDp1lgfMWfXKRUKnE1RZLsiJuzRIGNr5PGrt9zNJh1yjR/cat.webp", "prompt": "A kitten sits in a small boat on a rainy lake. The kitten wears a pink sweater and hat with a pom-pom. It has orange and white fur, and its paws are visible. The scene is misty and atmospheric, with trees and mountains in the background.", "azimuth": "0", "distance": "1.5", "elevation": "0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": true } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-12-30T13:56:11.961120Z", "created_at": "2024-12-30T13:55:15.636000Z", "data_removed": false, "error": null, "id": "cch61wvr6hrmc0cm2zcvjzzp2r", "input": { "task": "depth2image", "width": 1024, "height": 1024, "image1": "https://replicate.delivery/pbxt/MEbbDp1lgfMWfXKRUKnE1RZLsiJuzRIGNr5PGrt9zNJh1yjR/cat.webp", "prompt": "A kitten sits in a small boat on a rainy lake. The kitten wears a pink sweater and hat with a pom-pom. It has orange and white fur, and its paws are visible. The scene is misty and atmospheric, with trees and mountains in the background.", "azimuth": "0", "distance": "1.5", "elevation": "0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": true }, "logs": "Using width, height: 1024, 1024\nUsing seed: 32589\nUsing prompt: [[depth2image]] A kitten sits in a small boat on a rainy lake. The kitten wears a pink sweater and hat with a pom-pom. It has orange and white fur, and its paws are visible. The scene is misty and atmospheric, with trees and mountains in the background.\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:01<00:53, 1.10s/it]\n 4%|▍ | 2/50 [00:02<00:51, 1.07s/it]\n 6%|▌ | 3/50 [00:03<00:50, 1.08s/it]\n 8%|▊ | 4/50 [00:04<00:50, 1.09s/it]\n 10%|█ | 5/50 [00:05<00:49, 1.09s/it]\n 12%|█▏ | 6/50 [00:06<00:48, 1.10s/it]\n 14%|█▍ | 7/50 [00:07<00:47, 1.10s/it]\n 16%|█▌ | 8/50 [00:08<00:46, 1.10s/it]\n 18%|█▊ | 9/50 [00:09<00:45, 1.10s/it]\n 20%|██ | 10/50 [00:10<00:44, 1.10s/it]\n 22%|██▏ | 11/50 [00:12<00:42, 1.10s/it]\n 24%|██▍ | 12/50 [00:13<00:41, 1.10s/it]\n 26%|██▌ | 13/50 [00:14<00:40, 1.10s/it]\n 28%|██▊ | 14/50 [00:15<00:39, 1.10s/it]\n 30%|███ | 15/50 [00:16<00:38, 1.11s/it]\n 32%|███▏ | 16/50 [00:17<00:37, 1.11s/it]\n 34%|███▍ | 17/50 [00:18<00:36, 1.11s/it]\n 36%|███▌ | 18/50 [00:19<00:35, 1.11s/it]\n 38%|███▊ | 19/50 [00:20<00:34, 1.11s/it]\n 40%|████ | 20/50 [00:22<00:33, 1.11s/it]\n 42%|████▏ | 21/50 [00:23<00:32, 1.11s/it]\n 44%|████▍ | 22/50 [00:24<00:31, 1.11s/it]\n 46%|████▌ | 23/50 [00:25<00:29, 1.11s/it]\n 48%|████▊ | 24/50 [00:26<00:28, 1.11s/it]\n 50%|█████ | 25/50 [00:27<00:27, 1.11s/it]\n 52%|█████▏ | 26/50 [00:28<00:26, 1.11s/it]\n 54%|█████▍ | 27/50 [00:29<00:25, 1.11s/it]\n 56%|█████▌ | 28/50 [00:30<00:24, 1.11s/it]\n 58%|█████▊ | 29/50 [00:32<00:23, 1.11s/it]\n 60%|██████ | 30/50 [00:33<00:22, 1.11s/it]\n 62%|██████▏ | 31/50 [00:34<00:21, 1.11s/it]\n 64%|██████▍ | 32/50 [00:35<00:19, 1.11s/it]\n 66%|██████▌ | 33/50 [00:36<00:18, 1.11s/it]\n 68%|██████▊ | 34/50 [00:37<00:17, 1.11s/it]\n 70%|███████ | 35/50 [00:38<00:16, 1.11s/it]\n 72%|███████▏ | 36/50 [00:39<00:15, 1.11s/it]\n 74%|███████▍ | 37/50 [00:40<00:14, 1.11s/it]\n 76%|███████▌ | 38/50 [00:41<00:13, 1.11s/it]\n 78%|███████▊ | 39/50 [00:43<00:12, 1.11s/it]\n 80%|████████ | 40/50 [00:44<00:11, 1.11s/it]\n 82%|████████▏ | 41/50 [00:45<00:09, 1.11s/it]\n 84%|████████▍ | 42/50 [00:46<00:08, 1.11s/it]\n 86%|████████▌ | 43/50 [00:47<00:07, 1.11s/it]\n 88%|████████▊ | 44/50 [00:48<00:06, 1.11s/it]\n 90%|█████████ | 45/50 [00:49<00:05, 1.11s/it]\n 92%|█████████▏| 46/50 [00:50<00:04, 1.11s/it]\n 94%|█████████▍| 47/50 [00:51<00:03, 1.11s/it]\n 96%|█████████▌| 48/50 [00:53<00:02, 1.11s/it]\n 98%|█████████▊| 49/50 [00:54<00:01, 1.11s/it]\n100%|██████████| 50/50 [00:55<00:00, 1.11s/it]\n100%|██████████| 50/50 [00:55<00:00, 1.11s/it]", "metrics": { "predict_time": 56.317536718, "total_time": 56.32512 }, "output": [ "https://replicate.delivery/xezq/aPx7wvF2K1paJNYEKUoCSx5NNWSeYE438pIheRyv2Ez7hFAUA/out_0.png", "https://replicate.delivery/xezq/iypZsSipdcJLHdQPViIMwlo1hKkoSZWI7p0G3JI1vc8ewCAKA/out_1.png" ], "started_at": "2024-12-30T13:55:15.643584Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bcwr-qyh3pkeyqfmxh5rxr2v6usmgugtdkfc5iuphzp4mdlausmyd2hja", "get": "https://api.replicate.com/v1/predictions/cch61wvr6hrmc0cm2zcvjzzp2r", "cancel": "https://api.replicate.com/v1/predictions/cch61wvr6hrmc0cm2zcvjzzp2r/cancel" }, "version": "ca6eb28dc33f2f85969c8b0c7c26e10bc94a586c221b373c78095e44bcae94d8" }
Generated inUsing width, height: 1024, 1024 Using seed: 32589 Using prompt: [[depth2image]] A kitten sits in a small boat on a rainy lake. The kitten wears a pink sweater and hat with a pom-pom. It has orange and white fur, and its paws are visible. The scene is misty and atmospheric, with trees and mountains in the background. 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:01<00:53, 1.10s/it] 4%|▍ | 2/50 [00:02<00:51, 1.07s/it] 6%|▌ | 3/50 [00:03<00:50, 1.08s/it] 8%|▊ | 4/50 [00:04<00:50, 1.09s/it] 10%|█ | 5/50 [00:05<00:49, 1.09s/it] 12%|█▏ | 6/50 [00:06<00:48, 1.10s/it] 14%|█▍ | 7/50 [00:07<00:47, 1.10s/it] 16%|█▌ | 8/50 [00:08<00:46, 1.10s/it] 18%|█▊ | 9/50 [00:09<00:45, 1.10s/it] 20%|██ | 10/50 [00:10<00:44, 1.10s/it] 22%|██▏ | 11/50 [00:12<00:42, 1.10s/it] 24%|██▍ | 12/50 [00:13<00:41, 1.10s/it] 26%|██▌ | 13/50 [00:14<00:40, 1.10s/it] 28%|██▊ | 14/50 [00:15<00:39, 1.10s/it] 30%|███ | 15/50 [00:16<00:38, 1.11s/it] 32%|███▏ | 16/50 [00:17<00:37, 1.11s/it] 34%|███▍ | 17/50 [00:18<00:36, 1.11s/it] 36%|███▌ | 18/50 [00:19<00:35, 1.11s/it] 38%|███▊ | 19/50 [00:20<00:34, 1.11s/it] 40%|████ | 20/50 [00:22<00:33, 1.11s/it] 42%|████▏ | 21/50 [00:23<00:32, 1.11s/it] 44%|████▍ | 22/50 [00:24<00:31, 1.11s/it] 46%|████▌ | 23/50 [00:25<00:29, 1.11s/it] 48%|████▊ | 24/50 [00:26<00:28, 1.11s/it] 50%|█████ | 25/50 [00:27<00:27, 1.11s/it] 52%|█████▏ | 26/50 [00:28<00:26, 1.11s/it] 54%|█████▍ | 27/50 [00:29<00:25, 1.11s/it] 56%|█████▌ | 28/50 [00:30<00:24, 1.11s/it] 58%|█████▊ | 29/50 [00:32<00:23, 1.11s/it] 60%|██████ | 30/50 [00:33<00:22, 1.11s/it] 62%|██████▏ | 31/50 [00:34<00:21, 1.11s/it] 64%|██████▍ | 32/50 [00:35<00:19, 1.11s/it] 66%|██████▌ | 33/50 [00:36<00:18, 1.11s/it] 68%|██████▊ | 34/50 [00:37<00:17, 1.11s/it] 70%|███████ | 35/50 [00:38<00:16, 1.11s/it] 72%|███████▏ | 36/50 [00:39<00:15, 1.11s/it] 74%|███████▍ | 37/50 [00:40<00:14, 1.11s/it] 76%|███████▌ | 38/50 [00:41<00:13, 1.11s/it] 78%|███████▊ | 39/50 [00:43<00:12, 1.11s/it] 80%|████████ | 40/50 [00:44<00:11, 1.11s/it] 82%|████████▏ | 41/50 [00:45<00:09, 1.11s/it] 84%|████████▍ | 42/50 [00:46<00:08, 1.11s/it] 86%|████████▌ | 43/50 [00:47<00:07, 1.11s/it] 88%|████████▊ | 44/50 [00:48<00:06, 1.11s/it] 90%|█████████ | 45/50 [00:49<00:05, 1.11s/it] 92%|█████████▏| 46/50 [00:50<00:04, 1.11s/it] 94%|█████████▍| 47/50 [00:51<00:03, 1.11s/it] 96%|█████████▌| 48/50 [00:53<00:02, 1.11s/it] 98%|█████████▊| 49/50 [00:54<00:01, 1.11s/it] 100%|██████████| 50/50 [00:55<00:00, 1.11s/it] 100%|██████████| 50/50 [00:55<00:00, 1.11s/it]
Prediction
chenxwh/onediffusion:f69674f4IDckf0bks8w5rm80cm2zf8yk2btrStatusSucceededSourceWebHardwareL40STotal durationCreatedInput
- task
- image_editing
- width
- 1024
- height
- 1024
- prompt
- change it to winter and snowy weather
- azimuth
- 0
- distance
- 1.5
- elevation
- 0
- focal_length
- 1.3887
- guidance_scale
- 4
- negative_prompt
- monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation
- num_inference_steps
- 50
- use_input_image_size
{ "task": "image_editing", "width": 1024, "height": 1024, "image1": "https://replicate.delivery/pbxt/MEbg4ykuxG1zZldD3S1hpvflxw5qxoOp6LRWWJY5ItsJAZL7/astronaut%20%281%29.webp", "prompt": "change it to winter and snowy weather", "azimuth": "0", "distance": "1.5", "elevation": "0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": true }
npm install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run chenxwh/onediffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "chenxwh/onediffusion:f69674f4fc4fb6f6b085b7cd6a00a4ee5d7014d8f5b2dea7bc551cc996129307", { input: { task: "image_editing", width: 1024, height: 1024, image1: "https://replicate.delivery/pbxt/MEbg4ykuxG1zZldD3S1hpvflxw5qxoOp6LRWWJY5ItsJAZL7/astronaut%20%281%29.webp", prompt: "change it to winter and snowy weather", azimuth: "0", distance: "1.5", elevation: "0", focal_length: 1.3887, guidance_scale: 4, negative_prompt: "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", num_inference_steps: 50, use_input_image_size: true } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the clientimport replicate
Run chenxwh/onediffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "chenxwh/onediffusion:f69674f4fc4fb6f6b085b7cd6a00a4ee5d7014d8f5b2dea7bc551cc996129307", input={ "task": "image_editing", "width": 1024, "height": 1024, "image1": "https://replicate.delivery/pbxt/MEbg4ykuxG1zZldD3S1hpvflxw5qxoOp6LRWWJY5ItsJAZL7/astronaut%20%281%29.webp", "prompt": "change it to winter and snowy weather", "azimuth": "0", "distance": "1.5", "elevation": "0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": True } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run chenxwh/onediffusion 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": "f69674f4fc4fb6f6b085b7cd6a00a4ee5d7014d8f5b2dea7bc551cc996129307", "input": { "task": "image_editing", "width": 1024, "height": 1024, "image1": "https://replicate.delivery/pbxt/MEbg4ykuxG1zZldD3S1hpvflxw5qxoOp6LRWWJY5ItsJAZL7/astronaut%20%281%29.webp", "prompt": "change it to winter and snowy weather", "azimuth": "0", "distance": "1.5", "elevation": "0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": true } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-12-30T14:01:19.320534Z", "created_at": "2024-12-30T14:00:23.009000Z", "data_removed": false, "error": null, "id": "ckf0bks8w5rm80cm2zf8yk2btr", "input": { "task": "image_editing", "width": 1024, "height": 1024, "image1": "https://replicate.delivery/pbxt/MEbg4ykuxG1zZldD3S1hpvflxw5qxoOp6LRWWJY5ItsJAZL7/astronaut%20%281%29.webp", "prompt": "change it to winter and snowy weather", "azimuth": "0", "distance": "1.5", "elevation": "0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": true }, "logs": "Using width, height: 1024, 1024\nUsing seed: 31404\nUsing prompt: [[image_editing]] change it to winter and snowy weather\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:01<00:53, 1.10s/it]\n 4%|▍ | 2/50 [00:02<00:51, 1.07s/it]\n 6%|▌ | 3/50 [00:03<00:50, 1.08s/it]\n 8%|▊ | 4/50 [00:04<00:50, 1.09s/it]\n 10%|█ | 5/50 [00:05<00:49, 1.09s/it]\n 12%|█▏ | 6/50 [00:06<00:48, 1.10s/it]\n 14%|█▍ | 7/50 [00:07<00:47, 1.10s/it]\n 16%|█▌ | 8/50 [00:08<00:46, 1.10s/it]\n 18%|█▊ | 9/50 [00:09<00:45, 1.10s/it]\n 20%|██ | 10/50 [00:10<00:44, 1.10s/it]\n 22%|██▏ | 11/50 [00:12<00:43, 1.10s/it]\n 24%|██▍ | 12/50 [00:13<00:41, 1.10s/it]\n 26%|██▌ | 13/50 [00:14<00:40, 1.11s/it]\n 28%|██▊ | 14/50 [00:15<00:39, 1.11s/it]\n 30%|███ | 15/50 [00:16<00:38, 1.11s/it]\n 32%|███▏ | 16/50 [00:17<00:37, 1.11s/it]\n 34%|███▍ | 17/50 [00:18<00:36, 1.11s/it]\n 36%|███▌ | 18/50 [00:19<00:35, 1.11s/it]\n 38%|███▊ | 19/50 [00:20<00:34, 1.11s/it]\n 40%|████ | 20/50 [00:22<00:33, 1.11s/it]\n 42%|████▏ | 21/50 [00:23<00:32, 1.11s/it]\n 44%|████▍ | 22/50 [00:24<00:31, 1.11s/it]\n 46%|████▌ | 23/50 [00:25<00:29, 1.11s/it]\n 48%|████▊ | 24/50 [00:26<00:28, 1.11s/it]\n 50%|█████ | 25/50 [00:27<00:27, 1.11s/it]\n 52%|█████▏ | 26/50 [00:28<00:26, 1.11s/it]\n 54%|█████▍ | 27/50 [00:29<00:25, 1.11s/it]\n 56%|█████▌ | 28/50 [00:30<00:24, 1.11s/it]\n 58%|█████▊ | 29/50 [00:32<00:23, 1.11s/it]\n 60%|██████ | 30/50 [00:33<00:22, 1.12s/it]\n 62%|██████▏ | 31/50 [00:34<00:21, 1.12s/it]\n 64%|██████▍ | 32/50 [00:35<00:20, 1.12s/it]\n 66%|██████▌ | 33/50 [00:36<00:19, 1.12s/it]\n 68%|██████▊ | 34/50 [00:37<00:17, 1.12s/it]\n 70%|███████ | 35/50 [00:38<00:16, 1.12s/it]\n 72%|███████▏ | 36/50 [00:39<00:15, 1.12s/it]\n 74%|███████▍ | 37/50 [00:41<00:14, 1.12s/it]\n 76%|███████▌ | 38/50 [00:42<00:13, 1.12s/it]\n 78%|███████▊ | 39/50 [00:43<00:12, 1.12s/it]\n 80%|████████ | 40/50 [00:44<00:11, 1.11s/it]\n 82%|████████▏ | 41/50 [00:45<00:10, 1.11s/it]\n 84%|████████▍ | 42/50 [00:46<00:08, 1.11s/it]\n 86%|████████▌ | 43/50 [00:47<00:07, 1.11s/it]\n 88%|████████▊ | 44/50 [00:48<00:06, 1.11s/it]\n 90%|█████████ | 45/50 [00:49<00:05, 1.11s/it]\n 92%|█████████▏| 46/50 [00:51<00:04, 1.11s/it]\n 94%|█████████▍| 47/50 [00:52<00:03, 1.11s/it]\n 96%|█████████▌| 48/50 [00:53<00:02, 1.11s/it]\n 98%|█████████▊| 49/50 [00:54<00:01, 1.12s/it]\n100%|██████████| 50/50 [00:55<00:00, 1.12s/it]\n100%|██████████| 50/50 [00:55<00:00, 1.11s/it]", "metrics": { "predict_time": 56.302930612, "total_time": 56.311534 }, "output": [ "https://replicate.delivery/xezq/kPBPuQfHjUTbE6KASTSl2zvHwYbMhcHbrQklPXQ8SRnXzCAKA/out_0.png" ], "started_at": "2024-12-30T14:00:23.017604Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bcwr-3skuryjym4uzsui2offoeuocvfbrd6o2dz5zbn4n6x4fvcdme3wa", "get": "https://api.replicate.com/v1/predictions/ckf0bks8w5rm80cm2zf8yk2btr", "cancel": "https://api.replicate.com/v1/predictions/ckf0bks8w5rm80cm2zf8yk2btr/cancel" }, "version": "ca6eb28dc33f2f85969c8b0c7c26e10bc94a586c221b373c78095e44bcae94d8" }
Generated inUsing width, height: 1024, 1024 Using seed: 31404 Using prompt: [[image_editing]] change it to winter and snowy weather 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:01<00:53, 1.10s/it] 4%|▍ | 2/50 [00:02<00:51, 1.07s/it] 6%|▌ | 3/50 [00:03<00:50, 1.08s/it] 8%|▊ | 4/50 [00:04<00:50, 1.09s/it] 10%|█ | 5/50 [00:05<00:49, 1.09s/it] 12%|█▏ | 6/50 [00:06<00:48, 1.10s/it] 14%|█▍ | 7/50 [00:07<00:47, 1.10s/it] 16%|█▌ | 8/50 [00:08<00:46, 1.10s/it] 18%|█▊ | 9/50 [00:09<00:45, 1.10s/it] 20%|██ | 10/50 [00:10<00:44, 1.10s/it] 22%|██▏ | 11/50 [00:12<00:43, 1.10s/it] 24%|██▍ | 12/50 [00:13<00:41, 1.10s/it] 26%|██▌ | 13/50 [00:14<00:40, 1.11s/it] 28%|██▊ | 14/50 [00:15<00:39, 1.11s/it] 30%|███ | 15/50 [00:16<00:38, 1.11s/it] 32%|███▏ | 16/50 [00:17<00:37, 1.11s/it] 34%|███▍ | 17/50 [00:18<00:36, 1.11s/it] 36%|███▌ | 18/50 [00:19<00:35, 1.11s/it] 38%|███▊ | 19/50 [00:20<00:34, 1.11s/it] 40%|████ | 20/50 [00:22<00:33, 1.11s/it] 42%|████▏ | 21/50 [00:23<00:32, 1.11s/it] 44%|████▍ | 22/50 [00:24<00:31, 1.11s/it] 46%|████▌ | 23/50 [00:25<00:29, 1.11s/it] 48%|████▊ | 24/50 [00:26<00:28, 1.11s/it] 50%|█████ | 25/50 [00:27<00:27, 1.11s/it] 52%|█████▏ | 26/50 [00:28<00:26, 1.11s/it] 54%|█████▍ | 27/50 [00:29<00:25, 1.11s/it] 56%|█████▌ | 28/50 [00:30<00:24, 1.11s/it] 58%|█████▊ | 29/50 [00:32<00:23, 1.11s/it] 60%|██████ | 30/50 [00:33<00:22, 1.12s/it] 62%|██████▏ | 31/50 [00:34<00:21, 1.12s/it] 64%|██████▍ | 32/50 [00:35<00:20, 1.12s/it] 66%|██████▌ | 33/50 [00:36<00:19, 1.12s/it] 68%|██████▊ | 34/50 [00:37<00:17, 1.12s/it] 70%|███████ | 35/50 [00:38<00:16, 1.12s/it] 72%|███████▏ | 36/50 [00:39<00:15, 1.12s/it] 74%|███████▍ | 37/50 [00:41<00:14, 1.12s/it] 76%|███████▌ | 38/50 [00:42<00:13, 1.12s/it] 78%|███████▊ | 39/50 [00:43<00:12, 1.12s/it] 80%|████████ | 40/50 [00:44<00:11, 1.11s/it] 82%|████████▏ | 41/50 [00:45<00:10, 1.11s/it] 84%|████████▍ | 42/50 [00:46<00:08, 1.11s/it] 86%|████████▌ | 43/50 [00:47<00:07, 1.11s/it] 88%|████████▊ | 44/50 [00:48<00:06, 1.11s/it] 90%|█████████ | 45/50 [00:49<00:05, 1.11s/it] 92%|█████████▏| 46/50 [00:51<00:04, 1.11s/it] 94%|█████████▍| 47/50 [00:52<00:03, 1.11s/it] 96%|█████████▌| 48/50 [00:53<00:02, 1.11s/it] 98%|█████████▊| 49/50 [00:54<00:01, 1.12s/it] 100%|██████████| 50/50 [00:55<00:00, 1.12s/it] 100%|██████████| 50/50 [00:55<00:00, 1.11s/it]
Prediction
chenxwh/onediffusion:f69674f4IDnj9rd9f265rma0cm2zgr10ne4cStatusSucceededSourceWebHardwareL40STotal durationCreatedInput
- task
- multiview
- width
- 1024
- height
- 1024
- prompt
- A cat with orange and white fur sits on a round wooden table. The cat has striking green eyes and a pink nose. Its ears are perked up, and its tail is curled around its body. The background is blurred, showing a white wall, a wooden chair, and a wooden table with a white pot and green plant. A white curtain is visible on the right side. The cat's gaze is directed slightly to the right, and its paws are white. The overall scene creates a cozy, domestic atmosphere with the cat as the central focus.
- azimuth
- 0,20,40,60
- distance
- 1.5,1.5,1.5,1.5
- elevation
- 0,0,0,0
- focal_length
- 1.3887
- guidance_scale
- 4
- negative_prompt
- monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation
- num_inference_steps
- 50
- use_input_image_size
{ "task": "multiview", "width": 1024, "height": 1024, "image1": "https://replicate.delivery/pbxt/MEbjvoKviqoARp5MVJLlzbOt2LjrcUn0kHNRtEFc2cDnsZ4x/cat_on_table.webp", "prompt": "A cat with orange and white fur sits on a round wooden table. The cat has striking green eyes and a pink nose. Its ears are perked up, and its tail is curled around its body. The background is blurred, showing a white wall, a wooden chair, and a wooden table with a white pot and green plant. A white curtain is visible on the right side. The cat's gaze is directed slightly to the right, and its paws are white. The overall scene creates a cozy, domestic atmosphere with the cat as the central focus.", "azimuth": "0,20,40,60", "distance": "1.5,1.5,1.5,1.5", "elevation": "0,0,0,0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": true }
npm install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run chenxwh/onediffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "chenxwh/onediffusion:f69674f4fc4fb6f6b085b7cd6a00a4ee5d7014d8f5b2dea7bc551cc996129307", { input: { task: "multiview", width: 1024, height: 1024, image1: "https://replicate.delivery/pbxt/MEbjvoKviqoARp5MVJLlzbOt2LjrcUn0kHNRtEFc2cDnsZ4x/cat_on_table.webp", prompt: "A cat with orange and white fur sits on a round wooden table. The cat has striking green eyes and a pink nose. Its ears are perked up, and its tail is curled around its body. The background is blurred, showing a white wall, a wooden chair, and a wooden table with a white pot and green plant. A white curtain is visible on the right side. The cat's gaze is directed slightly to the right, and its paws are white. The overall scene creates a cozy, domestic atmosphere with the cat as the central focus.", azimuth: "0,20,40,60", distance: "1.5,1.5,1.5,1.5", elevation: "0,0,0,0", focal_length: 1.3887, guidance_scale: 4, negative_prompt: "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", num_inference_steps: 50, use_input_image_size: true } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the clientimport replicate
Run chenxwh/onediffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "chenxwh/onediffusion:f69674f4fc4fb6f6b085b7cd6a00a4ee5d7014d8f5b2dea7bc551cc996129307", input={ "task": "multiview", "width": 1024, "height": 1024, "image1": "https://replicate.delivery/pbxt/MEbjvoKviqoARp5MVJLlzbOt2LjrcUn0kHNRtEFc2cDnsZ4x/cat_on_table.webp", "prompt": "A cat with orange and white fur sits on a round wooden table. The cat has striking green eyes and a pink nose. Its ears are perked up, and its tail is curled around its body. The background is blurred, showing a white wall, a wooden chair, and a wooden table with a white pot and green plant. A white curtain is visible on the right side. The cat's gaze is directed slightly to the right, and its paws are white. The overall scene creates a cozy, domestic atmosphere with the cat as the central focus.", "azimuth": "0,20,40,60", "distance": "1.5,1.5,1.5,1.5", "elevation": "0,0,0,0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": True } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run chenxwh/onediffusion 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": "f69674f4fc4fb6f6b085b7cd6a00a4ee5d7014d8f5b2dea7bc551cc996129307", "input": { "task": "multiview", "width": 1024, "height": 1024, "image1": "https://replicate.delivery/pbxt/MEbjvoKviqoARp5MVJLlzbOt2LjrcUn0kHNRtEFc2cDnsZ4x/cat_on_table.webp", "prompt": "A cat with orange and white fur sits on a round wooden table. The cat has striking green eyes and a pink nose. Its ears are perked up, and its tail is curled around its body. The background is blurred, showing a white wall, a wooden chair, and a wooden table with a white pot and green plant. A white curtain is visible on the right side. The cat\'s gaze is directed slightly to the right, and its paws are white. The overall scene creates a cozy, domestic atmosphere with the cat as the central focus.", "azimuth": "0,20,40,60", "distance": "1.5,1.5,1.5,1.5", "elevation": "0,0,0,0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": true } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-12-30T14:10:15.106748Z", "created_at": "2024-12-30T14:04:27.057000Z", "data_removed": false, "error": null, "id": "nj9rd9f265rma0cm2zgr10ne4c", "input": { "task": "multiview", "width": 1024, "height": 1024, "image1": "https://replicate.delivery/pbxt/MEbjvoKviqoARp5MVJLlzbOt2LjrcUn0kHNRtEFc2cDnsZ4x/cat_on_table.webp", "prompt": "A cat with orange and white fur sits on a round wooden table. The cat has striking green eyes and a pink nose. Its ears are perked up, and its tail is curled around its body. The background is blurred, showing a white wall, a wooden chair, and a wooden table with a white pot and green plant. A white curtain is visible on the right side. The cat's gaze is directed slightly to the right, and its paws are white. The overall scene creates a cozy, domestic atmosphere with the cat as the central focus.", "azimuth": "0,20,40,60", "distance": "1.5,1.5,1.5,1.5", "elevation": "0,0,0,0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": true }, "logs": "Using width, height: 1024, 1024\nUsing seed: 53546\nUsing prompt: [[multiview]] A cat with orange and white fur sits on a round wooden table. The cat has striking green eyes and a pink nose. Its ears are perked up, and its tail is curled around its body. The background is blurred, showing a white wall, a wooden chair, and a wooden table with a white pot and green plant. A white curtain is visible on the right side. The cat's gaze is directed slightly to the right, and its paws are white. The overall scene creates a cozy, domestic atmosphere with the cat as the central focus.\n/src/onediffusion/diffusion/pipelines/image_processor.py:572: FutureWarning: Passing `image` as torch tensor with value range in [-1,1] is deprecated. The expected value range for image tensor is [0,1] when passing as pytorch tensor or numpy Array. You passed `image` with value range [-1.0,1.0]\nwarnings.warn(\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:06<05:13, 6.40s/it]\n 4%|▍ | 2/50 [00:12<05:07, 6.40s/it]\n 6%|▌ | 3/50 [00:19<05:01, 6.41s/it]\n 8%|▊ | 4/50 [00:25<04:56, 6.44s/it]\n 10%|█ | 5/50 [00:32<04:50, 6.45s/it]\n 12%|█▏ | 6/50 [00:38<04:44, 6.46s/it]\n 14%|█▍ | 7/50 [00:45<04:38, 6.47s/it]\n 16%|█▌ | 8/50 [00:51<04:32, 6.48s/it]\n 18%|█▊ | 9/50 [00:58<04:26, 6.50s/it]\n 20%|██ | 10/50 [01:04<04:20, 6.50s/it]\n 22%|██▏ | 11/50 [01:11<04:13, 6.51s/it]\n 24%|██▍ | 12/50 [01:17<04:07, 6.52s/it]\n 26%|██▌ | 13/50 [01:24<04:01, 6.53s/it]\n 28%|██▊ | 14/50 [01:30<03:55, 6.55s/it]\n 30%|███ | 15/50 [01:37<03:49, 6.56s/it]\n 32%|███▏ | 16/50 [01:44<03:43, 6.57s/it]\n 34%|███▍ | 17/50 [01:50<03:36, 6.57s/it]\n 36%|███▌ | 18/50 [01:57<03:30, 6.58s/it]\n 38%|███▊ | 19/50 [02:03<03:24, 6.59s/it]\n 40%|████ | 20/50 [02:10<03:17, 6.59s/it]\n 42%|████▏ | 21/50 [02:17<03:11, 6.59s/it]\n 44%|████▍ | 22/50 [02:23<03:04, 6.59s/it]\n 46%|████▌ | 23/50 [02:30<02:58, 6.60s/it]\n 48%|████▊ | 24/50 [02:36<02:51, 6.60s/it]\n 50%|█████ | 25/50 [02:43<02:45, 6.61s/it]\n 52%|█████▏ | 26/50 [02:50<02:38, 6.61s/it]\n 54%|█████▍ | 27/50 [02:56<02:32, 6.62s/it]\n 56%|█████▌ | 28/50 [03:03<02:25, 6.62s/it]\n 58%|█████▊ | 29/50 [03:09<02:18, 6.62s/it]\n 60%|██████ | 30/50 [03:16<02:12, 6.61s/it]\n 62%|██████▏ | 31/50 [03:23<02:05, 6.61s/it]\n 64%|██████▍ | 32/50 [03:29<01:59, 6.61s/it]\n 66%|██████▌ | 33/50 [03:36<01:52, 6.62s/it]\n 68%|██████▊ | 34/50 [03:43<01:45, 6.62s/it]\n 70%|███████ | 35/50 [03:49<01:39, 6.62s/it]\n 72%|███████▏ | 36/50 [03:56<01:32, 6.62s/it]\n 74%|███████▍ | 37/50 [04:02<01:26, 6.62s/it]\n 76%|███████▌ | 38/50 [04:09<01:19, 6.61s/it]\n 78%|███████▊ | 39/50 [04:16<01:12, 6.61s/it]\n 80%|████████ | 40/50 [04:22<01:06, 6.61s/it]\n 82%|████████▏ | 41/50 [04:29<00:59, 6.61s/it]\n 84%|████████▍ | 42/50 [04:35<00:52, 6.61s/it]\n 86%|████████▌ | 43/50 [04:42<00:46, 6.62s/it]\n 88%|████████▊ | 44/50 [04:49<00:39, 6.62s/it]\n 90%|█████████ | 45/50 [04:55<00:33, 6.63s/it]\n 92%|█████████▏| 46/50 [05:02<00:26, 6.63s/it]\n 94%|█████████▍| 47/50 [05:09<00:19, 6.63s/it]\n 96%|█████████▌| 48/50 [05:15<00:13, 6.63s/it]\n 98%|█████████▊| 49/50 [05:22<00:06, 6.63s/it]\n100%|██████████| 50/50 [05:29<00:00, 6.64s/it]\n100%|██████████| 50/50 [05:29<00:00, 6.58s/it]", "metrics": { "predict_time": 330.414773489, "total_time": 348.049748 }, "output": [ "https://replicate.delivery/xezq/5Xgkpm0fyF0wSizEfDcWo0RreUYV3szb7Bsuofvhdpze4tAgC/out_0.png" ], "started_at": "2024-12-30T14:04:44.691975Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bcwr-36a5jcb72gnq4yup5ebbmautbrhjsi75h27nqhkeg5j6blg2x6ua", "get": "https://api.replicate.com/v1/predictions/nj9rd9f265rma0cm2zgr10ne4c", "cancel": "https://api.replicate.com/v1/predictions/nj9rd9f265rma0cm2zgr10ne4c/cancel" }, "version": "ca6eb28dc33f2f85969c8b0c7c26e10bc94a586c221b373c78095e44bcae94d8" }
Generated inUsing width, height: 1024, 1024 Using seed: 53546 Using prompt: [[multiview]] A cat with orange and white fur sits on a round wooden table. The cat has striking green eyes and a pink nose. Its ears are perked up, and its tail is curled around its body. The background is blurred, showing a white wall, a wooden chair, and a wooden table with a white pot and green plant. A white curtain is visible on the right side. The cat's gaze is directed slightly to the right, and its paws are white. The overall scene creates a cozy, domestic atmosphere with the cat as the central focus. /src/onediffusion/diffusion/pipelines/image_processor.py:572: FutureWarning: Passing `image` as torch tensor with value range in [-1,1] is deprecated. The expected value range for image tensor is [0,1] when passing as pytorch tensor or numpy Array. You passed `image` with value range [-1.0,1.0] warnings.warn( 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:06<05:13, 6.40s/it] 4%|▍ | 2/50 [00:12<05:07, 6.40s/it] 6%|▌ | 3/50 [00:19<05:01, 6.41s/it] 8%|▊ | 4/50 [00:25<04:56, 6.44s/it] 10%|█ | 5/50 [00:32<04:50, 6.45s/it] 12%|█▏ | 6/50 [00:38<04:44, 6.46s/it] 14%|█▍ | 7/50 [00:45<04:38, 6.47s/it] 16%|█▌ | 8/50 [00:51<04:32, 6.48s/it] 18%|█▊ | 9/50 [00:58<04:26, 6.50s/it] 20%|██ | 10/50 [01:04<04:20, 6.50s/it] 22%|██▏ | 11/50 [01:11<04:13, 6.51s/it] 24%|██▍ | 12/50 [01:17<04:07, 6.52s/it] 26%|██▌ | 13/50 [01:24<04:01, 6.53s/it] 28%|██▊ | 14/50 [01:30<03:55, 6.55s/it] 30%|███ | 15/50 [01:37<03:49, 6.56s/it] 32%|███▏ | 16/50 [01:44<03:43, 6.57s/it] 34%|███▍ | 17/50 [01:50<03:36, 6.57s/it] 36%|███▌ | 18/50 [01:57<03:30, 6.58s/it] 38%|███▊ | 19/50 [02:03<03:24, 6.59s/it] 40%|████ | 20/50 [02:10<03:17, 6.59s/it] 42%|████▏ | 21/50 [02:17<03:11, 6.59s/it] 44%|████▍ | 22/50 [02:23<03:04, 6.59s/it] 46%|████▌ | 23/50 [02:30<02:58, 6.60s/it] 48%|████▊ | 24/50 [02:36<02:51, 6.60s/it] 50%|█████ | 25/50 [02:43<02:45, 6.61s/it] 52%|█████▏ | 26/50 [02:50<02:38, 6.61s/it] 54%|█████▍ | 27/50 [02:56<02:32, 6.62s/it] 56%|█████▌ | 28/50 [03:03<02:25, 6.62s/it] 58%|█████▊ | 29/50 [03:09<02:18, 6.62s/it] 60%|██████ | 30/50 [03:16<02:12, 6.61s/it] 62%|██████▏ | 31/50 [03:23<02:05, 6.61s/it] 64%|██████▍ | 32/50 [03:29<01:59, 6.61s/it] 66%|██████▌ | 33/50 [03:36<01:52, 6.62s/it] 68%|██████▊ | 34/50 [03:43<01:45, 6.62s/it] 70%|███████ | 35/50 [03:49<01:39, 6.62s/it] 72%|███████▏ | 36/50 [03:56<01:32, 6.62s/it] 74%|███████▍ | 37/50 [04:02<01:26, 6.62s/it] 76%|███████▌ | 38/50 [04:09<01:19, 6.61s/it] 78%|███████▊ | 39/50 [04:16<01:12, 6.61s/it] 80%|████████ | 40/50 [04:22<01:06, 6.61s/it] 82%|████████▏ | 41/50 [04:29<00:59, 6.61s/it] 84%|████████▍ | 42/50 [04:35<00:52, 6.61s/it] 86%|████████▌ | 43/50 [04:42<00:46, 6.62s/it] 88%|████████▊ | 44/50 [04:49<00:39, 6.62s/it] 90%|█████████ | 45/50 [04:55<00:33, 6.63s/it] 92%|█████████▏| 46/50 [05:02<00:26, 6.63s/it] 94%|█████████▍| 47/50 [05:09<00:19, 6.63s/it] 96%|█████████▌| 48/50 [05:15<00:13, 6.63s/it] 98%|█████████▊| 49/50 [05:22<00:06, 6.63s/it] 100%|██████████| 50/50 [05:29<00:00, 6.64s/it] 100%|██████████| 50/50 [05:29<00:00, 6.58s/it]
Prediction
chenxwh/onediffusion:f69674f4IDwkwkztkrd1rm80cm2zr8mhskpwStatusSucceededSourceWebHardwareL40STotal durationCreatedInput
- task
- subject_driven
- width
- 512
- height
- 512
- prompt
- <item: cartoon dog> [[img0]] a cartoon character resembling a dog, sitting on a beach. The character has a long, narrow face with a black nose and brown eyes. It's wearing a gray sweatshirt, blue jeans rolled up at the bottom, and red sneakers with white soles. it has a slight smirk on its face [[img1]] The photo features a cartoon character resembling a do. The character has a long, narrow face with a black nose and brown eyes. It's wearing a gray sweatshirt, blue jeans rolled up at the bottom, and red sneakers with white soles. The character's hands are tucked into its pockets, and it has a slight smirk on its face. The background is a solid gray color, and the image has a hand-drawn, slightly blurry quality. The character's head is turned to the left, and its body is facing forward. The overall style is simple and cartoonish, with bold lines and limited shading.
- azimuth
- 0
- distance
- 1.5
- elevation
- 0
- focal_length
- 1.3887
- guidance_scale
- 4
- negative_prompt
- monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation
- num_inference_steps
- 70
- use_input_image_size
{ "task": "subject_driven", "width": 512, "height": 512, "image1": "https://replicate.delivery/pbxt/MEbz1kdHKREEvMhD0ylI4YyMcunezsb6aGCUw4owxY6cAsft/chill_guy.jpg", "prompt": "<item: cartoon dog> [[img0]] a cartoon character resembling a dog, sitting on a beach. The character has a long, narrow face with a black nose and brown eyes. It's wearing a gray sweatshirt, blue jeans rolled up at the bottom, and red sneakers with white soles. it has a slight smirk on its face [[img1]] The photo features a cartoon character resembling a do. The character has a long, narrow face with a black nose and brown eyes. It's wearing a gray sweatshirt, blue jeans rolled up at the bottom, and red sneakers with white soles. The character's hands are tucked into its pockets, and it has a slight smirk on its face. The background is a solid gray color, and the image has a hand-drawn, slightly blurry quality. The character's head is turned to the left, and its body is facing forward. The overall style is simple and cartoonish, with bold lines and limited shading.", "azimuth": "0", "distance": "1.5", "elevation": "0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 70, "use_input_image_size": false }
npm install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run chenxwh/onediffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "chenxwh/onediffusion:f69674f4fc4fb6f6b085b7cd6a00a4ee5d7014d8f5b2dea7bc551cc996129307", { input: { task: "subject_driven", width: 512, height: 512, image1: "https://replicate.delivery/pbxt/MEbz1kdHKREEvMhD0ylI4YyMcunezsb6aGCUw4owxY6cAsft/chill_guy.jpg", prompt: "<item: cartoon dog> [[img0]] a cartoon character resembling a dog, sitting on a beach. The character has a long, narrow face with a black nose and brown eyes. It's wearing a gray sweatshirt, blue jeans rolled up at the bottom, and red sneakers with white soles. it has a slight smirk on its face [[img1]] The photo features a cartoon character resembling a do. The character has a long, narrow face with a black nose and brown eyes. It's wearing a gray sweatshirt, blue jeans rolled up at the bottom, and red sneakers with white soles. The character's hands are tucked into its pockets, and it has a slight smirk on its face. The background is a solid gray color, and the image has a hand-drawn, slightly blurry quality. The character's head is turned to the left, and its body is facing forward. The overall style is simple and cartoonish, with bold lines and limited shading.", azimuth: "0", distance: "1.5", elevation: "0", focal_length: 1.3887, guidance_scale: 4, negative_prompt: "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", num_inference_steps: 70, use_input_image_size: false } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the clientimport replicate
Run chenxwh/onediffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "chenxwh/onediffusion:f69674f4fc4fb6f6b085b7cd6a00a4ee5d7014d8f5b2dea7bc551cc996129307", input={ "task": "subject_driven", "width": 512, "height": 512, "image1": "https://replicate.delivery/pbxt/MEbz1kdHKREEvMhD0ylI4YyMcunezsb6aGCUw4owxY6cAsft/chill_guy.jpg", "prompt": "<item: cartoon dog> [[img0]] a cartoon character resembling a dog, sitting on a beach. The character has a long, narrow face with a black nose and brown eyes. It's wearing a gray sweatshirt, blue jeans rolled up at the bottom, and red sneakers with white soles. it has a slight smirk on its face [[img1]] The photo features a cartoon character resembling a do. The character has a long, narrow face with a black nose and brown eyes. It's wearing a gray sweatshirt, blue jeans rolled up at the bottom, and red sneakers with white soles. The character's hands are tucked into its pockets, and it has a slight smirk on its face. The background is a solid gray color, and the image has a hand-drawn, slightly blurry quality. The character's head is turned to the left, and its body is facing forward. The overall style is simple and cartoonish, with bold lines and limited shading.", "azimuth": "0", "distance": "1.5", "elevation": "0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 70, "use_input_image_size": False } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run chenxwh/onediffusion 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": "f69674f4fc4fb6f6b085b7cd6a00a4ee5d7014d8f5b2dea7bc551cc996129307", "input": { "task": "subject_driven", "width": 512, "height": 512, "image1": "https://replicate.delivery/pbxt/MEbz1kdHKREEvMhD0ylI4YyMcunezsb6aGCUw4owxY6cAsft/chill_guy.jpg", "prompt": "<item: cartoon dog> [[img0]] a cartoon character resembling a dog, sitting on a beach. The character has a long, narrow face with a black nose and brown eyes. It\'s wearing a gray sweatshirt, blue jeans rolled up at the bottom, and red sneakers with white soles. it has a slight smirk on its face [[img1]] The photo features a cartoon character resembling a do. The character has a long, narrow face with a black nose and brown eyes. It\'s wearing a gray sweatshirt, blue jeans rolled up at the bottom, and red sneakers with white soles. The character\'s hands are tucked into its pockets, and it has a slight smirk on its face. The background is a solid gray color, and the image has a hand-drawn, slightly blurry quality. The character\'s head is turned to the left, and its body is facing forward. The overall style is simple and cartoonish, with bold lines and limited shading.", "azimuth": "0", "distance": "1.5", "elevation": "0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 70, "use_input_image_size": false } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-12-30T14:20:38.330117Z", "created_at": "2024-12-30T14:20:23.016000Z", "data_removed": false, "error": null, "id": "wkwkztkrd1rm80cm2zr8mhskpw", "input": { "task": "subject_driven", "width": 512, "height": 512, "image1": "https://replicate.delivery/pbxt/MEbz1kdHKREEvMhD0ylI4YyMcunezsb6aGCUw4owxY6cAsft/chill_guy.jpg", "prompt": "<item: cartoon dog> [[img0]] a cartoon character resembling a dog, sitting on a beach. The character has a long, narrow face with a black nose and brown eyes. It's wearing a gray sweatshirt, blue jeans rolled up at the bottom, and red sneakers with white soles. it has a slight smirk on its face [[img1]] The photo features a cartoon character resembling a do. The character has a long, narrow face with a black nose and brown eyes. It's wearing a gray sweatshirt, blue jeans rolled up at the bottom, and red sneakers with white soles. The character's hands are tucked into its pockets, and it has a slight smirk on its face. The background is a solid gray color, and the image has a hand-drawn, slightly blurry quality. The character's head is turned to the left, and its body is facing forward. The overall style is simple and cartoonish, with bold lines and limited shading.", "azimuth": "0", "distance": "1.5", "elevation": "0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 70, "use_input_image_size": false }, "logs": "Using width, height: 512, 512\nUsing seed: 47235\nUsing prompt: [[subject_driven]] <item: cartoon dog> [[img0]] a cartoon character resembling a dog, sitting on a beach. The character has a long, narrow face with a black nose and brown eyes. It's wearing a gray sweatshirt, blue jeans rolled up at the bottom, and red sneakers with white soles. it has a slight smirk on its face [[img1]] The photo features a cartoon character resembling a do. The character has a long, narrow face with a black nose and brown eyes. It's wearing a gray sweatshirt, blue jeans rolled up at the bottom, and red sneakers with white soles. The character's hands are tucked into its pockets, and it has a slight smirk on its face. The background is a solid gray color, and the image has a hand-drawn, slightly blurry quality. The character's head is turned to the left, and its body is facing forward. The overall style is simple and cartoonish, with bold lines and limited shading.\n 0%| | 0/70 [00:00<?, ?it/s]\n 1%|▏ | 1/70 [00:00<00:14, 4.72it/s]\n 3%|▎ | 2/70 [00:00<00:14, 4.82it/s]\n 4%|▍ | 3/70 [00:00<00:14, 4.74it/s]\n 6%|▌ | 4/70 [00:00<00:13, 4.72it/s]\n 7%|▋ | 5/70 [00:01<00:13, 4.70it/s]\n 9%|▊ | 6/70 [00:01<00:13, 4.69it/s]\n 10%|█ | 7/70 [00:01<00:13, 4.68it/s]\n 11%|█▏ | 8/70 [00:01<00:13, 4.68it/s]\n 13%|█▎ | 9/70 [00:01<00:13, 4.68it/s]\n 14%|█▍ | 10/70 [00:02<00:12, 4.68it/s]\n 16%|█▌ | 11/70 [00:02<00:12, 4.67it/s]\n 17%|█▋ | 12/70 [00:02<00:12, 4.67it/s]\n 19%|█▊ | 13/70 [00:02<00:12, 4.67it/s]\n 20%|██ | 14/70 [00:02<00:11, 4.67it/s]\n 21%|██▏ | 15/70 [00:03<00:11, 4.67it/s]\n 23%|██▎ | 16/70 [00:03<00:11, 4.67it/s]\n 24%|██▍ | 17/70 [00:03<00:11, 4.66it/s]\n 26%|██▌ | 18/70 [00:03<00:11, 4.67it/s]\n 27%|██▋ | 19/70 [00:04<00:10, 4.66it/s]\n 29%|██▊ | 20/70 [00:04<00:10, 4.66it/s]\n 30%|███ | 21/70 [00:04<00:10, 4.66it/s]\n 31%|███▏ | 22/70 [00:04<00:10, 4.66it/s]\n 33%|███▎ | 23/70 [00:04<00:10, 4.66it/s]\n 34%|███▍ | 24/70 [00:05<00:09, 4.66it/s]\n 36%|███▌ | 25/70 [00:05<00:09, 4.66it/s]\n 37%|███▋ | 26/70 [00:05<00:09, 4.66it/s]\n 39%|███▊ | 27/70 [00:05<00:09, 4.66it/s]\n 40%|████ | 28/70 [00:05<00:09, 4.66it/s]\n 41%|████▏ | 29/70 [00:06<00:08, 4.66it/s]\n 43%|████▎ | 30/70 [00:06<00:08, 4.66it/s]\n 44%|████▍ | 31/70 [00:06<00:08, 4.66it/s]\n 46%|████▌ | 32/70 [00:06<00:08, 4.66it/s]\n 47%|████▋ | 33/70 [00:07<00:07, 4.66it/s]\n 49%|████▊ | 34/70 [00:07<00:07, 4.65it/s]\n 50%|█████ | 35/70 [00:07<00:07, 4.65it/s]\n 51%|█████▏ | 36/70 [00:07<00:07, 4.66it/s]\n 53%|█████▎ | 37/70 [00:07<00:07, 4.66it/s]\n 54%|█████▍ | 38/70 [00:08<00:06, 4.65it/s]\n 56%|█████▌ | 39/70 [00:08<00:06, 4.65it/s]\n 57%|█████▋ | 40/70 [00:08<00:06, 4.65it/s]\n 59%|█████▊ | 41/70 [00:08<00:06, 4.65it/s]\n 60%|██████ | 42/70 [00:08<00:06, 4.65it/s]\n 61%|██████▏ | 43/70 [00:09<00:05, 4.65it/s]\n 63%|██████▎ | 44/70 [00:09<00:05, 4.65it/s]\n 64%|██████▍ | 45/70 [00:09<00:05, 4.65it/s]\n 66%|██████▌ | 46/70 [00:09<00:05, 4.65it/s]\n 67%|██████▋ | 47/70 [00:10<00:04, 4.65it/s]\n 69%|██████▊ | 48/70 [00:10<00:04, 4.65it/s]\n 70%|███████ | 49/70 [00:10<00:04, 4.65it/s]\n 71%|███████▏ | 50/70 [00:10<00:04, 4.65it/s]\n 73%|███████▎ | 51/70 [00:10<00:04, 4.65it/s]\n 74%|███████▍ | 52/70 [00:11<00:03, 4.63it/s]\n 76%|███████▌ | 53/70 [00:11<00:03, 4.64it/s]\n 77%|███████▋ | 54/70 [00:11<00:03, 4.64it/s]\n 79%|███████▊ | 55/70 [00:11<00:03, 4.64it/s]\n 80%|████████ | 56/70 [00:12<00:03, 4.64it/s]\n 81%|████████▏ | 57/70 [00:12<00:02, 4.64it/s]\n 83%|████████▎ | 58/70 [00:12<00:02, 4.64it/s]\n 84%|████████▍ | 59/70 [00:12<00:02, 4.64it/s]\n 86%|████████▌ | 60/70 [00:12<00:02, 4.64it/s]\n 87%|████████▋ | 61/70 [00:13<00:01, 4.64it/s]\n 89%|████████▊ | 62/70 [00:13<00:01, 4.64it/s]\n 90%|█████████ | 63/70 [00:13<00:01, 4.64it/s]\n 91%|█████████▏| 64/70 [00:13<00:01, 4.64it/s]\n 93%|█████████▎| 65/70 [00:13<00:01, 4.63it/s]\n 94%|█████████▍| 66/70 [00:14<00:00, 4.63it/s]\n 96%|█████████▌| 67/70 [00:14<00:00, 4.63it/s]\n 97%|█████████▋| 68/70 [00:14<00:00, 4.63it/s]\n 99%|█████████▊| 69/70 [00:14<00:00, 4.63it/s]\n100%|██████████| 70/70 [00:15<00:00, 4.63it/s]\n100%|██████████| 70/70 [00:15<00:00, 4.66it/s]", "metrics": { "predict_time": 15.307524465, "total_time": 15.314117 }, "output": [ "https://replicate.delivery/xezq/QNrDNVli0MLTExvP7QytbejaMtTWsDS4s8DBYFEWazKb8CAKA/out_0.png" ], "started_at": "2024-12-30T14:20:23.022593Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bcwr-rhb2cstwe6qsktyx6xmeoyt62g7h4sjz3pg3xqzn32coioiv7z7a", "get": "https://api.replicate.com/v1/predictions/wkwkztkrd1rm80cm2zr8mhskpw", "cancel": "https://api.replicate.com/v1/predictions/wkwkztkrd1rm80cm2zr8mhskpw/cancel" }, "version": "c9f7b717764b5b64e02fad9cad583caee117e779c0ac0a8e2d80f154e68161a2" }
Generated inUsing width, height: 512, 512 Using seed: 47235 Using prompt: [[subject_driven]] <item: cartoon dog> [[img0]] a cartoon character resembling a dog, sitting on a beach. The character has a long, narrow face with a black nose and brown eyes. It's wearing a gray sweatshirt, blue jeans rolled up at the bottom, and red sneakers with white soles. it has a slight smirk on its face [[img1]] The photo features a cartoon character resembling a do. The character has a long, narrow face with a black nose and brown eyes. It's wearing a gray sweatshirt, blue jeans rolled up at the bottom, and red sneakers with white soles. The character's hands are tucked into its pockets, and it has a slight smirk on its face. The background is a solid gray color, and the image has a hand-drawn, slightly blurry quality. The character's head is turned to the left, and its body is facing forward. The overall style is simple and cartoonish, with bold lines and limited shading. 0%| | 0/70 [00:00<?, ?it/s] 1%|▏ | 1/70 [00:00<00:14, 4.72it/s] 3%|▎ | 2/70 [00:00<00:14, 4.82it/s] 4%|▍ | 3/70 [00:00<00:14, 4.74it/s] 6%|▌ | 4/70 [00:00<00:13, 4.72it/s] 7%|▋ | 5/70 [00:01<00:13, 4.70it/s] 9%|▊ | 6/70 [00:01<00:13, 4.69it/s] 10%|█ | 7/70 [00:01<00:13, 4.68it/s] 11%|█▏ | 8/70 [00:01<00:13, 4.68it/s] 13%|█▎ | 9/70 [00:01<00:13, 4.68it/s] 14%|█▍ | 10/70 [00:02<00:12, 4.68it/s] 16%|█▌ | 11/70 [00:02<00:12, 4.67it/s] 17%|█▋ | 12/70 [00:02<00:12, 4.67it/s] 19%|█▊ | 13/70 [00:02<00:12, 4.67it/s] 20%|██ | 14/70 [00:02<00:11, 4.67it/s] 21%|██▏ | 15/70 [00:03<00:11, 4.67it/s] 23%|██▎ | 16/70 [00:03<00:11, 4.67it/s] 24%|██▍ | 17/70 [00:03<00:11, 4.66it/s] 26%|██▌ | 18/70 [00:03<00:11, 4.67it/s] 27%|██▋ | 19/70 [00:04<00:10, 4.66it/s] 29%|██▊ | 20/70 [00:04<00:10, 4.66it/s] 30%|███ | 21/70 [00:04<00:10, 4.66it/s] 31%|███▏ | 22/70 [00:04<00:10, 4.66it/s] 33%|███▎ | 23/70 [00:04<00:10, 4.66it/s] 34%|███▍ | 24/70 [00:05<00:09, 4.66it/s] 36%|███▌ | 25/70 [00:05<00:09, 4.66it/s] 37%|███▋ | 26/70 [00:05<00:09, 4.66it/s] 39%|███▊ | 27/70 [00:05<00:09, 4.66it/s] 40%|████ | 28/70 [00:05<00:09, 4.66it/s] 41%|████▏ | 29/70 [00:06<00:08, 4.66it/s] 43%|████▎ | 30/70 [00:06<00:08, 4.66it/s] 44%|████▍ | 31/70 [00:06<00:08, 4.66it/s] 46%|████▌ | 32/70 [00:06<00:08, 4.66it/s] 47%|████▋ | 33/70 [00:07<00:07, 4.66it/s] 49%|████▊ | 34/70 [00:07<00:07, 4.65it/s] 50%|█████ | 35/70 [00:07<00:07, 4.65it/s] 51%|█████▏ | 36/70 [00:07<00:07, 4.66it/s] 53%|█████▎ | 37/70 [00:07<00:07, 4.66it/s] 54%|█████▍ | 38/70 [00:08<00:06, 4.65it/s] 56%|█████▌ | 39/70 [00:08<00:06, 4.65it/s] 57%|█████▋ | 40/70 [00:08<00:06, 4.65it/s] 59%|█████▊ | 41/70 [00:08<00:06, 4.65it/s] 60%|██████ | 42/70 [00:08<00:06, 4.65it/s] 61%|██████▏ | 43/70 [00:09<00:05, 4.65it/s] 63%|██████▎ | 44/70 [00:09<00:05, 4.65it/s] 64%|██████▍ | 45/70 [00:09<00:05, 4.65it/s] 66%|██████▌ | 46/70 [00:09<00:05, 4.65it/s] 67%|██████▋ | 47/70 [00:10<00:04, 4.65it/s] 69%|██████▊ | 48/70 [00:10<00:04, 4.65it/s] 70%|███████ | 49/70 [00:10<00:04, 4.65it/s] 71%|███████▏ | 50/70 [00:10<00:04, 4.65it/s] 73%|███████▎ | 51/70 [00:10<00:04, 4.65it/s] 74%|███████▍ | 52/70 [00:11<00:03, 4.63it/s] 76%|███████▌ | 53/70 [00:11<00:03, 4.64it/s] 77%|███████▋ | 54/70 [00:11<00:03, 4.64it/s] 79%|███████▊ | 55/70 [00:11<00:03, 4.64it/s] 80%|████████ | 56/70 [00:12<00:03, 4.64it/s] 81%|████████▏ | 57/70 [00:12<00:02, 4.64it/s] 83%|████████▎ | 58/70 [00:12<00:02, 4.64it/s] 84%|████████▍ | 59/70 [00:12<00:02, 4.64it/s] 86%|████████▌ | 60/70 [00:12<00:02, 4.64it/s] 87%|████████▋ | 61/70 [00:13<00:01, 4.64it/s] 89%|████████▊ | 62/70 [00:13<00:01, 4.64it/s] 90%|█████████ | 63/70 [00:13<00:01, 4.64it/s] 91%|█████████▏| 64/70 [00:13<00:01, 4.64it/s] 93%|█████████▎| 65/70 [00:13<00:01, 4.63it/s] 94%|█████████▍| 66/70 [00:14<00:00, 4.63it/s] 96%|█████████▌| 67/70 [00:14<00:00, 4.63it/s] 97%|█████████▋| 68/70 [00:14<00:00, 4.63it/s] 99%|█████████▊| 69/70 [00:14<00:00, 4.63it/s] 100%|██████████| 70/70 [00:15<00:00, 4.63it/s] 100%|██████████| 70/70 [00:15<00:00, 4.66it/s]
Prediction
chenxwh/onediffusion:f69674f4ID2tg20vj00srma0cm30dbfesammStatusSucceededSourceWebHardwareL40STotal durationCreatedInput
- task
- text2image
- width
- 1024
- height
- 1024
- prompt
- A bipedal black cat wearing a huge oversized witch hat, a wizards robe, casting a spell, in an enchanted forest. The scene is filled with fireflies and moss on surrounding rocks and trees
- azimuth
- 0
- distance
- 1.5
- elevation
- 0
- denoise_mask
- 0
- focal_length
- 1.3887
- guidance_scale
- 4
- negative_prompt
- monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation
- num_inference_steps
- 50
- use_input_image_size
{ "task": "text2image", "width": 1024, "height": 1024, "prompt": "A bipedal black cat wearing a huge oversized witch hat, a wizards robe, casting a spell, in an enchanted forest. The scene is filled with fireflies and moss on surrounding rocks and trees", "azimuth": "0", "distance": "1.5", "elevation": "0", "denoise_mask": "0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": false }
npm install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run chenxwh/onediffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "chenxwh/onediffusion:f69674f4fc4fb6f6b085b7cd6a00a4ee5d7014d8f5b2dea7bc551cc996129307", { input: { task: "text2image", width: 1024, height: 1024, prompt: "A bipedal black cat wearing a huge oversized witch hat, a wizards robe, casting a spell, in an enchanted forest. The scene is filled with fireflies and moss on surrounding rocks and trees", azimuth: "0", distance: "1.5", elevation: "0", denoise_mask: "0", focal_length: 1.3887, guidance_scale: 4, negative_prompt: "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", num_inference_steps: 50, use_input_image_size: false } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the clientimport replicate
Run chenxwh/onediffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "chenxwh/onediffusion:f69674f4fc4fb6f6b085b7cd6a00a4ee5d7014d8f5b2dea7bc551cc996129307", input={ "task": "text2image", "width": 1024, "height": 1024, "prompt": "A bipedal black cat wearing a huge oversized witch hat, a wizards robe, casting a spell, in an enchanted forest. The scene is filled with fireflies and moss on surrounding rocks and trees", "azimuth": "0", "distance": "1.5", "elevation": "0", "denoise_mask": "0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": False } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run chenxwh/onediffusion 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": "f69674f4fc4fb6f6b085b7cd6a00a4ee5d7014d8f5b2dea7bc551cc996129307", "input": { "task": "text2image", "width": 1024, "height": 1024, "prompt": "A bipedal black cat wearing a huge oversized witch hat, a wizards robe, casting a spell, in an enchanted forest. The scene is filled with fireflies and moss on surrounding rocks and trees", "azimuth": "0", "distance": "1.5", "elevation": "0", "denoise_mask": "0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": false } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-12-30T15:06:43.301826Z", "created_at": "2024-12-30T15:06:01.094000Z", "data_removed": false, "error": null, "id": "2tg20vj00srma0cm30dbfesamm", "input": { "task": "text2image", "width": 1024, "height": 1024, "prompt": "A bipedal black cat wearing a huge oversized witch hat, a wizards robe, casting a spell, in an enchanted forest. The scene is filled with fireflies and moss on surrounding rocks and trees", "azimuth": "0", "distance": "1.5", "elevation": "0", "denoise_mask": "0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": false }, "logs": "Using width, height: 1024, 1024\nUsing seed: 9157\nUsing prompt: [[text2image]] A bipedal black cat wearing a huge oversized witch hat, a wizards robe, casting a spell, in an enchanted forest. The scene is filled with fireflies and moss on surrounding rocks and trees\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:25, 1.94it/s]\n 4%|▍ | 2/50 [00:00<00:23, 2.02it/s]\n 6%|▌ | 3/50 [00:01<00:23, 2.02it/s]\n 8%|▊ | 4/50 [00:01<00:22, 2.01it/s]\n 10%|█ | 5/50 [00:02<00:22, 2.01it/s]\n 12%|█▏ | 6/50 [00:02<00:21, 2.01it/s]\n 14%|█▍ | 7/50 [00:03<00:21, 2.01it/s]\n 16%|█▌ | 8/50 [00:03<00:20, 2.01it/s]\n 18%|█▊ | 9/50 [00:04<00:20, 2.01it/s]\n 20%|██ | 10/50 [00:04<00:19, 2.01it/s]\n 22%|██▏ | 11/50 [00:05<00:19, 2.01it/s]\n 24%|██▍ | 12/50 [00:05<00:18, 2.01it/s]\n 26%|██▌ | 13/50 [00:06<00:18, 2.01it/s]\n 28%|██▊ | 14/50 [00:06<00:17, 2.00it/s]\n 30%|███ | 15/50 [00:07<00:17, 2.00it/s]\n 32%|███▏ | 16/50 [00:07<00:16, 2.00it/s]\n 34%|███▍ | 17/50 [00:08<00:16, 2.00it/s]\n 36%|███▌ | 18/50 [00:08<00:15, 2.00it/s]\n 38%|███▊ | 19/50 [00:09<00:15, 2.00it/s]\n 40%|████ | 20/50 [00:09<00:14, 2.00it/s]\n 42%|████▏ | 21/50 [00:10<00:14, 2.00it/s]\n 44%|████▍ | 22/50 [00:10<00:14, 2.00it/s]\n 46%|████▌ | 23/50 [00:11<00:13, 2.00it/s]\n 48%|████▊ | 24/50 [00:11<00:13, 2.00it/s]\n 50%|█████ | 25/50 [00:12<00:12, 2.00it/s]\n 52%|█████▏ | 26/50 [00:12<00:12, 2.00it/s]\n 54%|█████▍ | 27/50 [00:13<00:11, 2.00it/s]\n 56%|█████▌ | 28/50 [00:13<00:11, 2.00it/s]\n 58%|█████▊ | 29/50 [00:14<00:10, 2.00it/s]\n 60%|██████ | 30/50 [00:14<00:10, 2.00it/s]\n 62%|██████▏ | 31/50 [00:15<00:09, 2.00it/s]\n 64%|██████▍ | 32/50 [00:15<00:09, 2.00it/s]\n 66%|██████▌ | 33/50 [00:16<00:08, 1.99it/s]\n 68%|██████▊ | 34/50 [00:16<00:08, 1.99it/s]\n 70%|███████ | 35/50 [00:17<00:07, 1.99it/s]\n 72%|███████▏ | 36/50 [00:17<00:07, 1.99it/s]\n 74%|███████▍ | 37/50 [00:18<00:06, 1.99it/s]\n 76%|███████▌ | 38/50 [00:18<00:06, 1.99it/s]\n 78%|███████▊ | 39/50 [00:19<00:05, 1.99it/s]\n 80%|████████ | 40/50 [00:19<00:05, 1.99it/s]\n 82%|████████▏ | 41/50 [00:20<00:04, 1.99it/s]\n 84%|████████▍ | 42/50 [00:21<00:04, 1.99it/s]\n 86%|████████▌ | 43/50 [00:21<00:03, 1.99it/s]\n 88%|████████▊ | 44/50 [00:22<00:03, 1.99it/s]\n 90%|█████████ | 45/50 [00:22<00:02, 1.99it/s]\n 92%|█████████▏| 46/50 [00:23<00:02, 1.99it/s]\n 94%|█████████▍| 47/50 [00:23<00:01, 1.99it/s]\n 96%|█████████▌| 48/50 [00:24<00:01, 1.99it/s]\n 98%|█████████▊| 49/50 [00:24<00:00, 1.99it/s]\n100%|██████████| 50/50 [00:25<00:00, 1.99it/s]\n100%|██████████| 50/50 [00:25<00:00, 2.00it/s]", "metrics": { "predict_time": 25.745820312, "total_time": 42.207826 }, "output": [ "https://replicate.delivery/xezq/Dw4sHAfzlDVxZql6FCCLeEfSyorUHLJ07vquqFPCTKgGINAoA/out_0.png" ], "started_at": "2024-12-30T15:06:17.556006Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bcwr-pv2tkck447vj2olhvx5eltvhyji643g575754flo3u4ygcz6hhya", "get": "https://api.replicate.com/v1/predictions/2tg20vj00srma0cm30dbfesamm", "cancel": "https://api.replicate.com/v1/predictions/2tg20vj00srma0cm30dbfesamm/cancel" }, "version": "de9c4daae9e4792c9525e3fe6e605090bdaba107b0336eb873cc97336ec1a126" }
Generated inUsing width, height: 1024, 1024 Using seed: 9157 Using prompt: [[text2image]] A bipedal black cat wearing a huge oversized witch hat, a wizards robe, casting a spell, in an enchanted forest. The scene is filled with fireflies and moss on surrounding rocks and trees 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:25, 1.94it/s] 4%|▍ | 2/50 [00:00<00:23, 2.02it/s] 6%|▌ | 3/50 [00:01<00:23, 2.02it/s] 8%|▊ | 4/50 [00:01<00:22, 2.01it/s] 10%|█ | 5/50 [00:02<00:22, 2.01it/s] 12%|█▏ | 6/50 [00:02<00:21, 2.01it/s] 14%|█▍ | 7/50 [00:03<00:21, 2.01it/s] 16%|█▌ | 8/50 [00:03<00:20, 2.01it/s] 18%|█▊ | 9/50 [00:04<00:20, 2.01it/s] 20%|██ | 10/50 [00:04<00:19, 2.01it/s] 22%|██▏ | 11/50 [00:05<00:19, 2.01it/s] 24%|██▍ | 12/50 [00:05<00:18, 2.01it/s] 26%|██▌ | 13/50 [00:06<00:18, 2.01it/s] 28%|██▊ | 14/50 [00:06<00:17, 2.00it/s] 30%|███ | 15/50 [00:07<00:17, 2.00it/s] 32%|███▏ | 16/50 [00:07<00:16, 2.00it/s] 34%|███▍ | 17/50 [00:08<00:16, 2.00it/s] 36%|███▌ | 18/50 [00:08<00:15, 2.00it/s] 38%|███▊ | 19/50 [00:09<00:15, 2.00it/s] 40%|████ | 20/50 [00:09<00:14, 2.00it/s] 42%|████▏ | 21/50 [00:10<00:14, 2.00it/s] 44%|████▍ | 22/50 [00:10<00:14, 2.00it/s] 46%|████▌ | 23/50 [00:11<00:13, 2.00it/s] 48%|████▊ | 24/50 [00:11<00:13, 2.00it/s] 50%|█████ | 25/50 [00:12<00:12, 2.00it/s] 52%|█████▏ | 26/50 [00:12<00:12, 2.00it/s] 54%|█████▍ | 27/50 [00:13<00:11, 2.00it/s] 56%|█████▌ | 28/50 [00:13<00:11, 2.00it/s] 58%|█████▊ | 29/50 [00:14<00:10, 2.00it/s] 60%|██████ | 30/50 [00:14<00:10, 2.00it/s] 62%|██████▏ | 31/50 [00:15<00:09, 2.00it/s] 64%|██████▍ | 32/50 [00:15<00:09, 2.00it/s] 66%|██████▌ | 33/50 [00:16<00:08, 1.99it/s] 68%|██████▊ | 34/50 [00:16<00:08, 1.99it/s] 70%|███████ | 35/50 [00:17<00:07, 1.99it/s] 72%|███████▏ | 36/50 [00:17<00:07, 1.99it/s] 74%|███████▍ | 37/50 [00:18<00:06, 1.99it/s] 76%|███████▌ | 38/50 [00:18<00:06, 1.99it/s] 78%|███████▊ | 39/50 [00:19<00:05, 1.99it/s] 80%|████████ | 40/50 [00:19<00:05, 1.99it/s] 82%|████████▏ | 41/50 [00:20<00:04, 1.99it/s] 84%|████████▍ | 42/50 [00:21<00:04, 1.99it/s] 86%|████████▌ | 43/50 [00:21<00:03, 1.99it/s] 88%|████████▊ | 44/50 [00:22<00:03, 1.99it/s] 90%|█████████ | 45/50 [00:22<00:02, 1.99it/s] 92%|█████████▏| 46/50 [00:23<00:02, 1.99it/s] 94%|█████████▍| 47/50 [00:23<00:01, 1.99it/s] 96%|█████████▌| 48/50 [00:24<00:01, 1.99it/s] 98%|█████████▊| 49/50 [00:24<00:00, 1.99it/s] 100%|██████████| 50/50 [00:25<00:00, 1.99it/s] 100%|██████████| 50/50 [00:25<00:00, 2.00it/s]
Prediction
chenxwh/onediffusion:f69674f4ID3v06z2bwh9rmc0cm30frah2jycStatusSucceededSourceWebHardwareL40STotal durationCreatedInput
- task
- faceid
- width
- 1024
- height
- 1024
- prompt
- [[img0]] detailed face, A woman with dark hair styled in an intricate updo, wearing a traditional orange and black outfit with elaborate gold embroidery. She has an elegant, poised expression, standing against a serene outdoor setting with classical architecture [[img1]] A young Asian woman with long dark hair and brown eyes smiles at the camera. She wears a red tank top with white flowers and green leaves. The background is blurred, with white and blue tones visible. The image has a slightly grainy quality. [[img2]] A young Asian woman in traditional attire stands against a brown background. She wears a white dress adorned with purple and green floral patterns. Her hair is styled in a bun, and she holds a small white lace umbrella with a gold handle. The image captures her elegant appearance and cultural dress. [[img3]] A woman in traditional Asian attire stands in front of a blurred building. She wears a green robe with floral designs and a black hat with lace. A man in a red robe and black hat stands behind her. The scene appears to be set in an Asian country.
- azimuth
- 0
- distance
- 1.5
- elevation
- 0
- denoise_mask
- 1, 0, 0, 0
- focal_length
- 1.3887
- guidance_scale
- 4
- negative_prompt
- monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation
- num_inference_steps
- 50
- use_input_image_size
{ "task": "faceid", "width": 1024, "height": 1024, "image1": "https://replicate.delivery/pbxt/MEclgWn7tJPKoj7V2DsxtauylisSbg1AzzlFmCK9pZWaIex8/image.webp", "image2": "https://replicate.delivery/pbxt/MEclg9MolH2OG1dwo2C5zPhxnnGYQ4VFAysKHAyr5ORlgMNA/image%20%281%29.webp", "image3": "https://replicate.delivery/pbxt/MEclgBOrWcbUp6wWiGisxSdULWNxnWXY1KjrDBiYB019wyvu/image%20%282%29.webp", "prompt": "[[img0]] detailed face, A woman with dark hair styled in an intricate updo, wearing a traditional orange and black outfit with elaborate gold embroidery. She has an elegant, poised expression, standing against a serene outdoor setting with classical architecture [[img1]] A young Asian woman with long dark hair and brown eyes smiles at the camera. She wears a red tank top with white flowers and green leaves. The background is blurred, with white and blue tones visible. The image has a slightly grainy quality. [[img2]] A young Asian woman in traditional attire stands against a brown background. She wears a white dress adorned with purple and green floral patterns. Her hair is styled in a bun, and she holds a small white lace umbrella with a gold handle. The image captures her elegant appearance and cultural dress. [[img3]] A woman in traditional Asian attire stands in front of a blurred building. She wears a green robe with floral designs and a black hat with lace. A man in a red robe and black hat stands behind her. The scene appears to be set in an Asian country.", "azimuth": "0", "distance": "1.5", "elevation": "0", "denoise_mask": "1, 0, 0, 0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": true }
npm install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run chenxwh/onediffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "chenxwh/onediffusion:f69674f4fc4fb6f6b085b7cd6a00a4ee5d7014d8f5b2dea7bc551cc996129307", { input: { task: "faceid", width: 1024, height: 1024, image1: "https://replicate.delivery/pbxt/MEclgWn7tJPKoj7V2DsxtauylisSbg1AzzlFmCK9pZWaIex8/image.webp", image2: "https://replicate.delivery/pbxt/MEclg9MolH2OG1dwo2C5zPhxnnGYQ4VFAysKHAyr5ORlgMNA/image%20%281%29.webp", image3: "https://replicate.delivery/pbxt/MEclgBOrWcbUp6wWiGisxSdULWNxnWXY1KjrDBiYB019wyvu/image%20%282%29.webp", prompt: "[[img0]] detailed face, A woman with dark hair styled in an intricate updo, wearing a traditional orange and black outfit with elaborate gold embroidery. She has an elegant, poised expression, standing against a serene outdoor setting with classical architecture [[img1]] A young Asian woman with long dark hair and brown eyes smiles at the camera. She wears a red tank top with white flowers and green leaves. The background is blurred, with white and blue tones visible. The image has a slightly grainy quality. [[img2]] A young Asian woman in traditional attire stands against a brown background. She wears a white dress adorned with purple and green floral patterns. Her hair is styled in a bun, and she holds a small white lace umbrella with a gold handle. The image captures her elegant appearance and cultural dress. [[img3]] A woman in traditional Asian attire stands in front of a blurred building. She wears a green robe with floral designs and a black hat with lace. A man in a red robe and black hat stands behind her. The scene appears to be set in an Asian country.", azimuth: "0", distance: "1.5", elevation: "0", denoise_mask: "1, 0, 0, 0", focal_length: 1.3887, guidance_scale: 4, negative_prompt: "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", num_inference_steps: 50, use_input_image_size: true } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the clientimport replicate
Run chenxwh/onediffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "chenxwh/onediffusion:f69674f4fc4fb6f6b085b7cd6a00a4ee5d7014d8f5b2dea7bc551cc996129307", input={ "task": "faceid", "width": 1024, "height": 1024, "image1": "https://replicate.delivery/pbxt/MEclgWn7tJPKoj7V2DsxtauylisSbg1AzzlFmCK9pZWaIex8/image.webp", "image2": "https://replicate.delivery/pbxt/MEclg9MolH2OG1dwo2C5zPhxnnGYQ4VFAysKHAyr5ORlgMNA/image%20%281%29.webp", "image3": "https://replicate.delivery/pbxt/MEclgBOrWcbUp6wWiGisxSdULWNxnWXY1KjrDBiYB019wyvu/image%20%282%29.webp", "prompt": "[[img0]] detailed face, A woman with dark hair styled in an intricate updo, wearing a traditional orange and black outfit with elaborate gold embroidery. She has an elegant, poised expression, standing against a serene outdoor setting with classical architecture [[img1]] A young Asian woman with long dark hair and brown eyes smiles at the camera. She wears a red tank top with white flowers and green leaves. The background is blurred, with white and blue tones visible. The image has a slightly grainy quality. [[img2]] A young Asian woman in traditional attire stands against a brown background. She wears a white dress adorned with purple and green floral patterns. Her hair is styled in a bun, and she holds a small white lace umbrella with a gold handle. The image captures her elegant appearance and cultural dress. [[img3]] A woman in traditional Asian attire stands in front of a blurred building. She wears a green robe with floral designs and a black hat with lace. A man in a red robe and black hat stands behind her. The scene appears to be set in an Asian country.", "azimuth": "0", "distance": "1.5", "elevation": "0", "denoise_mask": "1, 0, 0, 0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": True } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run chenxwh/onediffusion 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": "f69674f4fc4fb6f6b085b7cd6a00a4ee5d7014d8f5b2dea7bc551cc996129307", "input": { "task": "faceid", "width": 1024, "height": 1024, "image1": "https://replicate.delivery/pbxt/MEclgWn7tJPKoj7V2DsxtauylisSbg1AzzlFmCK9pZWaIex8/image.webp", "image2": "https://replicate.delivery/pbxt/MEclg9MolH2OG1dwo2C5zPhxnnGYQ4VFAysKHAyr5ORlgMNA/image%20%281%29.webp", "image3": "https://replicate.delivery/pbxt/MEclgBOrWcbUp6wWiGisxSdULWNxnWXY1KjrDBiYB019wyvu/image%20%282%29.webp", "prompt": "[[img0]] detailed face, A woman with dark hair styled in an intricate updo, wearing a traditional orange and black outfit with elaborate gold embroidery. She has an elegant, poised expression, standing against a serene outdoor setting with classical architecture [[img1]] A young Asian woman with long dark hair and brown eyes smiles at the camera. She wears a red tank top with white flowers and green leaves. The background is blurred, with white and blue tones visible. The image has a slightly grainy quality. [[img2]] A young Asian woman in traditional attire stands against a brown background. She wears a white dress adorned with purple and green floral patterns. Her hair is styled in a bun, and she holds a small white lace umbrella with a gold handle. The image captures her elegant appearance and cultural dress. [[img3]] A woman in traditional Asian attire stands in front of a blurred building. She wears a green robe with floral designs and a black hat with lace. A man in a red robe and black hat stands behind her. The scene appears to be set in an Asian country.", "azimuth": "0", "distance": "1.5", "elevation": "0", "denoise_mask": "1, 0, 0, 0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": true } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-12-30T15:13:09.089394Z", "created_at": "2024-12-30T15:11:44.266000Z", "data_removed": false, "error": null, "id": "3v06z2bwh9rmc0cm30frah2jyc", "input": { "task": "faceid", "width": 1024, "height": 1024, "image1": "https://replicate.delivery/pbxt/MEclgWn7tJPKoj7V2DsxtauylisSbg1AzzlFmCK9pZWaIex8/image.webp", "image2": "https://replicate.delivery/pbxt/MEclg9MolH2OG1dwo2C5zPhxnnGYQ4VFAysKHAyr5ORlgMNA/image%20%281%29.webp", "image3": "https://replicate.delivery/pbxt/MEclgBOrWcbUp6wWiGisxSdULWNxnWXY1KjrDBiYB019wyvu/image%20%282%29.webp", "prompt": "[[img0]] detailed face, A woman with dark hair styled in an intricate updo, wearing a traditional orange and black outfit with elaborate gold embroidery. She has an elegant, poised expression, standing against a serene outdoor setting with classical architecture [[img1]] A young Asian woman with long dark hair and brown eyes smiles at the camera. She wears a red tank top with white flowers and green leaves. The background is blurred, with white and blue tones visible. The image has a slightly grainy quality. [[img2]] A young Asian woman in traditional attire stands against a brown background. She wears a white dress adorned with purple and green floral patterns. Her hair is styled in a bun, and she holds a small white lace umbrella with a gold handle. The image captures her elegant appearance and cultural dress. [[img3]] A woman in traditional Asian attire stands in front of a blurred building. She wears a green robe with floral designs and a black hat with lace. A man in a red robe and black hat stands behind her. The scene appears to be set in an Asian country.", "azimuth": "0", "distance": "1.5", "elevation": "0", "denoise_mask": "1, 0, 0, 0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": true }, "logs": "Using width, height: 608, 896\nUsing seed: 61442\nUsing prompt: [[faceid]] [[img0]] detailed face, A woman with dark hair styled in an intricate updo, wearing a traditional orange and black outfit with elaborate gold embroidery. She has an elegant, poised expression, standing against a serene outdoor setting with classical architecture [[img1]] A young Asian woman with long dark hair and brown eyes smiles at the camera. She wears a red tank top with white flowers and green leaves. The background is blurred, with white and blue tones visible. The image has a slightly grainy quality. [[img2]] A young Asian woman in traditional attire stands against a brown background. She wears a white dress adorned with purple and green floral patterns. Her hair is styled in a bun, and she holds a small white lace umbrella with a gold handle. The image captures her elegant appearance and cultural dress. [[img3]] A woman in traditional Asian attire stands in front of a blurred building. She wears a green robe with floral designs and a black hat with lace. A man in a red robe and black hat stands behind her. The scene appears to be set in an Asian country.\n/src/onediffusion/diffusion/pipelines/image_processor.py:572: FutureWarning: Passing `image` as torch tensor with value range in [-1,1] is deprecated. The expected value range for image tensor is [0,1] when passing as pytorch tensor or numpy Array. You passed `image` with value range [-1.0,1.0]\nwarnings.warn(\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:01<00:56, 1.16s/it]\n 4%|▍ | 2/50 [00:02<00:54, 1.13s/it]\n 6%|▌ | 3/50 [00:03<00:53, 1.15s/it]\n 8%|▊ | 4/50 [00:04<00:53, 1.15s/it]\n 10%|█ | 5/50 [00:05<00:52, 1.16s/it]\n 12%|█▏ | 6/50 [00:06<00:50, 1.16s/it]\n 14%|█▍ | 7/50 [00:08<00:49, 1.16s/it]\n 16%|█▌ | 8/50 [00:09<00:48, 1.16s/it]\n 18%|█▊ | 9/50 [00:10<00:47, 1.16s/it]\n 20%|██ | 10/50 [00:11<00:46, 1.16s/it]\n 22%|██▏ | 11/50 [00:12<00:45, 1.16s/it]\n 24%|██▍ | 12/50 [00:13<00:44, 1.16s/it]\n 26%|██▌ | 13/50 [00:15<00:42, 1.16s/it]\n 28%|██▊ | 14/50 [00:16<00:41, 1.16s/it]\n 30%|███ | 15/50 [00:17<00:40, 1.16s/it]\n 32%|███▏ | 16/50 [00:18<00:39, 1.16s/it]\n 34%|███▍ | 17/50 [00:19<00:38, 1.16s/it]\n 36%|███▌ | 18/50 [00:20<00:37, 1.16s/it]\n 38%|███▊ | 19/50 [00:22<00:36, 1.16s/it]\n 40%|████ | 20/50 [00:23<00:34, 1.16s/it]\n 42%|████▏ | 21/50 [00:24<00:33, 1.16s/it]\n 44%|████▍ | 22/50 [00:25<00:32, 1.16s/it]\n 46%|████▌ | 23/50 [00:26<00:31, 1.16s/it]\n 48%|████▊ | 24/50 [00:27<00:30, 1.16s/it]\n 50%|█████ | 25/50 [00:28<00:29, 1.16s/it]\n 52%|█████▏ | 26/50 [00:30<00:27, 1.16s/it]\n 54%|█████▍ | 27/50 [00:31<00:26, 1.16s/it]\n 56%|█████▌ | 28/50 [00:32<00:25, 1.16s/it]\n 58%|█████▊ | 29/50 [00:33<00:24, 1.16s/it]\n 60%|██████ | 30/50 [00:34<00:23, 1.16s/it]\n 62%|██████▏ | 31/50 [00:35<00:22, 1.16s/it]\n 64%|██████▍ | 32/50 [00:37<00:20, 1.16s/it]\n 66%|██████▌ | 33/50 [00:38<00:19, 1.16s/it]\n 68%|██████▊ | 34/50 [00:39<00:18, 1.16s/it]\n 70%|███████ | 35/50 [00:40<00:17, 1.16s/it]\n 72%|███████▏ | 36/50 [00:41<00:16, 1.16s/it]\n 74%|███████▍ | 37/50 [00:42<00:15, 1.16s/it]\n 76%|███████▌ | 38/50 [00:44<00:14, 1.17s/it]\n 78%|███████▊ | 39/50 [00:45<00:12, 1.17s/it]\n 80%|████████ | 40/50 [00:46<00:11, 1.16s/it]\n 82%|████████▏ | 41/50 [00:47<00:10, 1.16s/it]\n 84%|████████▍ | 42/50 [00:48<00:09, 1.16s/it]\n 86%|████████▌ | 43/50 [00:49<00:08, 1.16s/it]\n 88%|████████▊ | 44/50 [00:51<00:06, 1.16s/it]\n 90%|█████████ | 45/50 [00:52<00:05, 1.16s/it]\n 92%|█████████▏| 46/50 [00:53<00:04, 1.16s/it]\n 94%|█████████▍| 47/50 [00:54<00:03, 1.16s/it]\n 96%|█████████▌| 48/50 [00:55<00:02, 1.16s/it]\n 98%|█████████▊| 49/50 [00:56<00:01, 1.16s/it]\n100%|██████████| 50/50 [00:58<00:00, 1.16s/it]\n100%|██████████| 50/50 [00:58<00:00, 1.16s/it]", "metrics": { "predict_time": 59.047270655, "total_time": 84.823394 }, "output": [ "https://replicate.delivery/xezq/RnEEZt22kRpfHCXZf8e2RpBkUbx6fkyNnjYTD8ot8JpVoaAQB/out_0.png" ], "started_at": "2024-12-30T15:12:10.042123Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bcwr-scieb5ewxh3baaedwq6pean257b3d5owoauo3ffrrzujytecpnpq", "get": "https://api.replicate.com/v1/predictions/3v06z2bwh9rmc0cm30frah2jyc", "cancel": "https://api.replicate.com/v1/predictions/3v06z2bwh9rmc0cm30frah2jyc/cancel" }, "version": "de9c4daae9e4792c9525e3fe6e605090bdaba107b0336eb873cc97336ec1a126" }
Generated inUsing width, height: 608, 896 Using seed: 61442 Using prompt: [[faceid]] [[img0]] detailed face, A woman with dark hair styled in an intricate updo, wearing a traditional orange and black outfit with elaborate gold embroidery. She has an elegant, poised expression, standing against a serene outdoor setting with classical architecture [[img1]] A young Asian woman with long dark hair and brown eyes smiles at the camera. She wears a red tank top with white flowers and green leaves. The background is blurred, with white and blue tones visible. The image has a slightly grainy quality. [[img2]] A young Asian woman in traditional attire stands against a brown background. She wears a white dress adorned with purple and green floral patterns. Her hair is styled in a bun, and she holds a small white lace umbrella with a gold handle. The image captures her elegant appearance and cultural dress. [[img3]] A woman in traditional Asian attire stands in front of a blurred building. She wears a green robe with floral designs and a black hat with lace. A man in a red robe and black hat stands behind her. The scene appears to be set in an Asian country. /src/onediffusion/diffusion/pipelines/image_processor.py:572: FutureWarning: Passing `image` as torch tensor with value range in [-1,1] is deprecated. The expected value range for image tensor is [0,1] when passing as pytorch tensor or numpy Array. You passed `image` with value range [-1.0,1.0] warnings.warn( 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:01<00:56, 1.16s/it] 4%|▍ | 2/50 [00:02<00:54, 1.13s/it] 6%|▌ | 3/50 [00:03<00:53, 1.15s/it] 8%|▊ | 4/50 [00:04<00:53, 1.15s/it] 10%|█ | 5/50 [00:05<00:52, 1.16s/it] 12%|█▏ | 6/50 [00:06<00:50, 1.16s/it] 14%|█▍ | 7/50 [00:08<00:49, 1.16s/it] 16%|█▌ | 8/50 [00:09<00:48, 1.16s/it] 18%|█▊ | 9/50 [00:10<00:47, 1.16s/it] 20%|██ | 10/50 [00:11<00:46, 1.16s/it] 22%|██▏ | 11/50 [00:12<00:45, 1.16s/it] 24%|██▍ | 12/50 [00:13<00:44, 1.16s/it] 26%|██▌ | 13/50 [00:15<00:42, 1.16s/it] 28%|██▊ | 14/50 [00:16<00:41, 1.16s/it] 30%|███ | 15/50 [00:17<00:40, 1.16s/it] 32%|███▏ | 16/50 [00:18<00:39, 1.16s/it] 34%|███▍ | 17/50 [00:19<00:38, 1.16s/it] 36%|███▌ | 18/50 [00:20<00:37, 1.16s/it] 38%|███▊ | 19/50 [00:22<00:36, 1.16s/it] 40%|████ | 20/50 [00:23<00:34, 1.16s/it] 42%|████▏ | 21/50 [00:24<00:33, 1.16s/it] 44%|████▍ | 22/50 [00:25<00:32, 1.16s/it] 46%|████▌ | 23/50 [00:26<00:31, 1.16s/it] 48%|████▊ | 24/50 [00:27<00:30, 1.16s/it] 50%|█████ | 25/50 [00:28<00:29, 1.16s/it] 52%|█████▏ | 26/50 [00:30<00:27, 1.16s/it] 54%|█████▍ | 27/50 [00:31<00:26, 1.16s/it] 56%|█████▌ | 28/50 [00:32<00:25, 1.16s/it] 58%|█████▊ | 29/50 [00:33<00:24, 1.16s/it] 60%|██████ | 30/50 [00:34<00:23, 1.16s/it] 62%|██████▏ | 31/50 [00:35<00:22, 1.16s/it] 64%|██████▍ | 32/50 [00:37<00:20, 1.16s/it] 66%|██████▌ | 33/50 [00:38<00:19, 1.16s/it] 68%|██████▊ | 34/50 [00:39<00:18, 1.16s/it] 70%|███████ | 35/50 [00:40<00:17, 1.16s/it] 72%|███████▏ | 36/50 [00:41<00:16, 1.16s/it] 74%|███████▍ | 37/50 [00:42<00:15, 1.16s/it] 76%|███████▌ | 38/50 [00:44<00:14, 1.17s/it] 78%|███████▊ | 39/50 [00:45<00:12, 1.17s/it] 80%|████████ | 40/50 [00:46<00:11, 1.16s/it] 82%|████████▏ | 41/50 [00:47<00:10, 1.16s/it] 84%|████████▍ | 42/50 [00:48<00:09, 1.16s/it] 86%|████████▌ | 43/50 [00:49<00:08, 1.16s/it] 88%|████████▊ | 44/50 [00:51<00:06, 1.16s/it] 90%|█████████ | 45/50 [00:52<00:05, 1.16s/it] 92%|█████████▏| 46/50 [00:53<00:04, 1.16s/it] 94%|█████████▍| 47/50 [00:54<00:03, 1.16s/it] 96%|█████████▌| 48/50 [00:55<00:02, 1.16s/it] 98%|█████████▊| 49/50 [00:56<00:01, 1.16s/it] 100%|██████████| 50/50 [00:58<00:00, 1.16s/it] 100%|██████████| 50/50 [00:58<00:00, 1.16s/it]
Prediction
chenxwh/onediffusion:f69674f4ID9hwjebdww5rma0cm315v59az70StatusSucceededSourceWebHardwareL40STotal durationCreatedInput
- task
- multiview
- width
- 1024
- height
- 1024
- prompt
- A cat with orange and white fur sits on a round wooden table. The cat has striking green eyes and a pink nose. Its ears are perked up, and its tail is curled around its body. The background is blurred, showing a white wall, a wooden chair, and a wooden table with a white pot and green plant. A white curtain is visible on the right side. The cat's gaze is directed slightly to the right, and its paws are white. The overall scene creates a cozy, domestic atmosphere with the cat as the central focus.
- azimuth
- 0,20,40,60
- distance
- 1.5,1.5,1.5,1.5
- elevation
- 0,0,0,0
- denoise_mask
- 0, 0, 1, 0, 1, 0, 1, 0
- focal_length
- 1.3887
- guidance_scale
- 4
- negative_prompt
- monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation
- num_inference_steps
- 50
- use_input_image_size
{ "task": "multiview", "width": 1024, "height": 1024, "image1": "https://replicate.delivery/pbxt/MEdVTm6cjWH1LxPCFbJjkvWUAhvRp8VNLPWgXFdIgb44jYW2/cat_on_table.webp", "prompt": "A cat with orange and white fur sits on a round wooden table. The cat has striking green eyes and a pink nose. Its ears are perked up, and its tail is curled around its body. The background is blurred, showing a white wall, a wooden chair, and a wooden table with a white pot and green plant. A white curtain is visible on the right side. The cat's gaze is directed slightly to the right, and its paws are white. The overall scene creates a cozy, domestic atmosphere with the cat as the central focus.", "azimuth": "0,20,40,60", "distance": "1.5,1.5,1.5,1.5", "elevation": "0,0,0,0", "denoise_mask": "0, 0, 1, 0, 1, 0, 1, 0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": false }
npm install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run chenxwh/onediffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "chenxwh/onediffusion:f69674f4fc4fb6f6b085b7cd6a00a4ee5d7014d8f5b2dea7bc551cc996129307", { input: { task: "multiview", width: 1024, height: 1024, image1: "https://replicate.delivery/pbxt/MEdVTm6cjWH1LxPCFbJjkvWUAhvRp8VNLPWgXFdIgb44jYW2/cat_on_table.webp", prompt: "A cat with orange and white fur sits on a round wooden table. The cat has striking green eyes and a pink nose. Its ears are perked up, and its tail is curled around its body. The background is blurred, showing a white wall, a wooden chair, and a wooden table with a white pot and green plant. A white curtain is visible on the right side. The cat's gaze is directed slightly to the right, and its paws are white. The overall scene creates a cozy, domestic atmosphere with the cat as the central focus.", azimuth: "0,20,40,60", distance: "1.5,1.5,1.5,1.5", elevation: "0,0,0,0", denoise_mask: "0, 0, 1, 0, 1, 0, 1, 0", focal_length: 1.3887, guidance_scale: 4, negative_prompt: "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", num_inference_steps: 50, use_input_image_size: false } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the clientimport replicate
Run chenxwh/onediffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "chenxwh/onediffusion:f69674f4fc4fb6f6b085b7cd6a00a4ee5d7014d8f5b2dea7bc551cc996129307", input={ "task": "multiview", "width": 1024, "height": 1024, "image1": "https://replicate.delivery/pbxt/MEdVTm6cjWH1LxPCFbJjkvWUAhvRp8VNLPWgXFdIgb44jYW2/cat_on_table.webp", "prompt": "A cat with orange and white fur sits on a round wooden table. The cat has striking green eyes and a pink nose. Its ears are perked up, and its tail is curled around its body. The background is blurred, showing a white wall, a wooden chair, and a wooden table with a white pot and green plant. A white curtain is visible on the right side. The cat's gaze is directed slightly to the right, and its paws are white. The overall scene creates a cozy, domestic atmosphere with the cat as the central focus.", "azimuth": "0,20,40,60", "distance": "1.5,1.5,1.5,1.5", "elevation": "0,0,0,0", "denoise_mask": "0, 0, 1, 0, 1, 0, 1, 0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": False } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run chenxwh/onediffusion 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": "f69674f4fc4fb6f6b085b7cd6a00a4ee5d7014d8f5b2dea7bc551cc996129307", "input": { "task": "multiview", "width": 1024, "height": 1024, "image1": "https://replicate.delivery/pbxt/MEdVTm6cjWH1LxPCFbJjkvWUAhvRp8VNLPWgXFdIgb44jYW2/cat_on_table.webp", "prompt": "A cat with orange and white fur sits on a round wooden table. The cat has striking green eyes and a pink nose. Its ears are perked up, and its tail is curled around its body. The background is blurred, showing a white wall, a wooden chair, and a wooden table with a white pot and green plant. A white curtain is visible on the right side. The cat\'s gaze is directed slightly to the right, and its paws are white. The overall scene creates a cozy, domestic atmosphere with the cat as the central focus.", "azimuth": "0,20,40,60", "distance": "1.5,1.5,1.5,1.5", "elevation": "0,0,0,0", "denoise_mask": "0, 0, 1, 0, 1, 0, 1, 0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": false } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-12-30T16:06:22.679306Z", "created_at": "2024-12-30T16:00:04.321000Z", "data_removed": false, "error": null, "id": "9hwjebdww5rma0cm315v59az70", "input": { "task": "multiview", "width": 1024, "height": 1024, "image1": "https://replicate.delivery/pbxt/MEdVTm6cjWH1LxPCFbJjkvWUAhvRp8VNLPWgXFdIgb44jYW2/cat_on_table.webp", "prompt": "A cat with orange and white fur sits on a round wooden table. The cat has striking green eyes and a pink nose. Its ears are perked up, and its tail is curled around its body. The background is blurred, showing a white wall, a wooden chair, and a wooden table with a white pot and green plant. A white curtain is visible on the right side. The cat's gaze is directed slightly to the right, and its paws are white. The overall scene creates a cozy, domestic atmosphere with the cat as the central focus.", "azimuth": "0,20,40,60", "distance": "1.5,1.5,1.5,1.5", "elevation": "0,0,0,0", "denoise_mask": "0, 0, 1, 0, 1, 0, 1, 0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": false }, "logs": "Using width, height: 1024, 1024\nUsing seed: 50778\nUsing prompt: [[multiview]] A cat with orange and white fur sits on a round wooden table. The cat has striking green eyes and a pink nose. Its ears are perked up, and its tail is curled around its body. The background is blurred, showing a white wall, a wooden chair, and a wooden table with a white pot and green plant. A white curtain is visible on the right side. The cat's gaze is directed slightly to the right, and its paws are white. The overall scene creates a cozy, domestic atmosphere with the cat as the central focus.\n/src/onediffusion/diffusion/pipelines/image_processor.py:572: FutureWarning: Passing `image` as torch tensor with value range in [-1,1] is deprecated. The expected value range for image tensor is [0,1] when passing as pytorch tensor or numpy Array. You passed `image` with value range [-1.0,1.0]\nwarnings.warn(\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:06<05:12, 6.38s/it]\n 4%|▍ | 2/50 [00:12<05:05, 6.37s/it]\n 6%|▌ | 3/50 [00:19<05:00, 6.38s/it]\n 8%|▊ | 4/50 [00:25<04:54, 6.41s/it]\n 10%|█ | 5/50 [00:32<04:49, 6.43s/it]\n 12%|█▏ | 6/50 [00:38<04:43, 6.44s/it]\n 14%|█▍ | 7/50 [00:44<04:37, 6.45s/it]\n 16%|█▌ | 8/50 [00:51<04:31, 6.47s/it]\n 18%|█▊ | 9/50 [00:58<04:25, 6.49s/it]\n 20%|██ | 10/50 [01:04<04:19, 6.49s/it]\n 22%|██▏ | 11/50 [01:11<04:13, 6.49s/it]\n 24%|██▍ | 12/50 [01:17<04:06, 6.50s/it]\n 26%|██▌ | 13/50 [01:24<04:00, 6.50s/it]\n 28%|██▊ | 14/50 [01:30<03:54, 6.51s/it]\n 30%|███ | 15/50 [01:37<03:48, 6.52s/it]\n 32%|███▏ | 16/50 [01:43<03:41, 6.53s/it]\n 34%|███▍ | 17/50 [01:50<03:35, 6.53s/it]\n 36%|███▌ | 18/50 [01:56<03:29, 6.54s/it]\n 38%|███▊ | 19/50 [02:03<03:22, 6.55s/it]\n 40%|████ | 20/50 [02:09<03:16, 6.55s/it]\n 42%|████▏ | 21/50 [02:16<03:09, 6.55s/it]\n 44%|████▍ | 22/50 [02:22<03:03, 6.55s/it]\n 46%|████▌ | 23/50 [02:29<02:57, 6.56s/it]\n 48%|████▊ | 24/50 [02:36<02:50, 6.56s/it]\n 50%|█████ | 25/50 [02:42<02:43, 6.55s/it]\n 52%|█████▏ | 26/50 [02:49<02:37, 6.55s/it]\n 54%|█████▍ | 27/50 [02:55<02:30, 6.55s/it]\n 56%|█████▌ | 28/50 [03:02<02:24, 6.55s/it]\n 58%|█████▊ | 29/50 [03:08<02:17, 6.56s/it]\n 60%|██████ | 30/50 [03:15<02:11, 6.56s/it]\n 62%|██████▏ | 31/50 [03:22<02:04, 6.57s/it]\n 64%|██████▍ | 32/50 [03:28<01:58, 6.57s/it]\n 66%|██████▌ | 33/50 [03:35<01:51, 6.57s/it]\n 68%|██████▊ | 34/50 [03:41<01:45, 6.57s/it]\n 70%|███████ | 35/50 [03:48<01:38, 6.57s/it]\n 72%|███████▏ | 36/50 [03:54<01:31, 6.57s/it]\n 74%|███████▍ | 37/50 [04:01<01:25, 6.57s/it]\n 76%|███████▌ | 38/50 [04:08<01:18, 6.57s/it]\n 78%|███████▊ | 39/50 [04:14<01:12, 6.57s/it]\n 80%|████████ | 40/50 [04:21<01:05, 6.58s/it]\n 82%|████████▏ | 41/50 [04:27<00:59, 6.57s/it]\n 84%|████████▍ | 42/50 [04:34<00:52, 6.57s/it]\n 86%|████████▌ | 43/50 [04:40<00:46, 6.58s/it]\n 88%|████████▊ | 44/50 [04:47<00:39, 6.58s/it]\n 90%|█████████ | 45/50 [04:54<00:32, 6.58s/it]\n 92%|█████████▏| 46/50 [05:00<00:26, 6.58s/it]\n 94%|█████████▍| 47/50 [05:07<00:19, 6.58s/it]\n 96%|█████████▌| 48/50 [05:13<00:13, 6.58s/it]\n 98%|█████████▊| 49/50 [05:20<00:06, 6.58s/it]\n100%|██████████| 50/50 [05:27<00:00, 6.59s/it]\n100%|██████████| 50/50 [05:27<00:00, 6.54s/it]", "metrics": { "predict_time": 329.084405959, "total_time": 378.358306 }, "output": [ "https://replicate.delivery/xezq/gFVa0GN8OS4dARVkHf3uTBjmUjVA9Ybb33xLGylyfe183OAoA/out_0.png", "https://replicate.delivery/xezq/fEqyrSJefuP5NI35m2yWING2ai2NIbqVDfbl7lfZoufjftDAKA/out_1.png" ], "started_at": "2024-12-30T16:00:53.594900Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bcwr-gekbwiobnchom7yhg2hxihqwvzynpz6epv2wbeb5atbrqljwtluq", "get": "https://api.replicate.com/v1/predictions/9hwjebdww5rma0cm315v59az70", "cancel": "https://api.replicate.com/v1/predictions/9hwjebdww5rma0cm315v59az70/cancel" }, "version": "de9c4daae9e4792c9525e3fe6e605090bdaba107b0336eb873cc97336ec1a126" }
Generated inUsing width, height: 1024, 1024 Using seed: 50778 Using prompt: [[multiview]] A cat with orange and white fur sits on a round wooden table. The cat has striking green eyes and a pink nose. Its ears are perked up, and its tail is curled around its body. The background is blurred, showing a white wall, a wooden chair, and a wooden table with a white pot and green plant. A white curtain is visible on the right side. The cat's gaze is directed slightly to the right, and its paws are white. The overall scene creates a cozy, domestic atmosphere with the cat as the central focus. /src/onediffusion/diffusion/pipelines/image_processor.py:572: FutureWarning: Passing `image` as torch tensor with value range in [-1,1] is deprecated. The expected value range for image tensor is [0,1] when passing as pytorch tensor or numpy Array. You passed `image` with value range [-1.0,1.0] warnings.warn( 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:06<05:12, 6.38s/it] 4%|▍ | 2/50 [00:12<05:05, 6.37s/it] 6%|▌ | 3/50 [00:19<05:00, 6.38s/it] 8%|▊ | 4/50 [00:25<04:54, 6.41s/it] 10%|█ | 5/50 [00:32<04:49, 6.43s/it] 12%|█▏ | 6/50 [00:38<04:43, 6.44s/it] 14%|█▍ | 7/50 [00:44<04:37, 6.45s/it] 16%|█▌ | 8/50 [00:51<04:31, 6.47s/it] 18%|█▊ | 9/50 [00:58<04:25, 6.49s/it] 20%|██ | 10/50 [01:04<04:19, 6.49s/it] 22%|██▏ | 11/50 [01:11<04:13, 6.49s/it] 24%|██▍ | 12/50 [01:17<04:06, 6.50s/it] 26%|██▌ | 13/50 [01:24<04:00, 6.50s/it] 28%|██▊ | 14/50 [01:30<03:54, 6.51s/it] 30%|███ | 15/50 [01:37<03:48, 6.52s/it] 32%|███▏ | 16/50 [01:43<03:41, 6.53s/it] 34%|███▍ | 17/50 [01:50<03:35, 6.53s/it] 36%|███▌ | 18/50 [01:56<03:29, 6.54s/it] 38%|███▊ | 19/50 [02:03<03:22, 6.55s/it] 40%|████ | 20/50 [02:09<03:16, 6.55s/it] 42%|████▏ | 21/50 [02:16<03:09, 6.55s/it] 44%|████▍ | 22/50 [02:22<03:03, 6.55s/it] 46%|████▌ | 23/50 [02:29<02:57, 6.56s/it] 48%|████▊ | 24/50 [02:36<02:50, 6.56s/it] 50%|█████ | 25/50 [02:42<02:43, 6.55s/it] 52%|█████▏ | 26/50 [02:49<02:37, 6.55s/it] 54%|█████▍ | 27/50 [02:55<02:30, 6.55s/it] 56%|█████▌ | 28/50 [03:02<02:24, 6.55s/it] 58%|█████▊ | 29/50 [03:08<02:17, 6.56s/it] 60%|██████ | 30/50 [03:15<02:11, 6.56s/it] 62%|██████▏ | 31/50 [03:22<02:04, 6.57s/it] 64%|██████▍ | 32/50 [03:28<01:58, 6.57s/it] 66%|██████▌ | 33/50 [03:35<01:51, 6.57s/it] 68%|██████▊ | 34/50 [03:41<01:45, 6.57s/it] 70%|███████ | 35/50 [03:48<01:38, 6.57s/it] 72%|███████▏ | 36/50 [03:54<01:31, 6.57s/it] 74%|███████▍ | 37/50 [04:01<01:25, 6.57s/it] 76%|███████▌ | 38/50 [04:08<01:18, 6.57s/it] 78%|███████▊ | 39/50 [04:14<01:12, 6.57s/it] 80%|████████ | 40/50 [04:21<01:05, 6.58s/it] 82%|████████▏ | 41/50 [04:27<00:59, 6.57s/it] 84%|████████▍ | 42/50 [04:34<00:52, 6.57s/it] 86%|████████▌ | 43/50 [04:40<00:46, 6.58s/it] 88%|████████▊ | 44/50 [04:47<00:39, 6.58s/it] 90%|█████████ | 45/50 [04:54<00:32, 6.58s/it] 92%|█████████▏| 46/50 [05:00<00:26, 6.58s/it] 94%|█████████▍| 47/50 [05:07<00:19, 6.58s/it] 96%|█████████▌| 48/50 [05:13<00:13, 6.58s/it] 98%|█████████▊| 49/50 [05:20<00:06, 6.58s/it] 100%|██████████| 50/50 [05:27<00:00, 6.59s/it] 100%|██████████| 50/50 [05:27<00:00, 6.54s/it]
Prediction
chenxwh/onediffusion:f69674f4ID0dkwed1sqxrma0cm31avs75f8wStatusSucceededSourceWebHardwareL40STotal durationCreatedInput
- task
- text2image
- width
- 1024
- height
- 1024
- prompt
- A bipedal black cat wearing a huge oversized witch hat, a wizards robe, casting a spell, in an enchanted forest. The scene is filled with fireflies and moss on surrounding rocks and trees
- azimuth
- 0
- distance
- 1.5
- elevation
- 0
- denoise_mask
- 0
- focal_length
- 1.3887
- guidance_scale
- 4
- negative_prompt
- monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation
- num_inference_steps
- 50
- use_input_image_size
{ "task": "text2image", "width": 1024, "height": 1024, "prompt": "A bipedal black cat wearing a huge oversized witch hat, a wizards robe, casting a spell, in an enchanted forest. The scene is filled with fireflies and moss on surrounding rocks and trees", "azimuth": "0", "distance": "1.5", "elevation": "0", "denoise_mask": "0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": false }
npm install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run chenxwh/onediffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "chenxwh/onediffusion:f69674f4fc4fb6f6b085b7cd6a00a4ee5d7014d8f5b2dea7bc551cc996129307", { input: { task: "text2image", width: 1024, height: 1024, prompt: "A bipedal black cat wearing a huge oversized witch hat, a wizards robe, casting a spell, in an enchanted forest. The scene is filled with fireflies and moss on surrounding rocks and trees", azimuth: "0", distance: "1.5", elevation: "0", denoise_mask: "0", focal_length: 1.3887, guidance_scale: 4, negative_prompt: "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", num_inference_steps: 50, use_input_image_size: false } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the clientimport replicate
Run chenxwh/onediffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "chenxwh/onediffusion:f69674f4fc4fb6f6b085b7cd6a00a4ee5d7014d8f5b2dea7bc551cc996129307", input={ "task": "text2image", "width": 1024, "height": 1024, "prompt": "A bipedal black cat wearing a huge oversized witch hat, a wizards robe, casting a spell, in an enchanted forest. The scene is filled with fireflies and moss on surrounding rocks and trees", "azimuth": "0", "distance": "1.5", "elevation": "0", "denoise_mask": "0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": False } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run chenxwh/onediffusion 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": "f69674f4fc4fb6f6b085b7cd6a00a4ee5d7014d8f5b2dea7bc551cc996129307", "input": { "task": "text2image", "width": 1024, "height": 1024, "prompt": "A bipedal black cat wearing a huge oversized witch hat, a wizards robe, casting a spell, in an enchanted forest. The scene is filled with fireflies and moss on surrounding rocks and trees", "azimuth": "0", "distance": "1.5", "elevation": "0", "denoise_mask": "0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": false } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-12-30T16:11:40.677040Z", "created_at": "2024-12-30T16:10:26.111000Z", "data_removed": false, "error": null, "id": "0dkwed1sqxrma0cm31avs75f8w", "input": { "task": "text2image", "width": 1024, "height": 1024, "prompt": "A bipedal black cat wearing a huge oversized witch hat, a wizards robe, casting a spell, in an enchanted forest. The scene is filled with fireflies and moss on surrounding rocks and trees", "azimuth": "0", "distance": "1.5", "elevation": "0", "denoise_mask": "0", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": false }, "logs": "Using width, height: 1024, 1024\nUsing seed: 8078\nUsing prompt: [[text2image]] A bipedal black cat wearing a huge oversized witch hat, a wizards robe, casting a spell, in an enchanted forest. The scene is filled with fireflies and moss on surrounding rocks and trees\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:27, 1.80it/s]\n 4%|▍ | 2/50 [00:01<00:24, 1.98it/s]\n 6%|▌ | 3/50 [00:01<00:23, 2.00it/s]\n 8%|▊ | 4/50 [00:02<00:22, 2.01it/s]\n 10%|█ | 5/50 [00:02<00:22, 2.02it/s]\n 12%|█▏ | 6/50 [00:03<00:21, 2.01it/s]\n 14%|█▍ | 7/50 [00:03<00:21, 2.02it/s]\n 16%|█▌ | 8/50 [00:03<00:20, 2.02it/s]\n 18%|█▊ | 9/50 [00:04<00:20, 2.02it/s]\n 20%|██ | 10/50 [00:04<00:19, 2.02it/s]\n 22%|██▏ | 11/50 [00:05<00:19, 2.02it/s]\n 24%|██▍ | 12/50 [00:05<00:18, 2.02it/s]\n 26%|██▌ | 13/50 [00:06<00:18, 2.02it/s]\n 28%|██▊ | 14/50 [00:06<00:17, 2.02it/s]\n 30%|███ | 15/50 [00:07<00:17, 2.02it/s]\n 32%|███▏ | 16/50 [00:07<00:16, 2.02it/s]\n 34%|███▍ | 17/50 [00:08<00:16, 2.02it/s]\n 36%|███▌ | 18/50 [00:08<00:15, 2.02it/s]\n 38%|███▊ | 19/50 [00:09<00:15, 2.01it/s]\n 40%|████ | 20/50 [00:09<00:14, 2.01it/s]\n 42%|████▏ | 21/50 [00:10<00:14, 2.01it/s]\n 44%|████▍ | 22/50 [00:10<00:13, 2.01it/s]\n 46%|████▌ | 23/50 [00:11<00:13, 2.01it/s]\n 48%|████▊ | 24/50 [00:11<00:12, 2.01it/s]\n 50%|█████ | 25/50 [00:12<00:12, 2.00it/s]\n 52%|█████▏ | 26/50 [00:12<00:11, 2.01it/s]\n 54%|█████▍ | 27/50 [00:13<00:11, 2.01it/s]\n 56%|█████▌ | 28/50 [00:13<00:10, 2.01it/s]\n 58%|█████▊ | 29/50 [00:14<00:10, 2.01it/s]\n 60%|██████ | 30/50 [00:14<00:09, 2.01it/s]\n 62%|██████▏ | 31/50 [00:15<00:09, 2.01it/s]\n 64%|██████▍ | 32/50 [00:15<00:08, 2.01it/s]\n 66%|██████▌ | 33/50 [00:16<00:08, 2.01it/s]\n 68%|██████▊ | 34/50 [00:16<00:07, 2.01it/s]\n 70%|███████ | 35/50 [00:17<00:07, 2.01it/s]\n 72%|███████▏ | 36/50 [00:17<00:06, 2.01it/s]\n 74%|███████▍ | 37/50 [00:18<00:06, 2.00it/s]\n 76%|███████▌ | 38/50 [00:18<00:05, 2.01it/s]\n 78%|███████▊ | 39/50 [00:19<00:05, 2.00it/s]\n 80%|████████ | 40/50 [00:19<00:04, 2.00it/s]\n 82%|████████▏ | 41/50 [00:20<00:04, 2.00it/s]\n 84%|████████▍ | 42/50 [00:20<00:03, 2.00it/s]\n 86%|████████▌ | 43/50 [00:21<00:03, 2.00it/s]\n 88%|████████▊ | 44/50 [00:21<00:03, 2.00it/s]\n 90%|█████████ | 45/50 [00:22<00:02, 2.00it/s]\n 92%|█████████▏| 46/50 [00:22<00:02, 2.00it/s]\n 94%|█████████▍| 47/50 [00:23<00:01, 2.00it/s]\n 96%|█████████▌| 48/50 [00:23<00:01, 2.00it/s]\n 98%|█████████▊| 49/50 [00:24<00:00, 2.00it/s]\n100%|██████████| 50/50 [00:24<00:00, 2.00it/s]\n100%|██████████| 50/50 [00:24<00:00, 2.01it/s]", "metrics": { "predict_time": 25.692293366, "total_time": 74.56604 }, "output": [ "https://replicate.delivery/xezq/C6Xi9GGuBs6fe0hzPFeH1sac4qBwRaB8xGWEN7ATIlk5BPAoA/out_0.png" ], "started_at": "2024-12-30T16:11:14.984747Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bcwr-ldvwijexjqt5srr4c2ok2uex2jd54ix274n2cbx2usf4hfp3bloa", "get": "https://api.replicate.com/v1/predictions/0dkwed1sqxrma0cm31avs75f8w", "cancel": "https://api.replicate.com/v1/predictions/0dkwed1sqxrma0cm31avs75f8w/cancel" }, "version": "f69674f4fc4fb6f6b085b7cd6a00a4ee5d7014d8f5b2dea7bc551cc996129307" }
Generated inUsing width, height: 1024, 1024 Using seed: 8078 Using prompt: [[text2image]] A bipedal black cat wearing a huge oversized witch hat, a wizards robe, casting a spell, in an enchanted forest. The scene is filled with fireflies and moss on surrounding rocks and trees 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:27, 1.80it/s] 4%|▍ | 2/50 [00:01<00:24, 1.98it/s] 6%|▌ | 3/50 [00:01<00:23, 2.00it/s] 8%|▊ | 4/50 [00:02<00:22, 2.01it/s] 10%|█ | 5/50 [00:02<00:22, 2.02it/s] 12%|█▏ | 6/50 [00:03<00:21, 2.01it/s] 14%|█▍ | 7/50 [00:03<00:21, 2.02it/s] 16%|█▌ | 8/50 [00:03<00:20, 2.02it/s] 18%|█▊ | 9/50 [00:04<00:20, 2.02it/s] 20%|██ | 10/50 [00:04<00:19, 2.02it/s] 22%|██▏ | 11/50 [00:05<00:19, 2.02it/s] 24%|██▍ | 12/50 [00:05<00:18, 2.02it/s] 26%|██▌ | 13/50 [00:06<00:18, 2.02it/s] 28%|██▊ | 14/50 [00:06<00:17, 2.02it/s] 30%|███ | 15/50 [00:07<00:17, 2.02it/s] 32%|███▏ | 16/50 [00:07<00:16, 2.02it/s] 34%|███▍ | 17/50 [00:08<00:16, 2.02it/s] 36%|███▌ | 18/50 [00:08<00:15, 2.02it/s] 38%|███▊ | 19/50 [00:09<00:15, 2.01it/s] 40%|████ | 20/50 [00:09<00:14, 2.01it/s] 42%|████▏ | 21/50 [00:10<00:14, 2.01it/s] 44%|████▍ | 22/50 [00:10<00:13, 2.01it/s] 46%|████▌ | 23/50 [00:11<00:13, 2.01it/s] 48%|████▊ | 24/50 [00:11<00:12, 2.01it/s] 50%|█████ | 25/50 [00:12<00:12, 2.00it/s] 52%|█████▏ | 26/50 [00:12<00:11, 2.01it/s] 54%|█████▍ | 27/50 [00:13<00:11, 2.01it/s] 56%|█████▌ | 28/50 [00:13<00:10, 2.01it/s] 58%|█████▊ | 29/50 [00:14<00:10, 2.01it/s] 60%|██████ | 30/50 [00:14<00:09, 2.01it/s] 62%|██████▏ | 31/50 [00:15<00:09, 2.01it/s] 64%|██████▍ | 32/50 [00:15<00:08, 2.01it/s] 66%|██████▌ | 33/50 [00:16<00:08, 2.01it/s] 68%|██████▊ | 34/50 [00:16<00:07, 2.01it/s] 70%|███████ | 35/50 [00:17<00:07, 2.01it/s] 72%|███████▏ | 36/50 [00:17<00:06, 2.01it/s] 74%|███████▍ | 37/50 [00:18<00:06, 2.00it/s] 76%|███████▌ | 38/50 [00:18<00:05, 2.01it/s] 78%|███████▊ | 39/50 [00:19<00:05, 2.00it/s] 80%|████████ | 40/50 [00:19<00:04, 2.00it/s] 82%|████████▏ | 41/50 [00:20<00:04, 2.00it/s] 84%|████████▍ | 42/50 [00:20<00:03, 2.00it/s] 86%|████████▌ | 43/50 [00:21<00:03, 2.00it/s] 88%|████████▊ | 44/50 [00:21<00:03, 2.00it/s] 90%|█████████ | 45/50 [00:22<00:02, 2.00it/s] 92%|█████████▏| 46/50 [00:22<00:02, 2.00it/s] 94%|█████████▍| 47/50 [00:23<00:01, 2.00it/s] 96%|█████████▌| 48/50 [00:23<00:01, 2.00it/s] 98%|█████████▊| 49/50 [00:24<00:00, 2.00it/s] 100%|██████████| 50/50 [00:24<00:00, 2.00it/s] 100%|██████████| 50/50 [00:24<00:00, 2.01it/s]
Prediction
chenxwh/onediffusion:f69674f4IDxkn4g12a7srmc0cm31yr5afxmgStatusSucceededSourceWebHardwareL40STotal durationCreatedInput
- task
- canny2image
- width
- 1024
- height
- 1024
- prompt
- A woman in a flowing green dress with intricate silver floral patterns stands in a traditional Asian-style building. She has long dark hair styled in a bun and wears a silver choker and matching earrings. Behind her, a large blue dragon with white scales wraps around the wooden beams of the structure. Two birds, one golden and one white, are in flight near her shoulders. The building features wooden beams, paper windows, and a tiled roof with hanging lanterns. The composition emphasizes clear outlines of the woman, dragon, and birds, set against the structured lines of the building for a harmonious yet fantastical scene
- azimuth
- 0
- distance
- 1.5
- elevation
- 0
- denoise_mask
- 1
- focal_length
- 1.3887
- guidance_scale
- 4
- negative_prompt
- monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation
- num_inference_steps
- 50
- use_input_image_size
{ "task": "canny2image", "width": 1024, "height": 1024, "image1": "https://replicate.delivery/pbxt/MEeKm4pLfzaOT7F4pbcutGhO33ldpRq1QYJUztOiUrWqN0u1/canny.webp", "prompt": "A woman in a flowing green dress with intricate silver floral patterns stands in a traditional Asian-style building. She has long dark hair styled in a bun and wears a silver choker and matching earrings. Behind her, a large blue dragon with white scales wraps around the wooden beams of the structure. Two birds, one golden and one white, are in flight near her shoulders. The building features wooden beams, paper windows, and a tiled roof with hanging lanterns. The composition emphasizes clear outlines of the woman, dragon, and birds, set against the structured lines of the building for a harmonious yet fantastical scene", "azimuth": "0", "distance": "1.5", "elevation": "0", "denoise_mask": "1", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": true }
npm install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run chenxwh/onediffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "chenxwh/onediffusion:f69674f4fc4fb6f6b085b7cd6a00a4ee5d7014d8f5b2dea7bc551cc996129307", { input: { task: "canny2image", width: 1024, height: 1024, image1: "https://replicate.delivery/pbxt/MEeKm4pLfzaOT7F4pbcutGhO33ldpRq1QYJUztOiUrWqN0u1/canny.webp", prompt: "A woman in a flowing green dress with intricate silver floral patterns stands in a traditional Asian-style building. She has long dark hair styled in a bun and wears a silver choker and matching earrings. Behind her, a large blue dragon with white scales wraps around the wooden beams of the structure. Two birds, one golden and one white, are in flight near her shoulders. The building features wooden beams, paper windows, and a tiled roof with hanging lanterns. The composition emphasizes clear outlines of the woman, dragon, and birds, set against the structured lines of the building for a harmonious yet fantastical scene", azimuth: "0", distance: "1.5", elevation: "0", denoise_mask: "1", focal_length: 1.3887, guidance_scale: 4, negative_prompt: "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", num_inference_steps: 50, use_input_image_size: true } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the clientimport replicate
Run chenxwh/onediffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "chenxwh/onediffusion:f69674f4fc4fb6f6b085b7cd6a00a4ee5d7014d8f5b2dea7bc551cc996129307", input={ "task": "canny2image", "width": 1024, "height": 1024, "image1": "https://replicate.delivery/pbxt/MEeKm4pLfzaOT7F4pbcutGhO33ldpRq1QYJUztOiUrWqN0u1/canny.webp", "prompt": "A woman in a flowing green dress with intricate silver floral patterns stands in a traditional Asian-style building. She has long dark hair styled in a bun and wears a silver choker and matching earrings. Behind her, a large blue dragon with white scales wraps around the wooden beams of the structure. Two birds, one golden and one white, are in flight near her shoulders. The building features wooden beams, paper windows, and a tiled roof with hanging lanterns. The composition emphasizes clear outlines of the woman, dragon, and birds, set against the structured lines of the building for a harmonious yet fantastical scene", "azimuth": "0", "distance": "1.5", "elevation": "0", "denoise_mask": "1", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": True } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run chenxwh/onediffusion 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": "f69674f4fc4fb6f6b085b7cd6a00a4ee5d7014d8f5b2dea7bc551cc996129307", "input": { "task": "canny2image", "width": 1024, "height": 1024, "image1": "https://replicate.delivery/pbxt/MEeKm4pLfzaOT7F4pbcutGhO33ldpRq1QYJUztOiUrWqN0u1/canny.webp", "prompt": "A woman in a flowing green dress with intricate silver floral patterns stands in a traditional Asian-style building. She has long dark hair styled in a bun and wears a silver choker and matching earrings. Behind her, a large blue dragon with white scales wraps around the wooden beams of the structure. Two birds, one golden and one white, are in flight near her shoulders. The building features wooden beams, paper windows, and a tiled roof with hanging lanterns. The composition emphasizes clear outlines of the woman, dragon, and birds, set against the structured lines of the building for a harmonious yet fantastical scene", "azimuth": "0", "distance": "1.5", "elevation": "0", "denoise_mask": "1", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": true } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-12-30T16:55:40.937411Z", "created_at": "2024-12-30T16:54:11.774000Z", "data_removed": false, "error": null, "id": "xkn4g12a7srmc0cm31yr5afxmg", "input": { "task": "canny2image", "width": 1024, "height": 1024, "image1": "https://replicate.delivery/pbxt/MEeKm4pLfzaOT7F4pbcutGhO33ldpRq1QYJUztOiUrWqN0u1/canny.webp", "prompt": "A woman in a flowing green dress with intricate silver floral patterns stands in a traditional Asian-style building. She has long dark hair styled in a bun and wears a silver choker and matching earrings. Behind her, a large blue dragon with white scales wraps around the wooden beams of the structure. Two birds, one golden and one white, are in flight near her shoulders. The building features wooden beams, paper windows, and a tiled roof with hanging lanterns. The composition emphasizes clear outlines of the woman, dragon, and birds, set against the structured lines of the building for a harmonious yet fantastical scene", "azimuth": "0", "distance": "1.5", "elevation": "0", "denoise_mask": "1", "focal_length": 1.3887, "guidance_scale": 4, "negative_prompt": "monochrome, greyscale, low-res, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", "num_inference_steps": 50, "use_input_image_size": true }, "logs": "Using width, height: 384, 672\nUsing seed: 52919\nUsing prompt: [[canny2image]] A woman in a flowing green dress with intricate silver floral patterns stands in a traditional Asian-style building. She has long dark hair styled in a bun and wears a silver choker and matching earrings. Behind her, a large blue dragon with white scales wraps around the wooden beams of the structure. Two birds, one golden and one white, are in flight near her shoulders. The building features wooden beams, paper windows, and a tiled roof with hanging lanterns. The composition emphasizes clear outlines of the woman, dragon, and birds, set against the structured lines of the building for a harmonious yet fantastical scene\n/src/onediffusion/diffusion/pipelines/image_processor.py:572: FutureWarning: Passing `image` as torch tensor with value range in [-1,1] is deprecated. The expected value range for image tensor is [0,1] when passing as pytorch tensor or numpy Array. You passed `image` with value range [-1.0,1.0]\nwarnings.warn(\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:05, 9.28it/s]\n 6%|▌ | 3/50 [00:00<00:04, 10.50it/s]\n 10%|█ | 5/50 [00:00<00:04, 10.61it/s]\n 14%|█▍ | 7/50 [00:00<00:04, 10.68it/s]\n 18%|█▊ | 9/50 [00:00<00:03, 10.68it/s]\n 22%|██▏ | 11/50 [00:01<00:03, 10.70it/s]\n 26%|██▌ | 13/50 [00:01<00:03, 10.71it/s]\n 30%|███ | 15/50 [00:01<00:03, 10.71it/s]\n 34%|███▍ | 17/50 [00:01<00:03, 10.70it/s]\n 38%|███▊ | 19/50 [00:01<00:02, 10.70it/s]\n 42%|████▏ | 21/50 [00:01<00:02, 10.70it/s]\n 46%|████▌ | 23/50 [00:02<00:02, 10.71it/s]\n 50%|█████ | 25/50 [00:02<00:02, 10.73it/s]\n 54%|█████▍ | 27/50 [00:02<00:02, 10.72it/s]\n 58%|█████▊ | 29/50 [00:02<00:01, 10.75it/s]\n 62%|██████▏ | 31/50 [00:02<00:01, 10.73it/s]\n 66%|██████▌ | 33/50 [00:03<00:01, 10.75it/s]\n 70%|███████ | 35/50 [00:03<00:01, 10.76it/s]\n 74%|███████▍ | 37/50 [00:03<00:01, 10.74it/s]\n 78%|███████▊ | 39/50 [00:03<00:01, 10.73it/s]\n 82%|████████▏ | 41/50 [00:03<00:00, 10.73it/s]\n 86%|████████▌ | 43/50 [00:04<00:00, 10.65it/s]\n 90%|█████████ | 45/50 [00:04<00:00, 10.67it/s]\n 94%|█████████▍| 47/50 [00:04<00:00, 10.69it/s]\n 98%|█████████▊| 49/50 [00:04<00:00, 10.71it/s]\n100%|██████████| 50/50 [00:04<00:00, 10.69it/s]", "metrics": { "predict_time": 5.222425443, "total_time": 89.163411 }, "output": [ "https://replicate.delivery/xezq/OMUoFgf9c62cFqZYa5aOnoHYXQSM4NZtcYNs4IMcSOaGFEAKA/out_0.png" ], "started_at": "2024-12-30T16:55:35.714986Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bcwr-z7ixeqsc3e22wyb46wgtufmcvfeot4jr65fj4hgwmjovhvjqf6ja", "get": "https://api.replicate.com/v1/predictions/xkn4g12a7srmc0cm31yr5afxmg", "cancel": "https://api.replicate.com/v1/predictions/xkn4g12a7srmc0cm31yr5afxmg/cancel" }, "version": "f69674f4fc4fb6f6b085b7cd6a00a4ee5d7014d8f5b2dea7bc551cc996129307" }
Generated inUsing width, height: 384, 672 Using seed: 52919 Using prompt: [[canny2image]] A woman in a flowing green dress with intricate silver floral patterns stands in a traditional Asian-style building. She has long dark hair styled in a bun and wears a silver choker and matching earrings. Behind her, a large blue dragon with white scales wraps around the wooden beams of the structure. Two birds, one golden and one white, are in flight near her shoulders. The building features wooden beams, paper windows, and a tiled roof with hanging lanterns. The composition emphasizes clear outlines of the woman, dragon, and birds, set against the structured lines of the building for a harmonious yet fantastical scene /src/onediffusion/diffusion/pipelines/image_processor.py:572: FutureWarning: Passing `image` as torch tensor with value range in [-1,1] is deprecated. The expected value range for image tensor is [0,1] when passing as pytorch tensor or numpy Array. You passed `image` with value range [-1.0,1.0] warnings.warn( 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:05, 9.28it/s] 6%|▌ | 3/50 [00:00<00:04, 10.50it/s] 10%|█ | 5/50 [00:00<00:04, 10.61it/s] 14%|█▍ | 7/50 [00:00<00:04, 10.68it/s] 18%|█▊ | 9/50 [00:00<00:03, 10.68it/s] 22%|██▏ | 11/50 [00:01<00:03, 10.70it/s] 26%|██▌ | 13/50 [00:01<00:03, 10.71it/s] 30%|███ | 15/50 [00:01<00:03, 10.71it/s] 34%|███▍ | 17/50 [00:01<00:03, 10.70it/s] 38%|███▊ | 19/50 [00:01<00:02, 10.70it/s] 42%|████▏ | 21/50 [00:01<00:02, 10.70it/s] 46%|████▌ | 23/50 [00:02<00:02, 10.71it/s] 50%|█████ | 25/50 [00:02<00:02, 10.73it/s] 54%|█████▍ | 27/50 [00:02<00:02, 10.72it/s] 58%|█████▊ | 29/50 [00:02<00:01, 10.75it/s] 62%|██████▏ | 31/50 [00:02<00:01, 10.73it/s] 66%|██████▌ | 33/50 [00:03<00:01, 10.75it/s] 70%|███████ | 35/50 [00:03<00:01, 10.76it/s] 74%|███████▍ | 37/50 [00:03<00:01, 10.74it/s] 78%|███████▊ | 39/50 [00:03<00:01, 10.73it/s] 82%|████████▏ | 41/50 [00:03<00:00, 10.73it/s] 86%|████████▌ | 43/50 [00:04<00:00, 10.65it/s] 90%|█████████ | 45/50 [00:04<00:00, 10.67it/s] 94%|█████████▍| 47/50 [00:04<00:00, 10.69it/s] 98%|█████████▊| 49/50 [00:04<00:00, 10.71it/s] 100%|██████████| 50/50 [00:04<00:00, 10.69it/s]
Want to make some of these yourself?
Run this model