DiffusionLight: Light Probes by Painting a Chrome Ball
Prediction
lucataco/diffusionlight:958d6f0315da9b86f74ca6a67b8cafa1b44b4b6330f0385d956da171ec02e5efIDdc4dqllbowaiqmef53cpihtj5mStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- prompt
- a perfect mirrored reflective chrome ball sphere
- negative_prompt
- matte, diffuse, flat, dull
- num_inference_steps
- 30
- controlnet_conditioning_scale
- 0.5
{ "image": "https://replicate.delivery/pbxt/KJoE5o7FxdBpbyaooud9PQWSmzB44JjprzEQ32hiUaZN32Sr/bed.png", "prompt": "a perfect mirrored reflective chrome ball sphere", "negative_prompt": "matte, diffuse, flat, dull", "num_inference_steps": 30, "controlnet_conditioning_scale": 0.5 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run lucataco/diffusionlight using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/diffusionlight:958d6f0315da9b86f74ca6a67b8cafa1b44b4b6330f0385d956da171ec02e5ef", { input: { image: "https://replicate.delivery/pbxt/KJoE5o7FxdBpbyaooud9PQWSmzB44JjprzEQ32hiUaZN32Sr/bed.png", prompt: "a perfect mirrored reflective chrome ball sphere", negative_prompt: "matte, diffuse, flat, dull", num_inference_steps: 30, controlnet_conditioning_scale: 0.5 } } ); // To access the file URL: console.log(output.url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Import the client:import replicate
Run lucataco/diffusionlight using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/diffusionlight:958d6f0315da9b86f74ca6a67b8cafa1b44b4b6330f0385d956da171ec02e5ef", input={ "image": "https://replicate.delivery/pbxt/KJoE5o7FxdBpbyaooud9PQWSmzB44JjprzEQ32hiUaZN32Sr/bed.png", "prompt": "a perfect mirrored reflective chrome ball sphere", "negative_prompt": "matte, diffuse, flat, dull", "num_inference_steps": 30, "controlnet_conditioning_scale": 0.5 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run lucataco/diffusionlight using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "lucataco/diffusionlight:958d6f0315da9b86f74ca6a67b8cafa1b44b4b6330f0385d956da171ec02e5ef", "input": { "image": "https://replicate.delivery/pbxt/KJoE5o7FxdBpbyaooud9PQWSmzB44JjprzEQ32hiUaZN32Sr/bed.png", "prompt": "a perfect mirrored reflective chrome ball sphere", "negative_prompt": "matte, diffuse, flat, dull", "num_inference_steps": 30, "controlnet_conditioning_scale": 0.5 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-01-30T21:42:37.656926Z", "created_at": "2024-01-30T21:37:50.625579Z", "data_removed": false, "error": null, "id": "dc4dqllbowaiqmef53cpihtj5m", "input": { "image": "https://replicate.delivery/pbxt/KJoE5o7FxdBpbyaooud9PQWSmzB44JjprzEQ32hiUaZN32Sr/bed.png", "prompt": "a perfect mirrored reflective chrome ball sphere", "negative_prompt": "matte, diffuse, flat, dull", "num_inference_steps": 30, "controlnet_conditioning_scale": 0.5 }, "logs": "/root/.pyenv/versions/3.10.13/lib/python3.10/site-packages/torch/functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:3483.)\nreturn _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]\n 0%| | 0/29 [00:00<?, ?it/s]\n 3%|▎ | 1/29 [00:00<00:09, 2.81it/s]\n 7%|▋ | 2/29 [00:00<00:08, 3.10it/s]\n 10%|█ | 3/29 [00:00<00:08, 3.21it/s]\n 14%|█▍ | 4/29 [00:01<00:07, 3.26it/s]\n 17%|█▋ | 5/29 [00:01<00:07, 3.30it/s]\n 21%|██ | 6/29 [00:01<00:06, 3.31it/s]\n 24%|██▍ | 7/29 [00:02<00:06, 3.32it/s]\n 28%|██▊ | 8/29 [00:02<00:06, 3.33it/s]\n 31%|███ | 9/29 [00:02<00:06, 3.33it/s]\n 34%|███▍ | 10/29 [00:03<00:05, 3.34it/s]\n 38%|███▊ | 11/29 [00:03<00:05, 3.34it/s]\n 41%|████▏ | 12/29 [00:03<00:05, 3.34it/s]\n 45%|████▍ | 13/29 [00:03<00:04, 3.34it/s]\n 48%|████▊ | 14/29 [00:04<00:04, 3.34it/s]\n 52%|█████▏ | 15/29 [00:04<00:04, 3.33it/s]\n 55%|█████▌ | 16/29 [00:04<00:03, 3.33it/s]\n 59%|█████▊ | 17/29 [00:05<00:03, 3.33it/s]\n 62%|██████▏ | 18/29 [00:05<00:03, 3.33it/s]\n 66%|██████▌ | 19/29 [00:05<00:03, 3.33it/s]\n 69%|██████▉ | 20/29 [00:06<00:02, 3.33it/s]\n 72%|███████▏ | 21/29 [00:06<00:02, 3.33it/s]\n 76%|███████▌ | 22/29 [00:06<00:02, 3.33it/s]\n 79%|███████▉ | 23/29 [00:06<00:01, 3.33it/s]\n 83%|████████▎ | 24/29 [00:07<00:01, 3.33it/s]\n 86%|████████▌ | 25/29 [00:07<00:01, 3.33it/s]\n 90%|████████▉ | 26/29 [00:07<00:00, 3.33it/s]\n 93%|█████████▎| 27/29 [00:08<00:00, 3.33it/s]\n 97%|█████████▋| 28/29 [00:08<00:00, 3.32it/s]\n100%|██████████| 29/29 [00:08<00:00, 3.32it/s]\n100%|██████████| 29/29 [00:08<00:00, 3.31it/s]", "metrics": { "predict_time": 13.74481, "total_time": 287.031347 }, "output": "https://replicate.delivery/pbxt/YqYtularwBrQP9e3foKhaQyeA21k5du04umfYA3eBqqnpPOSC/output.png", "started_at": "2024-01-30T21:42:23.912116Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/dc4dqllbowaiqmef53cpihtj5m", "cancel": "https://api.replicate.com/v1/predictions/dc4dqllbowaiqmef53cpihtj5m/cancel" }, "version": "958d6f0315da9b86f74ca6a67b8cafa1b44b4b6330f0385d956da171ec02e5ef" }
Generated in/root/.pyenv/versions/3.10.13/lib/python3.10/site-packages/torch/functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:3483.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] 0%| | 0/29 [00:00<?, ?it/s] 3%|▎ | 1/29 [00:00<00:09, 2.81it/s] 7%|▋ | 2/29 [00:00<00:08, 3.10it/s] 10%|█ | 3/29 [00:00<00:08, 3.21it/s] 14%|█▍ | 4/29 [00:01<00:07, 3.26it/s] 17%|█▋ | 5/29 [00:01<00:07, 3.30it/s] 21%|██ | 6/29 [00:01<00:06, 3.31it/s] 24%|██▍ | 7/29 [00:02<00:06, 3.32it/s] 28%|██▊ | 8/29 [00:02<00:06, 3.33it/s] 31%|███ | 9/29 [00:02<00:06, 3.33it/s] 34%|███▍ | 10/29 [00:03<00:05, 3.34it/s] 38%|███▊ | 11/29 [00:03<00:05, 3.34it/s] 41%|████▏ | 12/29 [00:03<00:05, 3.34it/s] 45%|████▍ | 13/29 [00:03<00:04, 3.34it/s] 48%|████▊ | 14/29 [00:04<00:04, 3.34it/s] 52%|█████▏ | 15/29 [00:04<00:04, 3.33it/s] 55%|█████▌ | 16/29 [00:04<00:03, 3.33it/s] 59%|█████▊ | 17/29 [00:05<00:03, 3.33it/s] 62%|██████▏ | 18/29 [00:05<00:03, 3.33it/s] 66%|██████▌ | 19/29 [00:05<00:03, 3.33it/s] 69%|██████▉ | 20/29 [00:06<00:02, 3.33it/s] 72%|███████▏ | 21/29 [00:06<00:02, 3.33it/s] 76%|███████▌ | 22/29 [00:06<00:02, 3.33it/s] 79%|███████▉ | 23/29 [00:06<00:01, 3.33it/s] 83%|████████▎ | 24/29 [00:07<00:01, 3.33it/s] 86%|████████▌ | 25/29 [00:07<00:01, 3.33it/s] 90%|████████▉ | 26/29 [00:07<00:00, 3.33it/s] 93%|█████████▎| 27/29 [00:08<00:00, 3.33it/s] 97%|█████████▋| 28/29 [00:08<00:00, 3.32it/s] 100%|██████████| 29/29 [00:08<00:00, 3.32it/s] 100%|██████████| 29/29 [00:08<00:00, 3.31it/s]
Prediction
lucataco/diffusionlight:958d6f0315da9b86f74ca6a67b8cafa1b44b4b6330f0385d956da171ec02e5efIDc3twa5lb3dphdu5rhzrf5lqngmStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- prompt
- a perfect mirrored reflective chrome ball sphere
- negative_prompt
- matte, diffuse, flat, dull
- num_inference_steps
- 30
- controlnet_conditioning_scale
- 0.5
{ "image": "https://replicate.delivery/pbxt/KJoKQAifOmk7YFHsSVzSabOJdgjb6QXrgyjSCh3rskrUK32a/ski.jpeg", "prompt": "a perfect mirrored reflective chrome ball sphere", "negative_prompt": "matte, diffuse, flat, dull", "num_inference_steps": 30, "controlnet_conditioning_scale": 0.5 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run lucataco/diffusionlight using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/diffusionlight:958d6f0315da9b86f74ca6a67b8cafa1b44b4b6330f0385d956da171ec02e5ef", { input: { image: "https://replicate.delivery/pbxt/KJoKQAifOmk7YFHsSVzSabOJdgjb6QXrgyjSCh3rskrUK32a/ski.jpeg", prompt: "a perfect mirrored reflective chrome ball sphere", negative_prompt: "matte, diffuse, flat, dull", num_inference_steps: 30, controlnet_conditioning_scale: 0.5 } } ); // To access the file URL: console.log(output.url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Import the client:import replicate
Run lucataco/diffusionlight using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/diffusionlight:958d6f0315da9b86f74ca6a67b8cafa1b44b4b6330f0385d956da171ec02e5ef", input={ "image": "https://replicate.delivery/pbxt/KJoKQAifOmk7YFHsSVzSabOJdgjb6QXrgyjSCh3rskrUK32a/ski.jpeg", "prompt": "a perfect mirrored reflective chrome ball sphere", "negative_prompt": "matte, diffuse, flat, dull", "num_inference_steps": 30, "controlnet_conditioning_scale": 0.5 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run lucataco/diffusionlight using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "lucataco/diffusionlight:958d6f0315da9b86f74ca6a67b8cafa1b44b4b6330f0385d956da171ec02e5ef", "input": { "image": "https://replicate.delivery/pbxt/KJoKQAifOmk7YFHsSVzSabOJdgjb6QXrgyjSCh3rskrUK32a/ski.jpeg", "prompt": "a perfect mirrored reflective chrome ball sphere", "negative_prompt": "matte, diffuse, flat, dull", "num_inference_steps": 30, "controlnet_conditioning_scale": 0.5 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-01-30T21:51:51.655582Z", "created_at": "2024-01-30T21:49:10.599328Z", "data_removed": false, "error": null, "id": "c3twa5lb3dphdu5rhzrf5lqngm", "input": { "image": "https://replicate.delivery/pbxt/KJoKQAifOmk7YFHsSVzSabOJdgjb6QXrgyjSCh3rskrUK32a/ski.jpeg", "prompt": "a perfect mirrored reflective chrome ball sphere", "negative_prompt": "matte, diffuse, flat, dull", "num_inference_steps": 30, "controlnet_conditioning_scale": 0.5 }, "logs": "/root/.pyenv/versions/3.10.13/lib/python3.10/site-packages/torch/functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:3483.)\nreturn _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]\n 0%| | 0/29 [00:00<?, ?it/s]\n 3%|▎ | 1/29 [00:00<00:10, 2.72it/s]\n 7%|▋ | 2/29 [00:00<00:08, 3.09it/s]\n 10%|█ | 3/29 [00:00<00:08, 3.19it/s]\n 14%|█▍ | 4/29 [00:01<00:07, 3.27it/s]\n 17%|█▋ | 5/29 [00:01<00:07, 3.32it/s]\n 21%|██ | 6/29 [00:01<00:06, 3.34it/s]\n 24%|██▍ | 7/29 [00:02<00:06, 3.36it/s]\n 28%|██▊ | 8/29 [00:02<00:06, 3.37it/s]\n 31%|███ | 9/29 [00:02<00:05, 3.38it/s]\n 34%|███▍ | 10/29 [00:03<00:05, 3.38it/s]\n 38%|███▊ | 11/29 [00:03<00:05, 3.38it/s]\n 41%|████▏ | 12/29 [00:03<00:05, 3.39it/s]\n 45%|████▍ | 13/29 [00:03<00:04, 3.39it/s]\n 48%|████▊ | 14/29 [00:04<00:04, 3.39it/s]\n 52%|█████▏ | 15/29 [00:04<00:04, 3.39it/s]\n 55%|█████▌ | 16/29 [00:04<00:03, 3.39it/s]\n 59%|█████▊ | 17/29 [00:05<00:03, 3.38it/s]\n 62%|██████▏ | 18/29 [00:05<00:03, 3.38it/s]\n 66%|██████▌ | 19/29 [00:05<00:02, 3.38it/s]\n 69%|██████▉ | 20/29 [00:05<00:02, 3.38it/s]\n 72%|███████▏ | 21/29 [00:06<00:02, 3.38it/s]\n 76%|███████▌ | 22/29 [00:06<00:02, 3.38it/s]\n 79%|███████▉ | 23/29 [00:06<00:01, 3.38it/s]\n 83%|████████▎ | 24/29 [00:07<00:01, 3.38it/s]\n 86%|████████▌ | 25/29 [00:07<00:01, 3.38it/s]\n 90%|████████▉ | 26/29 [00:07<00:00, 3.38it/s]\n 93%|█████████▎| 27/29 [00:08<00:00, 3.38it/s]\n 97%|█████████▋| 28/29 [00:08<00:00, 3.37it/s]\n100%|██████████| 29/29 [00:08<00:00, 3.37it/s]\n100%|██████████| 29/29 [00:08<00:00, 3.35it/s]", "metrics": { "predict_time": 12.652394, "total_time": 161.056254 }, "output": "https://replicate.delivery/pbxt/Vkrkqo4CIxqVGNHcZy6EGY11W5KaBuu6ggRYeFsJ5fN3FyRSA/output.png", "started_at": "2024-01-30T21:51:39.003188Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/c3twa5lb3dphdu5rhzrf5lqngm", "cancel": "https://api.replicate.com/v1/predictions/c3twa5lb3dphdu5rhzrf5lqngm/cancel" }, "version": "958d6f0315da9b86f74ca6a67b8cafa1b44b4b6330f0385d956da171ec02e5ef" }
Generated in/root/.pyenv/versions/3.10.13/lib/python3.10/site-packages/torch/functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:3483.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] 0%| | 0/29 [00:00<?, ?it/s] 3%|▎ | 1/29 [00:00<00:10, 2.72it/s] 7%|▋ | 2/29 [00:00<00:08, 3.09it/s] 10%|█ | 3/29 [00:00<00:08, 3.19it/s] 14%|█▍ | 4/29 [00:01<00:07, 3.27it/s] 17%|█▋ | 5/29 [00:01<00:07, 3.32it/s] 21%|██ | 6/29 [00:01<00:06, 3.34it/s] 24%|██▍ | 7/29 [00:02<00:06, 3.36it/s] 28%|██▊ | 8/29 [00:02<00:06, 3.37it/s] 31%|███ | 9/29 [00:02<00:05, 3.38it/s] 34%|███▍ | 10/29 [00:03<00:05, 3.38it/s] 38%|███▊ | 11/29 [00:03<00:05, 3.38it/s] 41%|████▏ | 12/29 [00:03<00:05, 3.39it/s] 45%|████▍ | 13/29 [00:03<00:04, 3.39it/s] 48%|████▊ | 14/29 [00:04<00:04, 3.39it/s] 52%|█████▏ | 15/29 [00:04<00:04, 3.39it/s] 55%|█████▌ | 16/29 [00:04<00:03, 3.39it/s] 59%|█████▊ | 17/29 [00:05<00:03, 3.38it/s] 62%|██████▏ | 18/29 [00:05<00:03, 3.38it/s] 66%|██████▌ | 19/29 [00:05<00:02, 3.38it/s] 69%|██████▉ | 20/29 [00:05<00:02, 3.38it/s] 72%|███████▏ | 21/29 [00:06<00:02, 3.38it/s] 76%|███████▌ | 22/29 [00:06<00:02, 3.38it/s] 79%|███████▉ | 23/29 [00:06<00:01, 3.38it/s] 83%|████████▎ | 24/29 [00:07<00:01, 3.38it/s] 86%|████████▌ | 25/29 [00:07<00:01, 3.38it/s] 90%|████████▉ | 26/29 [00:07<00:00, 3.38it/s] 93%|█████████▎| 27/29 [00:08<00:00, 3.38it/s] 97%|█████████▋| 28/29 [00:08<00:00, 3.37it/s] 100%|██████████| 29/29 [00:08<00:00, 3.37it/s] 100%|██████████| 29/29 [00:08<00:00, 3.35it/s]
Prediction
lucataco/diffusionlight:958d6f0315da9b86f74ca6a67b8cafa1b44b4b6330f0385d956da171ec02e5efID2unlkz3brcoxc6p5wh7riqccsqStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- prompt
- a perfect mirrored reflective chrome ball sphere
- negative_prompt
- matte, diffuse, flat, dull
- num_inference_steps
- 30
- controlnet_conditioning_scale
- 0.5
{ "image": "https://replicate.delivery/pbxt/KJoRUsamLsqRyHxi3zsvimTpWPF4y2YNBp5G6qPuSgwinvaO/fountain.jpg", "prompt": "a perfect mirrored reflective chrome ball sphere", "negative_prompt": "matte, diffuse, flat, dull", "num_inference_steps": 30, "controlnet_conditioning_scale": 0.5 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run lucataco/diffusionlight using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/diffusionlight:958d6f0315da9b86f74ca6a67b8cafa1b44b4b6330f0385d956da171ec02e5ef", { input: { image: "https://replicate.delivery/pbxt/KJoRUsamLsqRyHxi3zsvimTpWPF4y2YNBp5G6qPuSgwinvaO/fountain.jpg", prompt: "a perfect mirrored reflective chrome ball sphere", negative_prompt: "matte, diffuse, flat, dull", num_inference_steps: 30, controlnet_conditioning_scale: 0.5 } } ); // To access the file URL: console.log(output.url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Import the client:import replicate
Run lucataco/diffusionlight using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/diffusionlight:958d6f0315da9b86f74ca6a67b8cafa1b44b4b6330f0385d956da171ec02e5ef", input={ "image": "https://replicate.delivery/pbxt/KJoRUsamLsqRyHxi3zsvimTpWPF4y2YNBp5G6qPuSgwinvaO/fountain.jpg", "prompt": "a perfect mirrored reflective chrome ball sphere", "negative_prompt": "matte, diffuse, flat, dull", "num_inference_steps": 30, "controlnet_conditioning_scale": 0.5 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run lucataco/diffusionlight using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "lucataco/diffusionlight:958d6f0315da9b86f74ca6a67b8cafa1b44b4b6330f0385d956da171ec02e5ef", "input": { "image": "https://replicate.delivery/pbxt/KJoRUsamLsqRyHxi3zsvimTpWPF4y2YNBp5G6qPuSgwinvaO/fountain.jpg", "prompt": "a perfect mirrored reflective chrome ball sphere", "negative_prompt": "matte, diffuse, flat, dull", "num_inference_steps": 30, "controlnet_conditioning_scale": 0.5 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-01-30T21:52:11.810101Z", "created_at": "2024-01-30T21:51:59.412923Z", "data_removed": false, "error": null, "id": "2unlkz3brcoxc6p5wh7riqccsq", "input": { "image": "https://replicate.delivery/pbxt/KJoRUsamLsqRyHxi3zsvimTpWPF4y2YNBp5G6qPuSgwinvaO/fountain.jpg", "prompt": "a perfect mirrored reflective chrome ball sphere", "negative_prompt": "matte, diffuse, flat, dull", "num_inference_steps": 30, "controlnet_conditioning_scale": 0.5 }, "logs": "0%| | 0/29 [00:00<?, ?it/s]\n 3%|▎ | 1/29 [00:00<00:08, 3.40it/s]\n 7%|▋ | 2/29 [00:00<00:07, 3.39it/s]\n 10%|█ | 3/29 [00:00<00:07, 3.38it/s]\n 14%|█▍ | 4/29 [00:01<00:07, 3.38it/s]\n 17%|█▋ | 5/29 [00:01<00:07, 3.38it/s]\n 21%|██ | 6/29 [00:01<00:06, 3.37it/s]\n 24%|██▍ | 7/29 [00:02<00:06, 3.37it/s]\n 28%|██▊ | 8/29 [00:02<00:06, 3.37it/s]\n 31%|███ | 9/29 [00:02<00:05, 3.37it/s]\n 34%|███▍ | 10/29 [00:02<00:05, 3.37it/s]\n 38%|███▊ | 11/29 [00:03<00:05, 3.37it/s]\n 41%|████▏ | 12/29 [00:03<00:05, 3.37it/s]\n 45%|████▍ | 13/29 [00:03<00:04, 3.37it/s]\n 48%|████▊ | 14/29 [00:04<00:04, 3.36it/s]\n 52%|█████▏ | 15/29 [00:04<00:04, 3.37it/s]\n 55%|█████▌ | 16/29 [00:04<00:03, 3.37it/s]\n 59%|█████▊ | 17/29 [00:05<00:03, 3.37it/s]\n 62%|██████▏ | 18/29 [00:05<00:03, 3.37it/s]\n 66%|██████▌ | 19/29 [00:05<00:02, 3.37it/s]\n 69%|██████▉ | 20/29 [00:05<00:02, 3.37it/s]\n 72%|███████▏ | 21/29 [00:06<00:02, 3.38it/s]\n 76%|███████▌ | 22/29 [00:06<00:02, 3.38it/s]\n 79%|███████▉ | 23/29 [00:06<00:01, 3.38it/s]\n 83%|████████▎ | 24/29 [00:07<00:01, 3.39it/s]\n 86%|████████▌ | 25/29 [00:07<00:01, 3.39it/s]\n 90%|████████▉ | 26/29 [00:07<00:00, 3.39it/s]\n 93%|█████████▎| 27/29 [00:07<00:00, 3.39it/s]\n 97%|█████████▋| 28/29 [00:08<00:00, 3.39it/s]\n100%|██████████| 29/29 [00:08<00:00, 3.39it/s]\n100%|██████████| 29/29 [00:08<00:00, 3.38it/s]", "metrics": { "predict_time": 12.36379, "total_time": 12.397178 }, "output": "https://replicate.delivery/pbxt/zeUOMvmigWz5CKmuVxXPerf6hQJ2LkdcUYrvvtipDDKXMkjkA/output.png", "started_at": "2024-01-30T21:51:59.446311Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/2unlkz3brcoxc6p5wh7riqccsq", "cancel": "https://api.replicate.com/v1/predictions/2unlkz3brcoxc6p5wh7riqccsq/cancel" }, "version": "958d6f0315da9b86f74ca6a67b8cafa1b44b4b6330f0385d956da171ec02e5ef" }
Generated in0%| | 0/29 [00:00<?, ?it/s] 3%|▎ | 1/29 [00:00<00:08, 3.40it/s] 7%|▋ | 2/29 [00:00<00:07, 3.39it/s] 10%|█ | 3/29 [00:00<00:07, 3.38it/s] 14%|█▍ | 4/29 [00:01<00:07, 3.38it/s] 17%|█▋ | 5/29 [00:01<00:07, 3.38it/s] 21%|██ | 6/29 [00:01<00:06, 3.37it/s] 24%|██▍ | 7/29 [00:02<00:06, 3.37it/s] 28%|██▊ | 8/29 [00:02<00:06, 3.37it/s] 31%|███ | 9/29 [00:02<00:05, 3.37it/s] 34%|███▍ | 10/29 [00:02<00:05, 3.37it/s] 38%|███▊ | 11/29 [00:03<00:05, 3.37it/s] 41%|████▏ | 12/29 [00:03<00:05, 3.37it/s] 45%|████▍ | 13/29 [00:03<00:04, 3.37it/s] 48%|████▊ | 14/29 [00:04<00:04, 3.36it/s] 52%|█████▏ | 15/29 [00:04<00:04, 3.37it/s] 55%|█████▌ | 16/29 [00:04<00:03, 3.37it/s] 59%|█████▊ | 17/29 [00:05<00:03, 3.37it/s] 62%|██████▏ | 18/29 [00:05<00:03, 3.37it/s] 66%|██████▌ | 19/29 [00:05<00:02, 3.37it/s] 69%|██████▉ | 20/29 [00:05<00:02, 3.37it/s] 72%|███████▏ | 21/29 [00:06<00:02, 3.38it/s] 76%|███████▌ | 22/29 [00:06<00:02, 3.38it/s] 79%|███████▉ | 23/29 [00:06<00:01, 3.38it/s] 83%|████████▎ | 24/29 [00:07<00:01, 3.39it/s] 86%|████████▌ | 25/29 [00:07<00:01, 3.39it/s] 90%|████████▉ | 26/29 [00:07<00:00, 3.39it/s] 93%|█████████▎| 27/29 [00:07<00:00, 3.39it/s] 97%|█████████▋| 28/29 [00:08<00:00, 3.39it/s] 100%|██████████| 29/29 [00:08<00:00, 3.39it/s] 100%|██████████| 29/29 [00:08<00:00, 3.38it/s]
Prediction
lucataco/diffusionlight:958d6f0315da9b86f74ca6a67b8cafa1b44b4b6330f0385d956da171ec02e5efIDrmgafv3bwvpjrcyhsryzumunkyStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- prompt
- a perfect mirrored reflective chrome ball sphere
- negative_prompt
- matte, diffuse, flat, dull
- num_inference_steps
- 30
- controlnet_conditioning_scale
- 0.5
{ "image": "https://replicate.delivery/pbxt/KJoRu8KEOxkJq4rtVV3kEga53JZj7iXtActgz9Lfe36M6Xa0/temple.png", "prompt": "a perfect mirrored reflective chrome ball sphere", "negative_prompt": "matte, diffuse, flat, dull", "num_inference_steps": 30, "controlnet_conditioning_scale": 0.5 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run lucataco/diffusionlight using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/diffusionlight:958d6f0315da9b86f74ca6a67b8cafa1b44b4b6330f0385d956da171ec02e5ef", { input: { image: "https://replicate.delivery/pbxt/KJoRu8KEOxkJq4rtVV3kEga53JZj7iXtActgz9Lfe36M6Xa0/temple.png", prompt: "a perfect mirrored reflective chrome ball sphere", negative_prompt: "matte, diffuse, flat, dull", num_inference_steps: 30, controlnet_conditioning_scale: 0.5 } } ); // To access the file URL: console.log(output.url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Import the client:import replicate
Run lucataco/diffusionlight using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/diffusionlight:958d6f0315da9b86f74ca6a67b8cafa1b44b4b6330f0385d956da171ec02e5ef", input={ "image": "https://replicate.delivery/pbxt/KJoRu8KEOxkJq4rtVV3kEga53JZj7iXtActgz9Lfe36M6Xa0/temple.png", "prompt": "a perfect mirrored reflective chrome ball sphere", "negative_prompt": "matte, diffuse, flat, dull", "num_inference_steps": 30, "controlnet_conditioning_scale": 0.5 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run lucataco/diffusionlight using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "lucataco/diffusionlight:958d6f0315da9b86f74ca6a67b8cafa1b44b4b6330f0385d956da171ec02e5ef", "input": { "image": "https://replicate.delivery/pbxt/KJoRu8KEOxkJq4rtVV3kEga53JZj7iXtActgz9Lfe36M6Xa0/temple.png", "prompt": "a perfect mirrored reflective chrome ball sphere", "negative_prompt": "matte, diffuse, flat, dull", "num_inference_steps": 30, "controlnet_conditioning_scale": 0.5 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-01-30T21:52:40.335140Z", "created_at": "2024-01-30T21:52:26.321345Z", "data_removed": false, "error": null, "id": "rmgafv3bwvpjrcyhsryzumunky", "input": { "image": "https://replicate.delivery/pbxt/KJoRu8KEOxkJq4rtVV3kEga53JZj7iXtActgz9Lfe36M6Xa0/temple.png", "prompt": "a perfect mirrored reflective chrome ball sphere", "negative_prompt": "matte, diffuse, flat, dull", "num_inference_steps": 30, "controlnet_conditioning_scale": 0.5 }, "logs": "0%| | 0/29 [00:00<?, ?it/s]\n 3%|▎ | 1/29 [00:00<00:08, 3.39it/s]\n 7%|▋ | 2/29 [00:00<00:07, 3.38it/s]\n 10%|█ | 3/29 [00:00<00:07, 3.38it/s]\n 14%|█▍ | 4/29 [00:01<00:07, 3.38it/s]\n 17%|█▋ | 5/29 [00:01<00:07, 3.37it/s]\n 21%|██ | 6/29 [00:01<00:06, 3.37it/s]\n 24%|██▍ | 7/29 [00:02<00:06, 3.37it/s]\n 28%|██▊ | 8/29 [00:02<00:06, 3.37it/s]\n 31%|███ | 9/29 [00:02<00:05, 3.37it/s]\n 34%|███▍ | 10/29 [00:02<00:05, 3.37it/s]\n 38%|███▊ | 11/29 [00:03<00:05, 3.37it/s]\n 41%|████▏ | 12/29 [00:03<00:05, 3.37it/s]\n 45%|████▍ | 13/29 [00:03<00:04, 3.37it/s]\n 48%|████▊ | 14/29 [00:04<00:04, 3.38it/s]\n 52%|█████▏ | 15/29 [00:04<00:04, 3.38it/s]\n 55%|█████▌ | 16/29 [00:04<00:03, 3.38it/s]\n 59%|█████▊ | 17/29 [00:05<00:03, 3.38it/s]\n 62%|██████▏ | 18/29 [00:05<00:03, 3.39it/s]\n 66%|██████▌ | 19/29 [00:05<00:02, 3.39it/s]\n 69%|██████▉ | 20/29 [00:05<00:02, 3.39it/s]\n 72%|███████▏ | 21/29 [00:06<00:02, 3.39it/s]\n 76%|███████▌ | 22/29 [00:06<00:02, 3.39it/s]\n 79%|███████▉ | 23/29 [00:06<00:01, 3.38it/s]\n 83%|████████▎ | 24/29 [00:07<00:01, 3.38it/s]\n 86%|████████▌ | 25/29 [00:07<00:01, 3.38it/s]\n 90%|████████▉ | 26/29 [00:07<00:00, 3.39it/s]\n 93%|█████████▎| 27/29 [00:07<00:00, 3.38it/s]\n 97%|█████████▋| 28/29 [00:08<00:00, 3.38it/s]\n100%|██████████| 29/29 [00:08<00:00, 3.39it/s]\n100%|██████████| 29/29 [00:08<00:00, 3.38it/s]", "metrics": { "predict_time": 14.001297, "total_time": 14.013795 }, "output": "https://replicate.delivery/pbxt/weKcHtMwx5X9FCvkzkh7RnOW9yQ1DcgxxPXpIm7lKX7TD5IJA/output.png", "started_at": "2024-01-30T21:52:26.333843Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/rmgafv3bwvpjrcyhsryzumunky", "cancel": "https://api.replicate.com/v1/predictions/rmgafv3bwvpjrcyhsryzumunky/cancel" }, "version": "958d6f0315da9b86f74ca6a67b8cafa1b44b4b6330f0385d956da171ec02e5ef" }
Generated in0%| | 0/29 [00:00<?, ?it/s] 3%|▎ | 1/29 [00:00<00:08, 3.39it/s] 7%|▋ | 2/29 [00:00<00:07, 3.38it/s] 10%|█ | 3/29 [00:00<00:07, 3.38it/s] 14%|█▍ | 4/29 [00:01<00:07, 3.38it/s] 17%|█▋ | 5/29 [00:01<00:07, 3.37it/s] 21%|██ | 6/29 [00:01<00:06, 3.37it/s] 24%|██▍ | 7/29 [00:02<00:06, 3.37it/s] 28%|██▊ | 8/29 [00:02<00:06, 3.37it/s] 31%|███ | 9/29 [00:02<00:05, 3.37it/s] 34%|███▍ | 10/29 [00:02<00:05, 3.37it/s] 38%|███▊ | 11/29 [00:03<00:05, 3.37it/s] 41%|████▏ | 12/29 [00:03<00:05, 3.37it/s] 45%|████▍ | 13/29 [00:03<00:04, 3.37it/s] 48%|████▊ | 14/29 [00:04<00:04, 3.38it/s] 52%|█████▏ | 15/29 [00:04<00:04, 3.38it/s] 55%|█████▌ | 16/29 [00:04<00:03, 3.38it/s] 59%|█████▊ | 17/29 [00:05<00:03, 3.38it/s] 62%|██████▏ | 18/29 [00:05<00:03, 3.39it/s] 66%|██████▌ | 19/29 [00:05<00:02, 3.39it/s] 69%|██████▉ | 20/29 [00:05<00:02, 3.39it/s] 72%|███████▏ | 21/29 [00:06<00:02, 3.39it/s] 76%|███████▌ | 22/29 [00:06<00:02, 3.39it/s] 79%|███████▉ | 23/29 [00:06<00:01, 3.38it/s] 83%|████████▎ | 24/29 [00:07<00:01, 3.38it/s] 86%|████████▌ | 25/29 [00:07<00:01, 3.38it/s] 90%|████████▉ | 26/29 [00:07<00:00, 3.39it/s] 93%|█████████▎| 27/29 [00:07<00:00, 3.38it/s] 97%|█████████▋| 28/29 [00:08<00:00, 3.38it/s] 100%|██████████| 29/29 [00:08<00:00, 3.39it/s] 100%|██████████| 29/29 [00:08<00:00, 3.38it/s]
Prediction
lucataco/diffusionlight:958d6f0315da9b86f74ca6a67b8cafa1b44b4b6330f0385d956da171ec02e5efID33g3vddbsmz73wwsgu7adxmvdiStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- prompt
- a perfect mirrored reflective chrome ball sphere
- negative_prompt
- matte, diffuse, flat, dull
- num_inference_steps
- 30
- controlnet_conditioning_scale
- 0.5
{ "image": "https://replicate.delivery/pbxt/KJoSORjE5eWmSivlqO28n5qI3ovSYubYzYR9nY2TDhCWaeDa/anime_on_wall%20%281%29.jpg", "prompt": "a perfect mirrored reflective chrome ball sphere", "negative_prompt": "matte, diffuse, flat, dull", "num_inference_steps": 30, "controlnet_conditioning_scale": 0.5 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run lucataco/diffusionlight using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/diffusionlight:958d6f0315da9b86f74ca6a67b8cafa1b44b4b6330f0385d956da171ec02e5ef", { input: { image: "https://replicate.delivery/pbxt/KJoSORjE5eWmSivlqO28n5qI3ovSYubYzYR9nY2TDhCWaeDa/anime_on_wall%20%281%29.jpg", prompt: "a perfect mirrored reflective chrome ball sphere", negative_prompt: "matte, diffuse, flat, dull", num_inference_steps: 30, controlnet_conditioning_scale: 0.5 } } ); // To access the file URL: console.log(output.url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Import the client:import replicate
Run lucataco/diffusionlight using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/diffusionlight:958d6f0315da9b86f74ca6a67b8cafa1b44b4b6330f0385d956da171ec02e5ef", input={ "image": "https://replicate.delivery/pbxt/KJoSORjE5eWmSivlqO28n5qI3ovSYubYzYR9nY2TDhCWaeDa/anime_on_wall%20%281%29.jpg", "prompt": "a perfect mirrored reflective chrome ball sphere", "negative_prompt": "matte, diffuse, flat, dull", "num_inference_steps": 30, "controlnet_conditioning_scale": 0.5 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run lucataco/diffusionlight using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "lucataco/diffusionlight:958d6f0315da9b86f74ca6a67b8cafa1b44b4b6330f0385d956da171ec02e5ef", "input": { "image": "https://replicate.delivery/pbxt/KJoSORjE5eWmSivlqO28n5qI3ovSYubYzYR9nY2TDhCWaeDa/anime_on_wall%20%281%29.jpg", "prompt": "a perfect mirrored reflective chrome ball sphere", "negative_prompt": "matte, diffuse, flat, dull", "num_inference_steps": 30, "controlnet_conditioning_scale": 0.5 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-01-30T21:53:09.162373Z", "created_at": "2024-01-30T21:52:56.792138Z", "data_removed": false, "error": null, "id": "33g3vddbsmz73wwsgu7adxmvdi", "input": { "image": "https://replicate.delivery/pbxt/KJoSORjE5eWmSivlqO28n5qI3ovSYubYzYR9nY2TDhCWaeDa/anime_on_wall%20%281%29.jpg", "prompt": "a perfect mirrored reflective chrome ball sphere", "negative_prompt": "matte, diffuse, flat, dull", "num_inference_steps": 30, "controlnet_conditioning_scale": 0.5 }, "logs": "0%| | 0/29 [00:00<?, ?it/s]\n 3%|▎ | 1/29 [00:00<00:08, 3.39it/s]\n 7%|▋ | 2/29 [00:00<00:07, 3.38it/s]\n 10%|█ | 3/29 [00:00<00:07, 3.38it/s]\n 14%|█▍ | 4/29 [00:01<00:07, 3.38it/s]\n 17%|█▋ | 5/29 [00:01<00:07, 3.37it/s]\n 21%|██ | 6/29 [00:01<00:06, 3.37it/s]\n 24%|██▍ | 7/29 [00:02<00:06, 3.37it/s]\n 28%|██▊ | 8/29 [00:02<00:06, 3.37it/s]\n 31%|███ | 9/29 [00:02<00:05, 3.37it/s]\n 34%|███▍ | 10/29 [00:02<00:05, 3.37it/s]\n 38%|███▊ | 11/29 [00:03<00:05, 3.37it/s]\n 41%|████▏ | 12/29 [00:03<00:05, 3.38it/s]\n 45%|████▍ | 13/29 [00:03<00:04, 3.38it/s]\n 48%|████▊ | 14/29 [00:04<00:04, 3.38it/s]\n 52%|█████▏ | 15/29 [00:04<00:04, 3.39it/s]\n 55%|█████▌ | 16/29 [00:04<00:03, 3.38it/s]\n 59%|█████▊ | 17/29 [00:05<00:03, 3.39it/s]\n 62%|██████▏ | 18/29 [00:05<00:03, 3.39it/s]\n 66%|██████▌ | 19/29 [00:05<00:02, 3.39it/s]\n 69%|██████▉ | 20/29 [00:05<00:02, 3.39it/s]\n 72%|███████▏ | 21/29 [00:06<00:02, 3.38it/s]\n 76%|███████▌ | 22/29 [00:06<00:02, 3.38it/s]\n 79%|███████▉ | 23/29 [00:06<00:01, 3.38it/s]\n 83%|████████▎ | 24/29 [00:07<00:01, 3.38it/s]\n 86%|████████▌ | 25/29 [00:07<00:01, 3.38it/s]\n 90%|████████▉ | 26/29 [00:07<00:00, 3.38it/s]\n 93%|█████████▎| 27/29 [00:07<00:00, 3.38it/s]\n 97%|█████████▋| 28/29 [00:08<00:00, 3.38it/s]\n100%|██████████| 29/29 [00:08<00:00, 3.38it/s]\n100%|██████████| 29/29 [00:08<00:00, 3.38it/s]", "metrics": { "predict_time": 12.352713, "total_time": 12.370235 }, "output": "https://replicate.delivery/pbxt/IetkYzUifEg9vU4LxWfiSLHufv4IwblMvYeDaj9zX33h4QOSC/output.png", "started_at": "2024-01-30T21:52:56.809660Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/33g3vddbsmz73wwsgu7adxmvdi", "cancel": "https://api.replicate.com/v1/predictions/33g3vddbsmz73wwsgu7adxmvdi/cancel" }, "version": "958d6f0315da9b86f74ca6a67b8cafa1b44b4b6330f0385d956da171ec02e5ef" }
Generated in0%| | 0/29 [00:00<?, ?it/s] 3%|▎ | 1/29 [00:00<00:08, 3.39it/s] 7%|▋ | 2/29 [00:00<00:07, 3.38it/s] 10%|█ | 3/29 [00:00<00:07, 3.38it/s] 14%|█▍ | 4/29 [00:01<00:07, 3.38it/s] 17%|█▋ | 5/29 [00:01<00:07, 3.37it/s] 21%|██ | 6/29 [00:01<00:06, 3.37it/s] 24%|██▍ | 7/29 [00:02<00:06, 3.37it/s] 28%|██▊ | 8/29 [00:02<00:06, 3.37it/s] 31%|███ | 9/29 [00:02<00:05, 3.37it/s] 34%|███▍ | 10/29 [00:02<00:05, 3.37it/s] 38%|███▊ | 11/29 [00:03<00:05, 3.37it/s] 41%|████▏ | 12/29 [00:03<00:05, 3.38it/s] 45%|████▍ | 13/29 [00:03<00:04, 3.38it/s] 48%|████▊ | 14/29 [00:04<00:04, 3.38it/s] 52%|█████▏ | 15/29 [00:04<00:04, 3.39it/s] 55%|█████▌ | 16/29 [00:04<00:03, 3.38it/s] 59%|█████▊ | 17/29 [00:05<00:03, 3.39it/s] 62%|██████▏ | 18/29 [00:05<00:03, 3.39it/s] 66%|██████▌ | 19/29 [00:05<00:02, 3.39it/s] 69%|██████▉ | 20/29 [00:05<00:02, 3.39it/s] 72%|███████▏ | 21/29 [00:06<00:02, 3.38it/s] 76%|███████▌ | 22/29 [00:06<00:02, 3.38it/s] 79%|███████▉ | 23/29 [00:06<00:01, 3.38it/s] 83%|████████▎ | 24/29 [00:07<00:01, 3.38it/s] 86%|████████▌ | 25/29 [00:07<00:01, 3.38it/s] 90%|████████▉ | 26/29 [00:07<00:00, 3.38it/s] 93%|█████████▎| 27/29 [00:07<00:00, 3.38it/s] 97%|█████████▋| 28/29 [00:08<00:00, 3.38it/s] 100%|██████████| 29/29 [00:08<00:00, 3.38it/s] 100%|██████████| 29/29 [00:08<00:00, 3.38it/s]
Prediction
lucataco/diffusionlight:958d6f0315da9b86f74ca6a67b8cafa1b44b4b6330f0385d956da171ec02e5efIDwgkwsddbkt4bbzw5dnhhshivzyStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- prompt
- a perfect mirrored reflective chrome ball sphere
- negative_prompt
- matte, diffuse, flat, dull
- num_inference_steps
- 30
- controlnet_conditioning_scale
- 0.5
{ "image": "https://replicate.delivery/pbxt/KJom4S0KWCYFLr3KxttipoAZGGfSd8NySbatwcyl7meDIKn5/oxaca.jpg", "prompt": "a perfect mirrored reflective chrome ball sphere", "negative_prompt": "matte, diffuse, flat, dull", "num_inference_steps": 30, "controlnet_conditioning_scale": 0.5 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run lucataco/diffusionlight using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/diffusionlight:958d6f0315da9b86f74ca6a67b8cafa1b44b4b6330f0385d956da171ec02e5ef", { input: { image: "https://replicate.delivery/pbxt/KJom4S0KWCYFLr3KxttipoAZGGfSd8NySbatwcyl7meDIKn5/oxaca.jpg", prompt: "a perfect mirrored reflective chrome ball sphere", negative_prompt: "matte, diffuse, flat, dull", num_inference_steps: 30, controlnet_conditioning_scale: 0.5 } } ); // To access the file URL: console.log(output.url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Import the client:import replicate
Run lucataco/diffusionlight using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/diffusionlight:958d6f0315da9b86f74ca6a67b8cafa1b44b4b6330f0385d956da171ec02e5ef", input={ "image": "https://replicate.delivery/pbxt/KJom4S0KWCYFLr3KxttipoAZGGfSd8NySbatwcyl7meDIKn5/oxaca.jpg", "prompt": "a perfect mirrored reflective chrome ball sphere", "negative_prompt": "matte, diffuse, flat, dull", "num_inference_steps": 30, "controlnet_conditioning_scale": 0.5 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run lucataco/diffusionlight using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "lucataco/diffusionlight:958d6f0315da9b86f74ca6a67b8cafa1b44b4b6330f0385d956da171ec02e5ef", "input": { "image": "https://replicate.delivery/pbxt/KJom4S0KWCYFLr3KxttipoAZGGfSd8NySbatwcyl7meDIKn5/oxaca.jpg", "prompt": "a perfect mirrored reflective chrome ball sphere", "negative_prompt": "matte, diffuse, flat, dull", "num_inference_steps": 30, "controlnet_conditioning_scale": 0.5 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-01-30T22:13:56.337001Z", "created_at": "2024-01-30T22:13:42.891700Z", "data_removed": false, "error": null, "id": "wgkwsddbkt4bbzw5dnhhshivzy", "input": { "image": "https://replicate.delivery/pbxt/KJom4S0KWCYFLr3KxttipoAZGGfSd8NySbatwcyl7meDIKn5/oxaca.jpg", "prompt": "a perfect mirrored reflective chrome ball sphere", "negative_prompt": "matte, diffuse, flat, dull", "num_inference_steps": 30, "controlnet_conditioning_scale": 0.5 }, "logs": "0%| | 0/29 [00:00<?, ?it/s]\n 3%|▎ | 1/29 [00:00<00:10, 2.71it/s]\n 7%|▋ | 2/29 [00:00<00:08, 3.06it/s]\n 10%|█ | 3/29 [00:00<00:08, 3.19it/s]\n 14%|█▍ | 4/29 [00:01<00:07, 3.25it/s]\n 17%|█▋ | 5/29 [00:01<00:07, 3.29it/s]\n 21%|██ | 6/29 [00:01<00:06, 3.31it/s]\n 24%|██▍ | 7/29 [00:02<00:06, 3.32it/s]\n 28%|██▊ | 8/29 [00:02<00:06, 3.33it/s]\n 31%|███ | 9/29 [00:02<00:05, 3.34it/s]\n 34%|███▍ | 10/29 [00:03<00:05, 3.34it/s]\n 38%|███▊ | 11/29 [00:03<00:05, 3.34it/s]\n 41%|████▏ | 12/29 [00:03<00:05, 3.35it/s]\n 45%|████▍ | 13/29 [00:03<00:04, 3.35it/s]\n 48%|████▊ | 14/29 [00:04<00:04, 3.36it/s]\n 52%|█████▏ | 15/29 [00:04<00:04, 3.36it/s]\n 55%|█████▌ | 16/29 [00:04<00:03, 3.37it/s]\n 59%|█████▊ | 17/29 [00:05<00:03, 3.37it/s]\n 62%|██████▏ | 18/29 [00:05<00:03, 3.37it/s]\n 66%|██████▌ | 19/29 [00:05<00:02, 3.37it/s]\n 69%|██████▉ | 20/29 [00:06<00:02, 3.37it/s]\n 72%|███████▏ | 21/29 [00:06<00:02, 3.37it/s]\n 76%|███████▌ | 22/29 [00:06<00:02, 3.37it/s]\n 79%|███████▉ | 23/29 [00:06<00:01, 3.37it/s]\n 83%|████████▎ | 24/29 [00:07<00:01, 3.37it/s]\n 86%|████████▌ | 25/29 [00:07<00:01, 3.37it/s]\n 90%|████████▉ | 26/29 [00:07<00:00, 3.37it/s]\n 93%|█████████▎| 27/29 [00:08<00:00, 3.37it/s]\n 97%|█████████▋| 28/29 [00:08<00:00, 3.37it/s]\n100%|██████████| 29/29 [00:08<00:00, 3.37it/s]\n100%|██████████| 29/29 [00:08<00:00, 3.34it/s]", "metrics": { "predict_time": 13.407797, "total_time": 13.445301 }, "output": "https://replicate.delivery/pbxt/PRHzwpG72XJ7MpfeFgEQSWxpT9gGRTm66GPPMsWV1hljayRSA/output.png", "started_at": "2024-01-30T22:13:42.929204Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/wgkwsddbkt4bbzw5dnhhshivzy", "cancel": "https://api.replicate.com/v1/predictions/wgkwsddbkt4bbzw5dnhhshivzy/cancel" }, "version": "958d6f0315da9b86f74ca6a67b8cafa1b44b4b6330f0385d956da171ec02e5ef" }
Generated in0%| | 0/29 [00:00<?, ?it/s] 3%|▎ | 1/29 [00:00<00:10, 2.71it/s] 7%|▋ | 2/29 [00:00<00:08, 3.06it/s] 10%|█ | 3/29 [00:00<00:08, 3.19it/s] 14%|█▍ | 4/29 [00:01<00:07, 3.25it/s] 17%|█▋ | 5/29 [00:01<00:07, 3.29it/s] 21%|██ | 6/29 [00:01<00:06, 3.31it/s] 24%|██▍ | 7/29 [00:02<00:06, 3.32it/s] 28%|██▊ | 8/29 [00:02<00:06, 3.33it/s] 31%|███ | 9/29 [00:02<00:05, 3.34it/s] 34%|███▍ | 10/29 [00:03<00:05, 3.34it/s] 38%|███▊ | 11/29 [00:03<00:05, 3.34it/s] 41%|████▏ | 12/29 [00:03<00:05, 3.35it/s] 45%|████▍ | 13/29 [00:03<00:04, 3.35it/s] 48%|████▊ | 14/29 [00:04<00:04, 3.36it/s] 52%|█████▏ | 15/29 [00:04<00:04, 3.36it/s] 55%|█████▌ | 16/29 [00:04<00:03, 3.37it/s] 59%|█████▊ | 17/29 [00:05<00:03, 3.37it/s] 62%|██████▏ | 18/29 [00:05<00:03, 3.37it/s] 66%|██████▌ | 19/29 [00:05<00:02, 3.37it/s] 69%|██████▉ | 20/29 [00:06<00:02, 3.37it/s] 72%|███████▏ | 21/29 [00:06<00:02, 3.37it/s] 76%|███████▌ | 22/29 [00:06<00:02, 3.37it/s] 79%|███████▉ | 23/29 [00:06<00:01, 3.37it/s] 83%|████████▎ | 24/29 [00:07<00:01, 3.37it/s] 86%|████████▌ | 25/29 [00:07<00:01, 3.37it/s] 90%|████████▉ | 26/29 [00:07<00:00, 3.37it/s] 93%|█████████▎| 27/29 [00:08<00:00, 3.37it/s] 97%|█████████▋| 28/29 [00:08<00:00, 3.37it/s] 100%|██████████| 29/29 [00:08<00:00, 3.37it/s] 100%|██████████| 29/29 [00:08<00:00, 3.34it/s]
Want to make some of these yourself?
Run this model