ℹ️
This model hasn’t been run in 90 days, so we’ve archived it
If you want to run it again, you can restore it from the archive. It’ll take a few minutes to restore.
alexgenovese / bg-remover
Improved background remover 2.0 - GroundingDino + SAM + Inpainting SDXL + Controlnet Canny
- Public
- 205 runs
-
A100 (80GB)
- GitHub
Prediction
alexgenovese/bg-remover:14684746943de5846e0e641b6cd1797e44843bf6537ec5aed0170d3c95345ac1IDolsoo7db466pq47mcitasx25qyStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- image
- prompt
- parfum set on the seaside in a sunny day
- img_size
- 1024, 1024
- apply_img
- scheduler
- DPMSolverMultistep
- product_fill
- Original
- guidance_scale
- 7.5
- condition_scale
- 0.9
- negative_prompt
- low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement
- num_refine_steps
- 10
- num_inference_steps
- 40
{ "image": "https://replicate.delivery/pbxt/KJSWONms3KtWmdboIeMkjM1qnvgT2X4QnRMgT48ug8s7EQDI/20220727_ABOUT_THE_FRAGRANCE_DESK_X1.jpg", "prompt": "parfum set on the seaside in a sunny day", "img_size": "1024, 1024", "apply_img": true, "scheduler": "DPMSolverMultistep", "product_fill": "Original", "guidance_scale": 7.5, "condition_scale": 0.9, "negative_prompt": "low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement", "num_refine_steps": 10, "num_inference_steps": 40 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run alexgenovese/bg-remover using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "alexgenovese/bg-remover:14684746943de5846e0e641b6cd1797e44843bf6537ec5aed0170d3c95345ac1", { input: { image: "https://replicate.delivery/pbxt/KJSWONms3KtWmdboIeMkjM1qnvgT2X4QnRMgT48ug8s7EQDI/20220727_ABOUT_THE_FRAGRANCE_DESK_X1.jpg", prompt: "parfum set on the seaside in a sunny day", img_size: "1024, 1024", apply_img: true, scheduler: "DPMSolverMultistep", product_fill: "Original", guidance_scale: 7.5, condition_scale: 0.9, negative_prompt: "low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement", num_refine_steps: 10, num_inference_steps: 40 } } ); // 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 replicateImport the client:import replicateRun alexgenovese/bg-remover using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "alexgenovese/bg-remover:14684746943de5846e0e641b6cd1797e44843bf6537ec5aed0170d3c95345ac1", input={ "image": "https://replicate.delivery/pbxt/KJSWONms3KtWmdboIeMkjM1qnvgT2X4QnRMgT48ug8s7EQDI/20220727_ABOUT_THE_FRAGRANCE_DESK_X1.jpg", "prompt": "parfum set on the seaside in a sunny day", "img_size": "1024, 1024", "apply_img": True, "scheduler": "DPMSolverMultistep", "product_fill": "Original", "guidance_scale": 7.5, "condition_scale": 0.9, "negative_prompt": "low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement", "num_refine_steps": 10, "num_inference_steps": 40 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run alexgenovese/bg-remover 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": "alexgenovese/bg-remover:14684746943de5846e0e641b6cd1797e44843bf6537ec5aed0170d3c95345ac1", "input": { "image": "https://replicate.delivery/pbxt/KJSWONms3KtWmdboIeMkjM1qnvgT2X4QnRMgT48ug8s7EQDI/20220727_ABOUT_THE_FRAGRANCE_DESK_X1.jpg", "prompt": "parfum set on the seaside in a sunny day", "img_size": "1024, 1024", "apply_img": true, "scheduler": "DPMSolverMultistep", "product_fill": "Original", "guidance_scale": 7.5, "condition_scale": 0.9, "negative_prompt": "low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement", "num_refine_steps": 10, "num_inference_steps": 40 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-01-29T22:01:15.727961Z", "created_at": "2024-01-29T21:57:39.240396Z", "data_removed": false, "error": null, "id": "olsoo7db466pq47mcitasx25qy", "input": { "image": "https://replicate.delivery/pbxt/KJSWONms3KtWmdboIeMkjM1qnvgT2X4QnRMgT48ug8s7EQDI/20220727_ABOUT_THE_FRAGRANCE_DESK_X1.jpg", "prompt": "parfum set on the seaside in a sunny day", "img_size": "1024, 1024", "apply_img": true, "scheduler": "DPMSolverMultistep", "product_fill": "Original", "guidance_scale": 7.5, "condition_scale": 0.9, "negative_prompt": "low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement", "num_refine_steps": 10, "num_inference_steps": 40 }, "logs": "Using seed: 7607\n/root/.pyenv/versions/3.10.13/lib/python3.10/site-packages/torchvision/transforms/functional.py:1603: UserWarning: The default value of the antialias parameter of all the resizing transforms (Resize(), RandomResizedCrop(), etc.) will change from None to True in v0.17, in order to be consistent across the PIL and Tensor backends. To suppress this warning, directly pass antialias=True (recommended, future default), antialias=None (current default, which means False for Tensors and True for PIL), or antialias=False (only works on Tensors - PIL will still use antialiasing). This also applies if you are using the inference transforms from the models weights: update the call to weights.transforms(antialias=True).\nwarnings.warn(\nProduct img W:480, H:632\nScale factor: 1.0\nFinal img W: 1024, H:1024\n 0%| | 0/40 [00:00<?, ?it/s]\n 2%|▎ | 1/40 [00:00<00:12, 3.14it/s]\n 5%|▌ | 2/40 [00:00<00:11, 3.26it/s]\n 8%|▊ | 3/40 [00:00<00:11, 3.30it/s]\n 10%|█ | 4/40 [00:01<00:10, 3.32it/s]\n 12%|█▎ | 5/40 [00:01<00:10, 3.33it/s]\n 15%|█▌ | 6/40 [00:01<00:10, 3.33it/s]\n 18%|█▊ | 7/40 [00:02<00:09, 3.33it/s]\n 20%|██ | 8/40 [00:02<00:09, 3.33it/s]\n 22%|██▎ | 9/40 [00:02<00:09, 3.34it/s]\n 25%|██▌ | 10/40 [00:03<00:08, 3.33it/s]\n 28%|██▊ | 11/40 [00:03<00:08, 3.33it/s]\n 30%|███ | 12/40 [00:03<00:08, 3.33it/s]\n 32%|███▎ | 13/40 [00:03<00:08, 3.33it/s]\n 35%|███▌ | 14/40 [00:04<00:07, 3.33it/s]\n 38%|███▊ | 15/40 [00:04<00:07, 3.33it/s]\n 40%|████ | 16/40 [00:04<00:07, 3.33it/s]\n 42%|████▎ | 17/40 [00:05<00:06, 3.33it/s]\n 45%|████▌ | 18/40 [00:05<00:06, 3.33it/s]\n 48%|████▊ | 19/40 [00:05<00:06, 3.33it/s]\n 50%|█████ | 20/40 [00:06<00:06, 3.33it/s]\n 52%|█████▎ | 21/40 [00:06<00:05, 3.33it/s]\n 55%|█████▌ | 22/40 [00:06<00:05, 3.33it/s]\n 57%|█████▊ | 23/40 [00:06<00:05, 3.33it/s]\n 60%|██████ | 24/40 [00:07<00:04, 3.33it/s]\n 62%|██████▎ | 25/40 [00:07<00:04, 3.33it/s]\n 65%|██████▌ | 26/40 [00:07<00:04, 3.33it/s]\n 68%|██████▊ | 27/40 [00:08<00:03, 3.34it/s]\n 70%|███████ | 28/40 [00:08<00:03, 3.35it/s]\n 72%|███████▎ | 29/40 [00:08<00:03, 3.35it/s]\n 75%|███████▌ | 30/40 [00:09<00:02, 3.35it/s]\n 78%|███████▊ | 31/40 [00:09<00:02, 3.35it/s]\n 80%|████████ | 32/40 [00:09<00:02, 3.35it/s]\n 82%|████████▎ | 33/40 [00:09<00:02, 3.35it/s]\n 85%|████████▌ | 34/40 [00:10<00:01, 3.36it/s]\n 88%|████████▊ | 35/40 [00:10<00:01, 3.36it/s]\n 90%|█████████ | 36/40 [00:10<00:01, 3.36it/s]\n 92%|█████████▎| 37/40 [00:11<00:00, 3.36it/s]\n 95%|█████████▌| 38/40 [00:11<00:00, 3.36it/s]\n 98%|█████████▊| 39/40 [00:11<00:00, 3.36it/s]\n100%|██████████| 40/40 [00:11<00:00, 3.35it/s]\n100%|██████████| 40/40 [00:11<00:00, 3.34it/s]\n 0%| | 0/3 [00:00<?, ?it/s]\n 33%|███▎ | 1/3 [00:00<00:00, 4.18it/s]\n 67%|██████▋ | 2/3 [00:00<00:00, 4.26it/s]\n100%|██████████| 3/3 [00:00<00:00, 4.29it/s]\n100%|██████████| 3/3 [00:00<00:00, 4.27it/s]", "metrics": { "predict_time": 18.77862, "total_time": 216.487565 }, "output": "https://replicate.delivery/pbxt/SloA2p0Z4P4bMNapa3vIDAI6yD8xZtm2iuisldqIftGVkuIJA/8-out.png", "started_at": "2024-01-29T22:00:56.949341Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/olsoo7db466pq47mcitasx25qy", "cancel": "https://api.replicate.com/v1/predictions/olsoo7db466pq47mcitasx25qy/cancel" }, "version": "14684746943de5846e0e641b6cd1797e44843bf6537ec5aed0170d3c95345ac1" }Generated inUsing seed: 7607 /root/.pyenv/versions/3.10.13/lib/python3.10/site-packages/torchvision/transforms/functional.py:1603: UserWarning: The default value of the antialias parameter of all the resizing transforms (Resize(), RandomResizedCrop(), etc.) will change from None to True in v0.17, in order to be consistent across the PIL and Tensor backends. To suppress this warning, directly pass antialias=True (recommended, future default), antialias=None (current default, which means False for Tensors and True for PIL), or antialias=False (only works on Tensors - PIL will still use antialiasing). This also applies if you are using the inference transforms from the models weights: update the call to weights.transforms(antialias=True). warnings.warn( Product img W:480, H:632 Scale factor: 1.0 Final img W: 1024, H:1024 0%| | 0/40 [00:00<?, ?it/s] 2%|▎ | 1/40 [00:00<00:12, 3.14it/s] 5%|▌ | 2/40 [00:00<00:11, 3.26it/s] 8%|▊ | 3/40 [00:00<00:11, 3.30it/s] 10%|█ | 4/40 [00:01<00:10, 3.32it/s] 12%|█▎ | 5/40 [00:01<00:10, 3.33it/s] 15%|█▌ | 6/40 [00:01<00:10, 3.33it/s] 18%|█▊ | 7/40 [00:02<00:09, 3.33it/s] 20%|██ | 8/40 [00:02<00:09, 3.33it/s] 22%|██▎ | 9/40 [00:02<00:09, 3.34it/s] 25%|██▌ | 10/40 [00:03<00:08, 3.33it/s] 28%|██▊ | 11/40 [00:03<00:08, 3.33it/s] 30%|███ | 12/40 [00:03<00:08, 3.33it/s] 32%|███▎ | 13/40 [00:03<00:08, 3.33it/s] 35%|███▌ | 14/40 [00:04<00:07, 3.33it/s] 38%|███▊ | 15/40 [00:04<00:07, 3.33it/s] 40%|████ | 16/40 [00:04<00:07, 3.33it/s] 42%|████▎ | 17/40 [00:05<00:06, 3.33it/s] 45%|████▌ | 18/40 [00:05<00:06, 3.33it/s] 48%|████▊ | 19/40 [00:05<00:06, 3.33it/s] 50%|█████ | 20/40 [00:06<00:06, 3.33it/s] 52%|█████▎ | 21/40 [00:06<00:05, 3.33it/s] 55%|█████▌ | 22/40 [00:06<00:05, 3.33it/s] 57%|█████▊ | 23/40 [00:06<00:05, 3.33it/s] 60%|██████ | 24/40 [00:07<00:04, 3.33it/s] 62%|██████▎ | 25/40 [00:07<00:04, 3.33it/s] 65%|██████▌ | 26/40 [00:07<00:04, 3.33it/s] 68%|██████▊ | 27/40 [00:08<00:03, 3.34it/s] 70%|███████ | 28/40 [00:08<00:03, 3.35it/s] 72%|███████▎ | 29/40 [00:08<00:03, 3.35it/s] 75%|███████▌ | 30/40 [00:09<00:02, 3.35it/s] 78%|███████▊ | 31/40 [00:09<00:02, 3.35it/s] 80%|████████ | 32/40 [00:09<00:02, 3.35it/s] 82%|████████▎ | 33/40 [00:09<00:02, 3.35it/s] 85%|████████▌ | 34/40 [00:10<00:01, 3.36it/s] 88%|████████▊ | 35/40 [00:10<00:01, 3.36it/s] 90%|█████████ | 36/40 [00:10<00:01, 3.36it/s] 92%|█████████▎| 37/40 [00:11<00:00, 3.36it/s] 95%|█████████▌| 38/40 [00:11<00:00, 3.36it/s] 98%|█████████▊| 39/40 [00:11<00:00, 3.36it/s] 100%|██████████| 40/40 [00:11<00:00, 3.35it/s] 100%|██████████| 40/40 [00:11<00:00, 3.34it/s] 0%| | 0/3 [00:00<?, ?it/s] 33%|███▎ | 1/3 [00:00<00:00, 4.18it/s] 67%|██████▋ | 2/3 [00:00<00:00, 4.26it/s] 100%|██████████| 3/3 [00:00<00:00, 4.29it/s] 100%|██████████| 3/3 [00:00<00:00, 4.27it/s]Prediction
alexgenovese/bg-remover:14684746943de5846e0e641b6cd1797e44843bf6537ec5aed0170d3c95345ac1IDac3gajdbjppignpi6qhex22uuaStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- image
- prompt
- bottle set on a wood table in an elegant room
- img_size
- 1024, 1024
- apply_img
- scheduler
- DPMSolverMultistep
- product_fill
- 80
- guidance_scale
- 7.5
- condition_scale
- 0.9
- negative_prompt
- low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement
- num_refine_steps
- 10
- num_inference_steps
- 40
{ "image": "https://replicate.delivery/pbxt/KJRuWwwkexuY6YbPJJsd6cWEhLVwtI6QXQnWDp4VxYyjsCTa/Orangina-bottle.jpg", "prompt": "bottle set on a wood table in an elegant room", "img_size": "1024, 1024", "apply_img": true, "scheduler": "DPMSolverMultistep", "product_fill": "80", "guidance_scale": 7.5, "condition_scale": 0.9, "negative_prompt": "low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement", "num_refine_steps": 10, "num_inference_steps": 40 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run alexgenovese/bg-remover using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "alexgenovese/bg-remover:14684746943de5846e0e641b6cd1797e44843bf6537ec5aed0170d3c95345ac1", { input: { image: "https://replicate.delivery/pbxt/KJRuWwwkexuY6YbPJJsd6cWEhLVwtI6QXQnWDp4VxYyjsCTa/Orangina-bottle.jpg", prompt: "bottle set on a wood table in an elegant room", img_size: "1024, 1024", apply_img: true, scheduler: "DPMSolverMultistep", product_fill: "80", guidance_scale: 7.5, condition_scale: 0.9, negative_prompt: "low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement", num_refine_steps: 10, num_inference_steps: 40 } } ); // 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 replicateImport the client:import replicateRun alexgenovese/bg-remover using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "alexgenovese/bg-remover:14684746943de5846e0e641b6cd1797e44843bf6537ec5aed0170d3c95345ac1", input={ "image": "https://replicate.delivery/pbxt/KJRuWwwkexuY6YbPJJsd6cWEhLVwtI6QXQnWDp4VxYyjsCTa/Orangina-bottle.jpg", "prompt": "bottle set on a wood table in an elegant room", "img_size": "1024, 1024", "apply_img": True, "scheduler": "DPMSolverMultistep", "product_fill": "80", "guidance_scale": 7.5, "condition_scale": 0.9, "negative_prompt": "low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement", "num_refine_steps": 10, "num_inference_steps": 40 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run alexgenovese/bg-remover 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": "alexgenovese/bg-remover:14684746943de5846e0e641b6cd1797e44843bf6537ec5aed0170d3c95345ac1", "input": { "image": "https://replicate.delivery/pbxt/KJRuWwwkexuY6YbPJJsd6cWEhLVwtI6QXQnWDp4VxYyjsCTa/Orangina-bottle.jpg", "prompt": "bottle set on a wood table in an elegant room", "img_size": "1024, 1024", "apply_img": true, "scheduler": "DPMSolverMultistep", "product_fill": "80", "guidance_scale": 7.5, "condition_scale": 0.9, "negative_prompt": "low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement", "num_refine_steps": 10, "num_inference_steps": 40 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-01-29T21:21:15.004050Z", "created_at": "2024-01-29T21:17:41.602850Z", "data_removed": false, "error": null, "id": "ac3gajdbjppignpi6qhex22uua", "input": { "image": "https://replicate.delivery/pbxt/KJRuWwwkexuY6YbPJJsd6cWEhLVwtI6QXQnWDp4VxYyjsCTa/Orangina-bottle.jpg", "prompt": "bottle set on a wood table in an elegant room", "img_size": "1024, 1024", "apply_img": true, "scheduler": "DPMSolverMultistep", "product_fill": "80", "guidance_scale": 7.5, "condition_scale": 0.9, "negative_prompt": "low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement", "num_refine_steps": 10, "num_inference_steps": 40 }, "logs": "Using seed: 49891\n/root/.pyenv/versions/3.10.13/lib/python3.10/site-packages/torchvision/transforms/functional.py:1603: UserWarning: The default value of the antialias parameter of all the resizing transforms (Resize(), RandomResizedCrop(), etc.) will change from None to True in v0.17, in order to be consistent across the PIL and Tensor backends. To suppress this warning, directly pass antialias=True (recommended, future default), antialias=None (current default, which means False for Tensors and True for PIL), or antialias=False (only works on Tensors - PIL will still use antialiasing). This also applies if you are using the inference transforms from the models weights: update the call to weights.transforms(antialias=True).\nwarnings.warn(\nProduct img W:800, H:800\nScale factor: 0.8\nFinal img W: 1024, H:1024\n 0%| | 0/40 [00:00<?, ?it/s]\n 2%|▎ | 1/40 [00:00<00:12, 3.15it/s]\n 5%|▌ | 2/40 [00:00<00:11, 3.27it/s]\n 8%|▊ | 3/40 [00:00<00:11, 3.31it/s]\n 10%|█ | 4/40 [00:01<00:10, 3.33it/s]\n 12%|█▎ | 5/40 [00:01<00:10, 3.34it/s]\n 15%|█▌ | 6/40 [00:01<00:10, 3.35it/s]\n 18%|█▊ | 7/40 [00:02<00:09, 3.35it/s]\n 20%|██ | 8/40 [00:02<00:09, 3.35it/s]\n 22%|██▎ | 9/40 [00:02<00:09, 3.35it/s]\n 25%|██▌ | 10/40 [00:02<00:08, 3.35it/s]\n 28%|██▊ | 11/40 [00:03<00:08, 3.35it/s]\n 30%|███ | 12/40 [00:03<00:08, 3.35it/s]\n 32%|███▎ | 13/40 [00:03<00:08, 3.35it/s]\n 35%|███▌ | 14/40 [00:04<00:07, 3.36it/s]\n 38%|███▊ | 15/40 [00:04<00:07, 3.36it/s]\n 40%|████ | 16/40 [00:04<00:07, 3.37it/s]\n 42%|████▎ | 17/40 [00:05<00:06, 3.37it/s]\n 45%|████▌ | 18/40 [00:05<00:06, 3.37it/s]\n 48%|████▊ | 19/40 [00:05<00:06, 3.37it/s]\n 50%|█████ | 20/40 [00:05<00:05, 3.37it/s]\n 52%|█████▎ | 21/40 [00:06<00:05, 3.37it/s]\n 55%|█████▌ | 22/40 [00:06<00:05, 3.37it/s]\n 57%|█████▊ | 23/40 [00:06<00:05, 3.37it/s]\n 60%|██████ | 24/40 [00:07<00:04, 3.37it/s]\n 62%|██████▎ | 25/40 [00:07<00:04, 3.37it/s]\n 65%|██████▌ | 26/40 [00:07<00:04, 3.37it/s]\n 68%|██████▊ | 27/40 [00:08<00:03, 3.38it/s]\n 70%|███████ | 28/40 [00:08<00:03, 3.37it/s]\n 72%|███████▎ | 29/40 [00:08<00:03, 3.37it/s]\n 75%|███████▌ | 30/40 [00:08<00:02, 3.37it/s]\n 78%|███████▊ | 31/40 [00:09<00:02, 3.37it/s]\n 80%|████████ | 32/40 [00:09<00:02, 3.37it/s]\n 82%|████████▎ | 33/40 [00:09<00:02, 3.37it/s]\n 85%|████████▌ | 34/40 [00:10<00:01, 3.37it/s]\n 88%|████████▊ | 35/40 [00:10<00:01, 3.37it/s]\n 90%|█████████ | 36/40 [00:10<00:01, 3.36it/s]\n 92%|█████████▎| 37/40 [00:11<00:00, 3.37it/s]\n 95%|█████████▌| 38/40 [00:11<00:00, 3.37it/s]\n 98%|█████████▊| 39/40 [00:11<00:00, 3.36it/s]\n100%|██████████| 40/40 [00:11<00:00, 3.36it/s]\n100%|██████████| 40/40 [00:11<00:00, 3.36it/s]\n 0%| | 0/3 [00:00<?, ?it/s]\n 33%|███▎ | 1/3 [00:00<00:00, 4.25it/s]\n 67%|██████▋ | 2/3 [00:00<00:00, 4.31it/s]\n100%|██████████| 3/3 [00:00<00:00, 4.33it/s]\n100%|██████████| 3/3 [00:00<00:00, 4.32it/s]", "metrics": { "predict_time": 19.165976, "total_time": 213.4012 }, "output": "https://replicate.delivery/pbxt/eZRu65n0oXynAqSKGd0t3sdq3qKP2Uab7fWwbNp3wDCKjcRSA/8-out.png", "started_at": "2024-01-29T21:20:55.838074Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/ac3gajdbjppignpi6qhex22uua", "cancel": "https://api.replicate.com/v1/predictions/ac3gajdbjppignpi6qhex22uua/cancel" }, "version": "14684746943de5846e0e641b6cd1797e44843bf6537ec5aed0170d3c95345ac1" }Generated inUsing seed: 49891 /root/.pyenv/versions/3.10.13/lib/python3.10/site-packages/torchvision/transforms/functional.py:1603: UserWarning: The default value of the antialias parameter of all the resizing transforms (Resize(), RandomResizedCrop(), etc.) will change from None to True in v0.17, in order to be consistent across the PIL and Tensor backends. To suppress this warning, directly pass antialias=True (recommended, future default), antialias=None (current default, which means False for Tensors and True for PIL), or antialias=False (only works on Tensors - PIL will still use antialiasing). This also applies if you are using the inference transforms from the models weights: update the call to weights.transforms(antialias=True). warnings.warn( Product img W:800, H:800 Scale factor: 0.8 Final img W: 1024, H:1024 0%| | 0/40 [00:00<?, ?it/s] 2%|▎ | 1/40 [00:00<00:12, 3.15it/s] 5%|▌ | 2/40 [00:00<00:11, 3.27it/s] 8%|▊ | 3/40 [00:00<00:11, 3.31it/s] 10%|█ | 4/40 [00:01<00:10, 3.33it/s] 12%|█▎ | 5/40 [00:01<00:10, 3.34it/s] 15%|█▌ | 6/40 [00:01<00:10, 3.35it/s] 18%|█▊ | 7/40 [00:02<00:09, 3.35it/s] 20%|██ | 8/40 [00:02<00:09, 3.35it/s] 22%|██▎ | 9/40 [00:02<00:09, 3.35it/s] 25%|██▌ | 10/40 [00:02<00:08, 3.35it/s] 28%|██▊ | 11/40 [00:03<00:08, 3.35it/s] 30%|███ | 12/40 [00:03<00:08, 3.35it/s] 32%|███▎ | 13/40 [00:03<00:08, 3.35it/s] 35%|███▌ | 14/40 [00:04<00:07, 3.36it/s] 38%|███▊ | 15/40 [00:04<00:07, 3.36it/s] 40%|████ | 16/40 [00:04<00:07, 3.37it/s] 42%|████▎ | 17/40 [00:05<00:06, 3.37it/s] 45%|████▌ | 18/40 [00:05<00:06, 3.37it/s] 48%|████▊ | 19/40 [00:05<00:06, 3.37it/s] 50%|█████ | 20/40 [00:05<00:05, 3.37it/s] 52%|█████▎ | 21/40 [00:06<00:05, 3.37it/s] 55%|█████▌ | 22/40 [00:06<00:05, 3.37it/s] 57%|█████▊ | 23/40 [00:06<00:05, 3.37it/s] 60%|██████ | 24/40 [00:07<00:04, 3.37it/s] 62%|██████▎ | 25/40 [00:07<00:04, 3.37it/s] 65%|██████▌ | 26/40 [00:07<00:04, 3.37it/s] 68%|██████▊ | 27/40 [00:08<00:03, 3.38it/s] 70%|███████ | 28/40 [00:08<00:03, 3.37it/s] 72%|███████▎ | 29/40 [00:08<00:03, 3.37it/s] 75%|███████▌ | 30/40 [00:08<00:02, 3.37it/s] 78%|███████▊ | 31/40 [00:09<00:02, 3.37it/s] 80%|████████ | 32/40 [00:09<00:02, 3.37it/s] 82%|████████▎ | 33/40 [00:09<00:02, 3.37it/s] 85%|████████▌ | 34/40 [00:10<00:01, 3.37it/s] 88%|████████▊ | 35/40 [00:10<00:01, 3.37it/s] 90%|█████████ | 36/40 [00:10<00:01, 3.36it/s] 92%|█████████▎| 37/40 [00:11<00:00, 3.37it/s] 95%|█████████▌| 38/40 [00:11<00:00, 3.37it/s] 98%|█████████▊| 39/40 [00:11<00:00, 3.36it/s] 100%|██████████| 40/40 [00:11<00:00, 3.36it/s] 100%|██████████| 40/40 [00:11<00:00, 3.36it/s] 0%| | 0/3 [00:00<?, ?it/s] 33%|███▎ | 1/3 [00:00<00:00, 4.25it/s] 67%|██████▋ | 2/3 [00:00<00:00, 4.31it/s] 100%|██████████| 3/3 [00:00<00:00, 4.33it/s] 100%|██████████| 3/3 [00:00<00:00, 4.32it/s]Prediction
alexgenovese/bg-remover:14684746943de5846e0e641b6cd1797e44843bf6537ec5aed0170d3c95345ac1IDitn2t33b3gnjrdduoligzavvmyStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- image
- prompt
- a lamp on a table in a Mountain cabin, sunny day
- img_size
- 1024, 1024
- apply_img
- scheduler
- DDIM
- product_fill
- 70
- guidance_scale
- 7.5
- condition_scale
- 0.7
- negative_prompt
- low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement
- num_refine_steps
- 25
- num_inference_steps
- 35
{ "image": "https://replicate.delivery/pbxt/KJShAcXHbblPtuFERQGz1QMRnolyg9JUC7GZfmtXcSmmoXAV/Lampada-da-montagna-da-comodino-in-legno-vecchio-e-corten-cervo-con-paralume-panna.webp", "prompt": "a lamp on a table in a Mountain cabin, sunny day", "img_size": "1024, 1024", "apply_img": true, "scheduler": "DDIM", "product_fill": "70", "guidance_scale": 7.5, "condition_scale": 0.7, "negative_prompt": "low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement", "num_refine_steps": 25, "num_inference_steps": 35 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run alexgenovese/bg-remover using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "alexgenovese/bg-remover:14684746943de5846e0e641b6cd1797e44843bf6537ec5aed0170d3c95345ac1", { input: { image: "https://replicate.delivery/pbxt/KJShAcXHbblPtuFERQGz1QMRnolyg9JUC7GZfmtXcSmmoXAV/Lampada-da-montagna-da-comodino-in-legno-vecchio-e-corten-cervo-con-paralume-panna.webp", prompt: "a lamp on a table in a Mountain cabin, sunny day", img_size: "1024, 1024", apply_img: true, scheduler: "DDIM", product_fill: "70", guidance_scale: 7.5, condition_scale: 0.7, negative_prompt: "low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement", num_refine_steps: 25, num_inference_steps: 35 } } ); // 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 replicateImport the client:import replicateRun alexgenovese/bg-remover using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "alexgenovese/bg-remover:14684746943de5846e0e641b6cd1797e44843bf6537ec5aed0170d3c95345ac1", input={ "image": "https://replicate.delivery/pbxt/KJShAcXHbblPtuFERQGz1QMRnolyg9JUC7GZfmtXcSmmoXAV/Lampada-da-montagna-da-comodino-in-legno-vecchio-e-corten-cervo-con-paralume-panna.webp", "prompt": "a lamp on a table in a Mountain cabin, sunny day", "img_size": "1024, 1024", "apply_img": True, "scheduler": "DDIM", "product_fill": "70", "guidance_scale": 7.5, "condition_scale": 0.7, "negative_prompt": "low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement", "num_refine_steps": 25, "num_inference_steps": 35 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run alexgenovese/bg-remover 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": "alexgenovese/bg-remover:14684746943de5846e0e641b6cd1797e44843bf6537ec5aed0170d3c95345ac1", "input": { "image": "https://replicate.delivery/pbxt/KJShAcXHbblPtuFERQGz1QMRnolyg9JUC7GZfmtXcSmmoXAV/Lampada-da-montagna-da-comodino-in-legno-vecchio-e-corten-cervo-con-paralume-panna.webp", "prompt": "a lamp on a table in a Mountain cabin, sunny day", "img_size": "1024, 1024", "apply_img": true, "scheduler": "DDIM", "product_fill": "70", "guidance_scale": 7.5, "condition_scale": 0.7, "negative_prompt": "low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement", "num_refine_steps": 25, "num_inference_steps": 35 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-01-29T22:10:58.245147Z", "created_at": "2024-01-29T22:09:01.734899Z", "data_removed": false, "error": null, "id": "itn2t33b3gnjrdduoligzavvmy", "input": { "image": "https://replicate.delivery/pbxt/KJShAcXHbblPtuFERQGz1QMRnolyg9JUC7GZfmtXcSmmoXAV/Lampada-da-montagna-da-comodino-in-legno-vecchio-e-corten-cervo-con-paralume-panna.webp", "prompt": "a lamp on a table in a Mountain cabin, sunny day", "img_size": "1024, 1024", "apply_img": true, "scheduler": "DDIM", "product_fill": "70", "guidance_scale": 7.5, "condition_scale": 0.7, "negative_prompt": "low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement", "num_refine_steps": 25, "num_inference_steps": 35 }, "logs": "Using seed: 27309\nProduct img W:2048, H:2048\nScale factor: 0.7\nFinal img W: 1024, H:1024\n 0%| | 0/35 [00:00<?, ?it/s]\n 3%|▎ | 1/35 [00:00<00:10, 3.39it/s]\n 6%|▌ | 2/35 [00:00<00:09, 3.39it/s]\n 9%|▊ | 3/35 [00:00<00:09, 3.39it/s]\n 11%|█▏ | 4/35 [00:01<00:09, 3.38it/s]\n 14%|█▍ | 5/35 [00:01<00:08, 3.38it/s]\n 17%|█▋ | 6/35 [00:01<00:08, 3.38it/s]\n 20%|██ | 7/35 [00:02<00:08, 3.38it/s]\n 23%|██▎ | 8/35 [00:02<00:07, 3.38it/s]\n 26%|██▌ | 9/35 [00:02<00:07, 3.38it/s]\n 29%|██▊ | 10/35 [00:02<00:07, 3.38it/s]\n 31%|███▏ | 11/35 [00:03<00:07, 3.37it/s]\n 34%|███▍ | 12/35 [00:03<00:06, 3.37it/s]\n 37%|███▋ | 13/35 [00:03<00:06, 3.37it/s]\n 40%|████ | 14/35 [00:04<00:06, 3.37it/s]\n 43%|████▎ | 15/35 [00:04<00:05, 3.37it/s]\n 46%|████▌ | 16/35 [00:04<00:05, 3.36it/s]\n 49%|████▊ | 17/35 [00:05<00:05, 3.36it/s]\n 51%|█████▏ | 18/35 [00:05<00:05, 3.36it/s]\n 54%|█████▍ | 19/35 [00:05<00:04, 3.36it/s]\n 57%|█████▋ | 20/35 [00:05<00:04, 3.36it/s]\n 60%|██████ | 21/35 [00:06<00:04, 3.36it/s]\n 63%|██████▎ | 22/35 [00:06<00:03, 3.36it/s]\n 66%|██████▌ | 23/35 [00:06<00:03, 3.36it/s]\n 69%|██████▊ | 24/35 [00:07<00:03, 3.36it/s]\n 71%|███████▏ | 25/35 [00:07<00:02, 3.36it/s]\n 74%|███████▍ | 26/35 [00:07<00:02, 3.35it/s]\n 77%|███████▋ | 27/35 [00:08<00:02, 3.35it/s]\n 80%|████████ | 28/35 [00:08<00:02, 3.35it/s]\n 83%|████████▎ | 29/35 [00:08<00:01, 3.35it/s]\n 86%|████████▌ | 30/35 [00:08<00:01, 3.35it/s]\n 89%|████████▊ | 31/35 [00:09<00:01, 3.35it/s]\n 91%|█████████▏| 32/35 [00:09<00:00, 3.35it/s]\n 94%|█████████▍| 33/35 [00:09<00:00, 3.34it/s]\n 97%|█████████▋| 34/35 [00:10<00:00, 3.33it/s]\n100%|██████████| 35/35 [00:10<00:00, 3.34it/s]\n100%|██████████| 35/35 [00:10<00:00, 3.36it/s]\n 0%| | 0/7 [00:00<?, ?it/s]\n 14%|█▍ | 1/7 [00:00<00:01, 4.35it/s]\n 29%|██▊ | 2/7 [00:00<00:01, 4.33it/s]\n 43%|████▎ | 3/7 [00:00<00:00, 4.33it/s]\n 57%|█████▋ | 4/7 [00:00<00:00, 4.31it/s]\n 71%|███████▏ | 5/7 [00:01<00:00, 4.31it/s]\n 86%|████████▌ | 6/7 [00:01<00:00, 4.31it/s]\n100%|██████████| 7/7 [00:01<00:00, 4.31it/s]\n100%|██████████| 7/7 [00:01<00:00, 4.32it/s]", "metrics": { "predict_time": 19.968368, "total_time": 116.510248 }, "output": "https://replicate.delivery/pbxt/NbuGBereOqjP9U2OKcuVk9nbhFANJHqg1BOF91wFFPIxRdRSA/8-out.png", "started_at": "2024-01-29T22:10:38.276779Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/itn2t33b3gnjrdduoligzavvmy", "cancel": "https://api.replicate.com/v1/predictions/itn2t33b3gnjrdduoligzavvmy/cancel" }, "version": "14684746943de5846e0e641b6cd1797e44843bf6537ec5aed0170d3c95345ac1" }Generated inUsing seed: 27309 Product img W:2048, H:2048 Scale factor: 0.7 Final img W: 1024, H:1024 0%| | 0/35 [00:00<?, ?it/s] 3%|▎ | 1/35 [00:00<00:10, 3.39it/s] 6%|▌ | 2/35 [00:00<00:09, 3.39it/s] 9%|▊ | 3/35 [00:00<00:09, 3.39it/s] 11%|█▏ | 4/35 [00:01<00:09, 3.38it/s] 14%|█▍ | 5/35 [00:01<00:08, 3.38it/s] 17%|█▋ | 6/35 [00:01<00:08, 3.38it/s] 20%|██ | 7/35 [00:02<00:08, 3.38it/s] 23%|██▎ | 8/35 [00:02<00:07, 3.38it/s] 26%|██▌ | 9/35 [00:02<00:07, 3.38it/s] 29%|██▊ | 10/35 [00:02<00:07, 3.38it/s] 31%|███▏ | 11/35 [00:03<00:07, 3.37it/s] 34%|███▍ | 12/35 [00:03<00:06, 3.37it/s] 37%|███▋ | 13/35 [00:03<00:06, 3.37it/s] 40%|████ | 14/35 [00:04<00:06, 3.37it/s] 43%|████▎ | 15/35 [00:04<00:05, 3.37it/s] 46%|████▌ | 16/35 [00:04<00:05, 3.36it/s] 49%|████▊ | 17/35 [00:05<00:05, 3.36it/s] 51%|█████▏ | 18/35 [00:05<00:05, 3.36it/s] 54%|█████▍ | 19/35 [00:05<00:04, 3.36it/s] 57%|█████▋ | 20/35 [00:05<00:04, 3.36it/s] 60%|██████ | 21/35 [00:06<00:04, 3.36it/s] 63%|██████▎ | 22/35 [00:06<00:03, 3.36it/s] 66%|██████▌ | 23/35 [00:06<00:03, 3.36it/s] 69%|██████▊ | 24/35 [00:07<00:03, 3.36it/s] 71%|███████▏ | 25/35 [00:07<00:02, 3.36it/s] 74%|███████▍ | 26/35 [00:07<00:02, 3.35it/s] 77%|███████▋ | 27/35 [00:08<00:02, 3.35it/s] 80%|████████ | 28/35 [00:08<00:02, 3.35it/s] 83%|████████▎ | 29/35 [00:08<00:01, 3.35it/s] 86%|████████▌ | 30/35 [00:08<00:01, 3.35it/s] 89%|████████▊ | 31/35 [00:09<00:01, 3.35it/s] 91%|█████████▏| 32/35 [00:09<00:00, 3.35it/s] 94%|█████████▍| 33/35 [00:09<00:00, 3.34it/s] 97%|█████████▋| 34/35 [00:10<00:00, 3.33it/s] 100%|██████████| 35/35 [00:10<00:00, 3.34it/s] 100%|██████████| 35/35 [00:10<00:00, 3.36it/s] 0%| | 0/7 [00:00<?, ?it/s] 14%|█▍ | 1/7 [00:00<00:01, 4.35it/s] 29%|██▊ | 2/7 [00:00<00:01, 4.33it/s] 43%|████▎ | 3/7 [00:00<00:00, 4.33it/s] 57%|█████▋ | 4/7 [00:00<00:00, 4.31it/s] 71%|███████▏ | 5/7 [00:01<00:00, 4.31it/s] 86%|████████▌ | 6/7 [00:01<00:00, 4.31it/s] 100%|██████████| 7/7 [00:01<00:00, 4.31it/s] 100%|██████████| 7/7 [00:01<00:00, 4.32it/s]Prediction
alexgenovese/bg-remover:14684746943de5846e0e641b6cd1797e44843bf6537ec5aed0170d3c95345ac1IDelall2tbqwjqynacy7ce2av6eyStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- image
- prompt
- a lamp on a table in a modern living room, a cloudy day
- img_size
- 1024, 1024
- apply_img
- scheduler
- DPMSolverMultistep
- product_fill
- 70
- guidance_scale
- 7.5
- condition_scale
- 0.9
- negative_prompt
- low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement
- num_refine_steps
- 10
- num_inference_steps
- 40
{ "image": "https://replicate.delivery/pbxt/KJSfJ2zOic9r1MIsV8MbCL0YWN4UOa93GWmjfwJl6Hb955Re/2efdfccdeeeb42c765d75ab2a60c5f32.webp", "prompt": "a lamp on a table in a modern living room, a cloudy day", "img_size": "1024, 1024", "apply_img": true, "scheduler": "DPMSolverMultistep", "product_fill": "70", "guidance_scale": 7.5, "condition_scale": 0.9, "negative_prompt": "low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement", "num_refine_steps": 10, "num_inference_steps": 40 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run alexgenovese/bg-remover using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "alexgenovese/bg-remover:14684746943de5846e0e641b6cd1797e44843bf6537ec5aed0170d3c95345ac1", { input: { image: "https://replicate.delivery/pbxt/KJSfJ2zOic9r1MIsV8MbCL0YWN4UOa93GWmjfwJl6Hb955Re/2efdfccdeeeb42c765d75ab2a60c5f32.webp", prompt: "a lamp on a table in a modern living room, a cloudy day", img_size: "1024, 1024", apply_img: true, scheduler: "DPMSolverMultistep", product_fill: "70", guidance_scale: 7.5, condition_scale: 0.9, negative_prompt: "low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement", num_refine_steps: 10, num_inference_steps: 40 } } ); // 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 replicateImport the client:import replicateRun alexgenovese/bg-remover using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "alexgenovese/bg-remover:14684746943de5846e0e641b6cd1797e44843bf6537ec5aed0170d3c95345ac1", input={ "image": "https://replicate.delivery/pbxt/KJSfJ2zOic9r1MIsV8MbCL0YWN4UOa93GWmjfwJl6Hb955Re/2efdfccdeeeb42c765d75ab2a60c5f32.webp", "prompt": "a lamp on a table in a modern living room, a cloudy day", "img_size": "1024, 1024", "apply_img": True, "scheduler": "DPMSolverMultistep", "product_fill": "70", "guidance_scale": 7.5, "condition_scale": 0.9, "negative_prompt": "low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement", "num_refine_steps": 10, "num_inference_steps": 40 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run alexgenovese/bg-remover 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": "alexgenovese/bg-remover:14684746943de5846e0e641b6cd1797e44843bf6537ec5aed0170d3c95345ac1", "input": { "image": "https://replicate.delivery/pbxt/KJSfJ2zOic9r1MIsV8MbCL0YWN4UOa93GWmjfwJl6Hb955Re/2efdfccdeeeb42c765d75ab2a60c5f32.webp", "prompt": "a lamp on a table in a modern living room, a cloudy day", "img_size": "1024, 1024", "apply_img": true, "scheduler": "DPMSolverMultistep", "product_fill": "70", "guidance_scale": 7.5, "condition_scale": 0.9, "negative_prompt": "low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement", "num_refine_steps": 10, "num_inference_steps": 40 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-01-29T22:10:37.801197Z", "created_at": "2024-01-29T22:07:04.077544Z", "data_removed": false, "error": null, "id": "elall2tbqwjqynacy7ce2av6ey", "input": { "image": "https://replicate.delivery/pbxt/KJSfJ2zOic9r1MIsV8MbCL0YWN4UOa93GWmjfwJl6Hb955Re/2efdfccdeeeb42c765d75ab2a60c5f32.webp", "prompt": "a lamp on a table in a modern living room, a cloudy day", "img_size": "1024, 1024", "apply_img": true, "scheduler": "DPMSolverMultistep", "product_fill": "70", "guidance_scale": 7.5, "condition_scale": 0.9, "negative_prompt": "low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement", "num_refine_steps": 10, "num_inference_steps": 40 }, "logs": "Using seed: 53181\n/root/.pyenv/versions/3.10.13/lib/python3.10/site-packages/torchvision/transforms/functional.py:1603: UserWarning: The default value of the antialias parameter of all the resizing transforms (Resize(), RandomResizedCrop(), etc.) will change from None to True in v0.17, in order to be consistent across the PIL and Tensor backends. To suppress this warning, directly pass antialias=True (recommended, future default), antialias=None (current default, which means False for Tensors and True for PIL), or antialias=False (only works on Tensors - PIL will still use antialiasing). This also applies if you are using the inference transforms from the models weights: update the call to weights.transforms(antialias=True).\nwarnings.warn(\nProduct img W:1000, H:1000\nScale factor: 0.7\nFinal img W: 1024, H:1024\n 0%| | 0/40 [00:00<?, ?it/s]\n 2%|▎ | 1/40 [00:00<00:12, 3.14it/s]\n 5%|▌ | 2/40 [00:00<00:11, 3.28it/s]\n 8%|▊ | 3/40 [00:00<00:11, 3.32it/s]\n 10%|█ | 4/40 [00:01<00:10, 3.34it/s]\n 12%|█▎ | 5/40 [00:01<00:10, 3.32it/s]\n 15%|█▌ | 6/40 [00:01<00:10, 3.34it/s]\n 18%|█▊ | 7/40 [00:02<00:09, 3.35it/s]\n 20%|██ | 8/40 [00:02<00:09, 3.35it/s]\n 22%|██▎ | 9/40 [00:02<00:09, 3.36it/s]\n 25%|██▌ | 10/40 [00:02<00:08, 3.36it/s]\n 28%|██▊ | 11/40 [00:03<00:08, 3.36it/s]\n 30%|███ | 12/40 [00:03<00:08, 3.36it/s]\n 32%|███▎ | 13/40 [00:03<00:08, 3.36it/s]\n 35%|███▌ | 14/40 [00:04<00:07, 3.36it/s]\n 38%|███▊ | 15/40 [00:04<00:07, 3.36it/s]\n 40%|████ | 16/40 [00:04<00:07, 3.36it/s]\n 42%|████▎ | 17/40 [00:05<00:06, 3.37it/s]\n 45%|████▌ | 18/40 [00:05<00:06, 3.38it/s]\n 48%|████▊ | 19/40 [00:05<00:06, 3.38it/s]\n 50%|█████ | 20/40 [00:05<00:05, 3.38it/s]\n 52%|█████▎ | 21/40 [00:06<00:05, 3.38it/s]\n 55%|█████▌ | 22/40 [00:06<00:05, 3.39it/s]\n 57%|█████▊ | 23/40 [00:06<00:05, 3.39it/s]\n 60%|██████ | 24/40 [00:07<00:04, 3.39it/s]\n 62%|██████▎ | 25/40 [00:07<00:04, 3.38it/s]\n 65%|██████▌ | 26/40 [00:07<00:04, 3.39it/s]\n 68%|██████▊ | 27/40 [00:08<00:03, 3.39it/s]\n 70%|███████ | 28/40 [00:08<00:03, 3.38it/s]\n 72%|███████▎ | 29/40 [00:08<00:03, 3.38it/s]\n 75%|███████▌ | 30/40 [00:08<00:02, 3.38it/s]\n 78%|███████▊ | 31/40 [00:09<00:02, 3.38it/s]\n 80%|████████ | 32/40 [00:09<00:02, 3.38it/s]\n 82%|████████▎ | 33/40 [00:09<00:02, 3.38it/s]\n 85%|████████▌ | 34/40 [00:10<00:01, 3.38it/s]\n 88%|████████▊ | 35/40 [00:10<00:01, 3.38it/s]\n 90%|█████████ | 36/40 [00:10<00:01, 3.38it/s]\n 92%|█████████▎| 37/40 [00:10<00:00, 3.38it/s]\n 95%|█████████▌| 38/40 [00:11<00:00, 3.38it/s]\n 98%|█████████▊| 39/40 [00:11<00:00, 3.38it/s]\n100%|██████████| 40/40 [00:11<00:00, 3.38it/s]\n100%|██████████| 40/40 [00:11<00:00, 3.37it/s]\n 0%| | 0/3 [00:00<?, ?it/s]\n 33%|███▎ | 1/3 [00:00<00:00, 4.25it/s]\n 67%|██████▋ | 2/3 [00:00<00:00, 4.31it/s]\n100%|██████████| 3/3 [00:00<00:00, 4.33it/s]\n100%|██████████| 3/3 [00:00<00:00, 4.32it/s]", "metrics": { "predict_time": 19.693867, "total_time": 213.723653 }, "output": "https://replicate.delivery/pbxt/2txBeewEvWkZB0G3AtomDhT0pw3Fef2BjHEjJ3g7RHywF1FJB/8-out.png", "started_at": "2024-01-29T22:10:18.107330Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/elall2tbqwjqynacy7ce2av6ey", "cancel": "https://api.replicate.com/v1/predictions/elall2tbqwjqynacy7ce2av6ey/cancel" }, "version": "14684746943de5846e0e641b6cd1797e44843bf6537ec5aed0170d3c95345ac1" }Generated inUsing seed: 53181 /root/.pyenv/versions/3.10.13/lib/python3.10/site-packages/torchvision/transforms/functional.py:1603: UserWarning: The default value of the antialias parameter of all the resizing transforms (Resize(), RandomResizedCrop(), etc.) will change from None to True in v0.17, in order to be consistent across the PIL and Tensor backends. To suppress this warning, directly pass antialias=True (recommended, future default), antialias=None (current default, which means False for Tensors and True for PIL), or antialias=False (only works on Tensors - PIL will still use antialiasing). This also applies if you are using the inference transforms from the models weights: update the call to weights.transforms(antialias=True). warnings.warn( Product img W:1000, H:1000 Scale factor: 0.7 Final img W: 1024, H:1024 0%| | 0/40 [00:00<?, ?it/s] 2%|▎ | 1/40 [00:00<00:12, 3.14it/s] 5%|▌ | 2/40 [00:00<00:11, 3.28it/s] 8%|▊ | 3/40 [00:00<00:11, 3.32it/s] 10%|█ | 4/40 [00:01<00:10, 3.34it/s] 12%|█▎ | 5/40 [00:01<00:10, 3.32it/s] 15%|█▌ | 6/40 [00:01<00:10, 3.34it/s] 18%|█▊ | 7/40 [00:02<00:09, 3.35it/s] 20%|██ | 8/40 [00:02<00:09, 3.35it/s] 22%|██▎ | 9/40 [00:02<00:09, 3.36it/s] 25%|██▌ | 10/40 [00:02<00:08, 3.36it/s] 28%|██▊ | 11/40 [00:03<00:08, 3.36it/s] 30%|███ | 12/40 [00:03<00:08, 3.36it/s] 32%|███▎ | 13/40 [00:03<00:08, 3.36it/s] 35%|███▌ | 14/40 [00:04<00:07, 3.36it/s] 38%|███▊ | 15/40 [00:04<00:07, 3.36it/s] 40%|████ | 16/40 [00:04<00:07, 3.36it/s] 42%|████▎ | 17/40 [00:05<00:06, 3.37it/s] 45%|████▌ | 18/40 [00:05<00:06, 3.38it/s] 48%|████▊ | 19/40 [00:05<00:06, 3.38it/s] 50%|█████ | 20/40 [00:05<00:05, 3.38it/s] 52%|█████▎ | 21/40 [00:06<00:05, 3.38it/s] 55%|█████▌ | 22/40 [00:06<00:05, 3.39it/s] 57%|█████▊ | 23/40 [00:06<00:05, 3.39it/s] 60%|██████ | 24/40 [00:07<00:04, 3.39it/s] 62%|██████▎ | 25/40 [00:07<00:04, 3.38it/s] 65%|██████▌ | 26/40 [00:07<00:04, 3.39it/s] 68%|██████▊ | 27/40 [00:08<00:03, 3.39it/s] 70%|███████ | 28/40 [00:08<00:03, 3.38it/s] 72%|███████▎ | 29/40 [00:08<00:03, 3.38it/s] 75%|███████▌ | 30/40 [00:08<00:02, 3.38it/s] 78%|███████▊ | 31/40 [00:09<00:02, 3.38it/s] 80%|████████ | 32/40 [00:09<00:02, 3.38it/s] 82%|████████▎ | 33/40 [00:09<00:02, 3.38it/s] 85%|████████▌ | 34/40 [00:10<00:01, 3.38it/s] 88%|████████▊ | 35/40 [00:10<00:01, 3.38it/s] 90%|█████████ | 36/40 [00:10<00:01, 3.38it/s] 92%|█████████▎| 37/40 [00:10<00:00, 3.38it/s] 95%|█████████▌| 38/40 [00:11<00:00, 3.38it/s] 98%|█████████▊| 39/40 [00:11<00:00, 3.38it/s] 100%|██████████| 40/40 [00:11<00:00, 3.38it/s] 100%|██████████| 40/40 [00:11<00:00, 3.37it/s] 0%| | 0/3 [00:00<?, ?it/s] 33%|███▎ | 1/3 [00:00<00:00, 4.25it/s] 67%|██████▋ | 2/3 [00:00<00:00, 4.31it/s] 100%|██████████| 3/3 [00:00<00:00, 4.33it/s] 100%|██████████| 3/3 [00:00<00:00, 4.32it/s]Prediction
alexgenovese/bg-remover:14684746943de5846e0e641b6cd1797e44843bf6537ec5aed0170d3c95345ac1IDhnkqaslbqnwaaeg623gw5ckh5yStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- image
- prompt
- a sofa in a elegant room hotel, sunny day
- img_size
- 1024, 1024
- apply_img
- scheduler
- DDIM
- product_fill
- 70
- guidance_scale
- 7.5
- condition_scale
- 0.7
- negative_prompt
- low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement
- num_refine_steps
- 25
- num_inference_steps
- 35
{ "image": "https://replicate.delivery/pbxt/KJSmxhoLhprmpshUk4uDYvhX1aXgZWE9DvAY8h5JQMXp0Em4/divani-letto-con-penisola-strip-outlet-diotti-com-in-offerta-40_n1_1365490.webp", "prompt": "a sofa in a elegant room hotel, sunny day", "img_size": "1024, 1024", "apply_img": true, "scheduler": "DDIM", "product_fill": "70", "guidance_scale": 7.5, "condition_scale": 0.7, "negative_prompt": "low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement", "num_refine_steps": 25, "num_inference_steps": 35 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run alexgenovese/bg-remover using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "alexgenovese/bg-remover:14684746943de5846e0e641b6cd1797e44843bf6537ec5aed0170d3c95345ac1", { input: { image: "https://replicate.delivery/pbxt/KJSmxhoLhprmpshUk4uDYvhX1aXgZWE9DvAY8h5JQMXp0Em4/divani-letto-con-penisola-strip-outlet-diotti-com-in-offerta-40_n1_1365490.webp", prompt: "a sofa in a elegant room hotel, sunny day", img_size: "1024, 1024", apply_img: true, scheduler: "DDIM", product_fill: "70", guidance_scale: 7.5, condition_scale: 0.7, negative_prompt: "low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement", num_refine_steps: 25, num_inference_steps: 35 } } ); // 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 replicateImport the client:import replicateRun alexgenovese/bg-remover using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "alexgenovese/bg-remover:14684746943de5846e0e641b6cd1797e44843bf6537ec5aed0170d3c95345ac1", input={ "image": "https://replicate.delivery/pbxt/KJSmxhoLhprmpshUk4uDYvhX1aXgZWE9DvAY8h5JQMXp0Em4/divani-letto-con-penisola-strip-outlet-diotti-com-in-offerta-40_n1_1365490.webp", "prompt": "a sofa in a elegant room hotel, sunny day", "img_size": "1024, 1024", "apply_img": True, "scheduler": "DDIM", "product_fill": "70", "guidance_scale": 7.5, "condition_scale": 0.7, "negative_prompt": "low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement", "num_refine_steps": 25, "num_inference_steps": 35 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run alexgenovese/bg-remover 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": "alexgenovese/bg-remover:14684746943de5846e0e641b6cd1797e44843bf6537ec5aed0170d3c95345ac1", "input": { "image": "https://replicate.delivery/pbxt/KJSmxhoLhprmpshUk4uDYvhX1aXgZWE9DvAY8h5JQMXp0Em4/divani-letto-con-penisola-strip-outlet-diotti-com-in-offerta-40_n1_1365490.webp", "prompt": "a sofa in a elegant room hotel, sunny day", "img_size": "1024, 1024", "apply_img": true, "scheduler": "DDIM", "product_fill": "70", "guidance_scale": 7.5, "condition_scale": 0.7, "negative_prompt": "low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement", "num_refine_steps": 25, "num_inference_steps": 35 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-01-29T22:18:17.768192Z", "created_at": "2024-01-29T22:15:08.211424Z", "data_removed": false, "error": null, "id": "hnkqaslbqnwaaeg623gw5ckh5y", "input": { "image": "https://replicate.delivery/pbxt/KJSmxhoLhprmpshUk4uDYvhX1aXgZWE9DvAY8h5JQMXp0Em4/divani-letto-con-penisola-strip-outlet-diotti-com-in-offerta-40_n1_1365490.webp", "prompt": "a sofa in a elegant room hotel, sunny day", "img_size": "1024, 1024", "apply_img": true, "scheduler": "DDIM", "product_fill": "70", "guidance_scale": 7.5, "condition_scale": 0.7, "negative_prompt": "low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement", "num_refine_steps": 25, "num_inference_steps": 35 }, "logs": "Using seed: 6807\n/root/.pyenv/versions/3.10.13/lib/python3.10/site-packages/torchvision/transforms/functional.py:1603: UserWarning: The default value of the antialias parameter of all the resizing transforms (Resize(), RandomResizedCrop(), etc.) will change from None to True in v0.17, in order to be consistent across the PIL and Tensor backends. To suppress this warning, directly pass antialias=True (recommended, future default), antialias=None (current default, which means False for Tensors and True for PIL), or antialias=False (only works on Tensors - PIL will still use antialiasing). This also applies if you are using the inference transforms from the models weights: update the call to weights.transforms(antialias=True).\nwarnings.warn(\nProduct img W:796, H:597\nScale factor: 0.7\nFinal img W: 1024, H:1024\n 0%| | 0/35 [00:00<?, ?it/s]\n 3%|▎ | 1/35 [00:00<00:10, 3.15it/s]\n 6%|▌ | 2/35 [00:00<00:10, 3.25it/s]\n 9%|▊ | 3/35 [00:00<00:09, 3.31it/s]\n 11%|█▏ | 4/35 [00:01<00:09, 3.35it/s]\n 14%|█▍ | 5/35 [00:01<00:08, 3.36it/s]\n 17%|█▋ | 6/35 [00:01<00:08, 3.37it/s]\n 20%|██ | 7/35 [00:02<00:08, 3.38it/s]\n 23%|██▎ | 8/35 [00:02<00:07, 3.38it/s]\n 26%|██▌ | 9/35 [00:02<00:07, 3.38it/s]\n 29%|██▊ | 10/35 [00:02<00:07, 3.39it/s]\n 31%|███▏ | 11/35 [00:03<00:07, 3.39it/s]\n 34%|███▍ | 12/35 [00:03<00:06, 3.39it/s]\n 37%|███▋ | 13/35 [00:03<00:06, 3.39it/s]\n 40%|████ | 14/35 [00:04<00:06, 3.39it/s]\n 43%|████▎ | 15/35 [00:04<00:05, 3.40it/s]\n 46%|████▌ | 16/35 [00:04<00:05, 3.39it/s]\n 49%|████▊ | 17/35 [00:05<00:05, 3.39it/s]\n 51%|█████▏ | 18/35 [00:05<00:05, 3.39it/s]\n 54%|█████▍ | 19/35 [00:05<00:04, 3.39it/s]\n 57%|█████▋ | 20/35 [00:05<00:04, 3.39it/s]\n 60%|██████ | 21/35 [00:06<00:04, 3.39it/s]\n 63%|██████▎ | 22/35 [00:06<00:03, 3.38it/s]\n 66%|██████▌ | 23/35 [00:06<00:03, 3.38it/s]\n 69%|██████▊ | 24/35 [00:07<00:03, 3.38it/s]\n 71%|███████▏ | 25/35 [00:07<00:02, 3.38it/s]\n 74%|███████▍ | 26/35 [00:07<00:02, 3.38it/s]\n 77%|███████▋ | 27/35 [00:07<00:02, 3.38it/s]\n 80%|████████ | 28/35 [00:08<00:02, 3.38it/s]\n 83%|████████▎ | 29/35 [00:08<00:01, 3.38it/s]\n 86%|████████▌ | 30/35 [00:08<00:01, 3.37it/s]\n 89%|████████▊ | 31/35 [00:09<00:01, 3.38it/s]\n 91%|█████████▏| 32/35 [00:09<00:00, 3.37it/s]\n 94%|█████████▍| 33/35 [00:09<00:00, 3.37it/s]\n 97%|█████████▋| 34/35 [00:10<00:00, 3.37it/s]\n100%|██████████| 35/35 [00:10<00:00, 3.37it/s]\n100%|██████████| 35/35 [00:10<00:00, 3.38it/s]\n 0%| | 0/7 [00:00<?, ?it/s]\n 14%|█▍ | 1/7 [00:00<00:01, 4.21it/s]\n 29%|██▊ | 2/7 [00:00<00:01, 4.29it/s]\n 43%|████▎ | 3/7 [00:00<00:00, 4.31it/s]\n 57%|█████▋ | 4/7 [00:00<00:00, 4.32it/s]\n 71%|███████▏ | 5/7 [00:01<00:00, 4.33it/s]\n 86%|████████▌ | 6/7 [00:01<00:00, 4.33it/s]\n100%|██████████| 7/7 [00:01<00:00, 4.33it/s]\n100%|██████████| 7/7 [00:01<00:00, 4.32it/s]", "metrics": { "predict_time": 19.125157, "total_time": 189.556768 }, "output": "https://replicate.delivery/pbxt/pwe6DWpVG2wzfkjQ19y3UNyVLVDyQgpYnbEfYTpjSqtTx6ikA/8-out.png", "started_at": "2024-01-29T22:17:58.643035Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/hnkqaslbqnwaaeg623gw5ckh5y", "cancel": "https://api.replicate.com/v1/predictions/hnkqaslbqnwaaeg623gw5ckh5y/cancel" }, "version": "14684746943de5846e0e641b6cd1797e44843bf6537ec5aed0170d3c95345ac1" }Generated inUsing seed: 6807 /root/.pyenv/versions/3.10.13/lib/python3.10/site-packages/torchvision/transforms/functional.py:1603: UserWarning: The default value of the antialias parameter of all the resizing transforms (Resize(), RandomResizedCrop(), etc.) will change from None to True in v0.17, in order to be consistent across the PIL and Tensor backends. To suppress this warning, directly pass antialias=True (recommended, future default), antialias=None (current default, which means False for Tensors and True for PIL), or antialias=False (only works on Tensors - PIL will still use antialiasing). This also applies if you are using the inference transforms from the models weights: update the call to weights.transforms(antialias=True). warnings.warn( Product img W:796, H:597 Scale factor: 0.7 Final img W: 1024, H:1024 0%| | 0/35 [00:00<?, ?it/s] 3%|▎ | 1/35 [00:00<00:10, 3.15it/s] 6%|▌ | 2/35 [00:00<00:10, 3.25it/s] 9%|▊ | 3/35 [00:00<00:09, 3.31it/s] 11%|█▏ | 4/35 [00:01<00:09, 3.35it/s] 14%|█▍ | 5/35 [00:01<00:08, 3.36it/s] 17%|█▋ | 6/35 [00:01<00:08, 3.37it/s] 20%|██ | 7/35 [00:02<00:08, 3.38it/s] 23%|██▎ | 8/35 [00:02<00:07, 3.38it/s] 26%|██▌ | 9/35 [00:02<00:07, 3.38it/s] 29%|██▊ | 10/35 [00:02<00:07, 3.39it/s] 31%|███▏ | 11/35 [00:03<00:07, 3.39it/s] 34%|███▍ | 12/35 [00:03<00:06, 3.39it/s] 37%|███▋ | 13/35 [00:03<00:06, 3.39it/s] 40%|████ | 14/35 [00:04<00:06, 3.39it/s] 43%|████▎ | 15/35 [00:04<00:05, 3.40it/s] 46%|████▌ | 16/35 [00:04<00:05, 3.39it/s] 49%|████▊ | 17/35 [00:05<00:05, 3.39it/s] 51%|█████▏ | 18/35 [00:05<00:05, 3.39it/s] 54%|█████▍ | 19/35 [00:05<00:04, 3.39it/s] 57%|█████▋ | 20/35 [00:05<00:04, 3.39it/s] 60%|██████ | 21/35 [00:06<00:04, 3.39it/s] 63%|██████▎ | 22/35 [00:06<00:03, 3.38it/s] 66%|██████▌ | 23/35 [00:06<00:03, 3.38it/s] 69%|██████▊ | 24/35 [00:07<00:03, 3.38it/s] 71%|███████▏ | 25/35 [00:07<00:02, 3.38it/s] 74%|███████▍ | 26/35 [00:07<00:02, 3.38it/s] 77%|███████▋ | 27/35 [00:07<00:02, 3.38it/s] 80%|████████ | 28/35 [00:08<00:02, 3.38it/s] 83%|████████▎ | 29/35 [00:08<00:01, 3.38it/s] 86%|████████▌ | 30/35 [00:08<00:01, 3.37it/s] 89%|████████▊ | 31/35 [00:09<00:01, 3.38it/s] 91%|█████████▏| 32/35 [00:09<00:00, 3.37it/s] 94%|█████████▍| 33/35 [00:09<00:00, 3.37it/s] 97%|█████████▋| 34/35 [00:10<00:00, 3.37it/s] 100%|██████████| 35/35 [00:10<00:00, 3.37it/s] 100%|██████████| 35/35 [00:10<00:00, 3.38it/s] 0%| | 0/7 [00:00<?, ?it/s] 14%|█▍ | 1/7 [00:00<00:01, 4.21it/s] 29%|██▊ | 2/7 [00:00<00:01, 4.29it/s] 43%|████▎ | 3/7 [00:00<00:00, 4.31it/s] 57%|█████▋ | 4/7 [00:00<00:00, 4.32it/s] 71%|███████▏ | 5/7 [00:01<00:00, 4.33it/s] 86%|████████▌ | 6/7 [00:01<00:00, 4.33it/s] 100%|██████████| 7/7 [00:01<00:00, 4.33it/s] 100%|██████████| 7/7 [00:01<00:00, 4.32it/s]Prediction
alexgenovese/bg-remover:14684746943de5846e0e641b6cd1797e44843bf6537ec5aed0170d3c95345ac1IDcm4x26tbubz7z3jduqjsi3uyxyStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- image
- prompt
- a bag set on a table, background party, nightlife, 8k
- img_size
- 1024, 1024
- apply_img
- scheduler
- DPMSolverMultistep
- product_fill
- 70
- guidance_scale
- 7.5
- condition_scale
- 0.9
- negative_prompt
- low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement
- num_refine_steps
- 10
- num_inference_steps
- 40
{ "image": "https://replicate.delivery/pbxt/KJSxwZmnxItVYLXVWZZeBHmB3hhTbF3ezxeXOwNHL8Jgzd7O/borsa-a-mano-elegante-nera.webp", "prompt": "a bag set on a table, background party, nightlife, 8k", "img_size": "1024, 1024", "apply_img": true, "scheduler": "DPMSolverMultistep", "product_fill": "70", "guidance_scale": 7.5, "condition_scale": 0.9, "negative_prompt": "low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement", "num_refine_steps": 10, "num_inference_steps": 40 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run alexgenovese/bg-remover using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "alexgenovese/bg-remover:14684746943de5846e0e641b6cd1797e44843bf6537ec5aed0170d3c95345ac1", { input: { image: "https://replicate.delivery/pbxt/KJSxwZmnxItVYLXVWZZeBHmB3hhTbF3ezxeXOwNHL8Jgzd7O/borsa-a-mano-elegante-nera.webp", prompt: "a bag set on a table, background party, nightlife, 8k", img_size: "1024, 1024", apply_img: true, scheduler: "DPMSolverMultistep", product_fill: "70", guidance_scale: 7.5, condition_scale: 0.9, negative_prompt: "low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement", num_refine_steps: 10, num_inference_steps: 40 } } ); // 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 replicateImport the client:import replicateRun alexgenovese/bg-remover using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "alexgenovese/bg-remover:14684746943de5846e0e641b6cd1797e44843bf6537ec5aed0170d3c95345ac1", input={ "image": "https://replicate.delivery/pbxt/KJSxwZmnxItVYLXVWZZeBHmB3hhTbF3ezxeXOwNHL8Jgzd7O/borsa-a-mano-elegante-nera.webp", "prompt": "a bag set on a table, background party, nightlife, 8k", "img_size": "1024, 1024", "apply_img": True, "scheduler": "DPMSolverMultistep", "product_fill": "70", "guidance_scale": 7.5, "condition_scale": 0.9, "negative_prompt": "low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement", "num_refine_steps": 10, "num_inference_steps": 40 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run alexgenovese/bg-remover 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": "alexgenovese/bg-remover:14684746943de5846e0e641b6cd1797e44843bf6537ec5aed0170d3c95345ac1", "input": { "image": "https://replicate.delivery/pbxt/KJSxwZmnxItVYLXVWZZeBHmB3hhTbF3ezxeXOwNHL8Jgzd7O/borsa-a-mano-elegante-nera.webp", "prompt": "a bag set on a table, background party, nightlife, 8k", "img_size": "1024, 1024", "apply_img": true, "scheduler": "DPMSolverMultistep", "product_fill": "70", "guidance_scale": 7.5, "condition_scale": 0.9, "negative_prompt": "low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement", "num_refine_steps": 10, "num_inference_steps": 40 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-01-29T22:29:07.653642Z", "created_at": "2024-01-29T22:26:43.363173Z", "data_removed": false, "error": null, "id": "cm4x26tbubz7z3jduqjsi3uyxy", "input": { "image": "https://replicate.delivery/pbxt/KJSxwZmnxItVYLXVWZZeBHmB3hhTbF3ezxeXOwNHL8Jgzd7O/borsa-a-mano-elegante-nera.webp", "prompt": "a bag set on a table, background party, nightlife, 8k", "img_size": "1024, 1024", "apply_img": true, "scheduler": "DPMSolverMultistep", "product_fill": "70", "guidance_scale": 7.5, "condition_scale": 0.9, "negative_prompt": "low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement", "num_refine_steps": 10, "num_inference_steps": 40 }, "logs": "Using seed: 15607\nProduct img W:1800, H:1799\nScale factor: 0.7\nFinal img W: 1024, H:1024\n 0%| | 0/40 [00:00<?, ?it/s]\n 2%|▎ | 1/40 [00:00<00:11, 3.38it/s]\n 5%|▌ | 2/40 [00:00<00:11, 3.38it/s]\n 8%|▊ | 3/40 [00:00<00:10, 3.38it/s]\n 10%|█ | 4/40 [00:01<00:10, 3.37it/s]\n 12%|█▎ | 5/40 [00:01<00:10, 3.37it/s]\n 15%|█▌ | 6/40 [00:01<00:10, 3.37it/s]\n 18%|█▊ | 7/40 [00:02<00:09, 3.37it/s]\n 20%|██ | 8/40 [00:02<00:09, 3.37it/s]\n 22%|██▎ | 9/40 [00:02<00:09, 3.37it/s]\n 25%|██▌ | 10/40 [00:02<00:08, 3.37it/s]\n 28%|██▊ | 11/40 [00:03<00:08, 3.36it/s]\n 30%|███ | 12/40 [00:03<00:08, 3.36it/s]\n 32%|███▎ | 13/40 [00:03<00:08, 3.36it/s]\n 35%|███▌ | 14/40 [00:04<00:07, 3.36it/s]\n 38%|███▊ | 15/40 [00:04<00:07, 3.36it/s]\n 40%|████ | 16/40 [00:04<00:07, 3.35it/s]\n 42%|████▎ | 17/40 [00:05<00:06, 3.36it/s]\n 45%|████▌ | 18/40 [00:05<00:06, 3.36it/s]\n 48%|████▊ | 19/40 [00:05<00:06, 3.36it/s]\n 50%|█████ | 20/40 [00:05<00:05, 3.36it/s]\n 52%|█████▎ | 21/40 [00:06<00:05, 3.36it/s]\n 55%|█████▌ | 22/40 [00:06<00:05, 3.35it/s]\n 57%|█████▊ | 23/40 [00:06<00:05, 3.35it/s]\n 60%|██████ | 24/40 [00:07<00:04, 3.35it/s]\n 62%|██████▎ | 25/40 [00:07<00:04, 3.35it/s]\n 65%|██████▌ | 26/40 [00:07<00:04, 3.35it/s]\n 68%|██████▊ | 27/40 [00:08<00:03, 3.35it/s]\n 70%|███████ | 28/40 [00:08<00:03, 3.35it/s]\n 72%|███████▎ | 29/40 [00:08<00:03, 3.35it/s]\n 75%|███████▌ | 30/40 [00:08<00:02, 3.36it/s]\n 78%|███████▊ | 31/40 [00:09<00:02, 3.36it/s]\n 80%|████████ | 32/40 [00:09<00:02, 3.35it/s]\n 82%|████████▎ | 33/40 [00:09<00:02, 3.35it/s]\n 85%|████████▌ | 34/40 [00:10<00:01, 3.35it/s]\n 88%|████████▊ | 35/40 [00:10<00:01, 3.35it/s]\n 90%|█████████ | 36/40 [00:10<00:01, 3.35it/s]\n 92%|█████████▎| 37/40 [00:11<00:00, 3.35it/s]\n 95%|█████████▌| 38/40 [00:11<00:00, 3.35it/s]\n 98%|█████████▊| 39/40 [00:11<00:00, 3.35it/s]\n100%|██████████| 40/40 [00:11<00:00, 3.34it/s]\n100%|██████████| 40/40 [00:11<00:00, 3.36it/s]\n 0%| | 0/3 [00:00<?, ?it/s]\n 33%|███▎ | 1/3 [00:00<00:00, 4.33it/s]\n 67%|██████▋ | 2/3 [00:00<00:00, 4.33it/s]\n100%|██████████| 3/3 [00:00<00:00, 4.32it/s]\n100%|██████████| 3/3 [00:00<00:00, 4.32it/s]", "metrics": { "predict_time": 19.822352, "total_time": 144.290469 }, "output": "https://replicate.delivery/pbxt/rmXspliFjL5HKhe7JiPc1RHSeuns94ReOnh80UbjmM9kF7ikA/8-out.png", "started_at": "2024-01-29T22:28:47.831290Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/cm4x26tbubz7z3jduqjsi3uyxy", "cancel": "https://api.replicate.com/v1/predictions/cm4x26tbubz7z3jduqjsi3uyxy/cancel" }, "version": "14684746943de5846e0e641b6cd1797e44843bf6537ec5aed0170d3c95345ac1" }Generated inUsing seed: 15607 Product img W:1800, H:1799 Scale factor: 0.7 Final img W: 1024, H:1024 0%| | 0/40 [00:00<?, ?it/s] 2%|▎ | 1/40 [00:00<00:11, 3.38it/s] 5%|▌ | 2/40 [00:00<00:11, 3.38it/s] 8%|▊ | 3/40 [00:00<00:10, 3.38it/s] 10%|█ | 4/40 [00:01<00:10, 3.37it/s] 12%|█▎ | 5/40 [00:01<00:10, 3.37it/s] 15%|█▌ | 6/40 [00:01<00:10, 3.37it/s] 18%|█▊ | 7/40 [00:02<00:09, 3.37it/s] 20%|██ | 8/40 [00:02<00:09, 3.37it/s] 22%|██▎ | 9/40 [00:02<00:09, 3.37it/s] 25%|██▌ | 10/40 [00:02<00:08, 3.37it/s] 28%|██▊ | 11/40 [00:03<00:08, 3.36it/s] 30%|███ | 12/40 [00:03<00:08, 3.36it/s] 32%|███▎ | 13/40 [00:03<00:08, 3.36it/s] 35%|███▌ | 14/40 [00:04<00:07, 3.36it/s] 38%|███▊ | 15/40 [00:04<00:07, 3.36it/s] 40%|████ | 16/40 [00:04<00:07, 3.35it/s] 42%|████▎ | 17/40 [00:05<00:06, 3.36it/s] 45%|████▌ | 18/40 [00:05<00:06, 3.36it/s] 48%|████▊ | 19/40 [00:05<00:06, 3.36it/s] 50%|█████ | 20/40 [00:05<00:05, 3.36it/s] 52%|█████▎ | 21/40 [00:06<00:05, 3.36it/s] 55%|█████▌ | 22/40 [00:06<00:05, 3.35it/s] 57%|█████▊ | 23/40 [00:06<00:05, 3.35it/s] 60%|██████ | 24/40 [00:07<00:04, 3.35it/s] 62%|██████▎ | 25/40 [00:07<00:04, 3.35it/s] 65%|██████▌ | 26/40 [00:07<00:04, 3.35it/s] 68%|██████▊ | 27/40 [00:08<00:03, 3.35it/s] 70%|███████ | 28/40 [00:08<00:03, 3.35it/s] 72%|███████▎ | 29/40 [00:08<00:03, 3.35it/s] 75%|███████▌ | 30/40 [00:08<00:02, 3.36it/s] 78%|███████▊ | 31/40 [00:09<00:02, 3.36it/s] 80%|████████ | 32/40 [00:09<00:02, 3.35it/s] 82%|████████▎ | 33/40 [00:09<00:02, 3.35it/s] 85%|████████▌ | 34/40 [00:10<00:01, 3.35it/s] 88%|████████▊ | 35/40 [00:10<00:01, 3.35it/s] 90%|█████████ | 36/40 [00:10<00:01, 3.35it/s] 92%|█████████▎| 37/40 [00:11<00:00, 3.35it/s] 95%|█████████▌| 38/40 [00:11<00:00, 3.35it/s] 98%|█████████▊| 39/40 [00:11<00:00, 3.35it/s] 100%|██████████| 40/40 [00:11<00:00, 3.34it/s] 100%|██████████| 40/40 [00:11<00:00, 3.36it/s] 0%| | 0/3 [00:00<?, ?it/s] 33%|███▎ | 1/3 [00:00<00:00, 4.33it/s] 67%|██████▋ | 2/3 [00:00<00:00, 4.33it/s] 100%|██████████| 3/3 [00:00<00:00, 4.32it/s] 100%|██████████| 3/3 [00:00<00:00, 4.32it/s]Prediction
alexgenovese/bg-remover:14684746943de5846e0e641b6cd1797e44843bf6537ec5aed0170d3c95345ac1IDanekfrlbbebwh7cvmrfbmwslceStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- image
- prompt
- a bag on a little sofa in a luxury retail
- img_size
- 1024, 1024
- apply_img
- scheduler
- DPMSolverMultistep
- product_fill
- 40
- guidance_scale
- 7.5
- condition_scale
- 0.9
- negative_prompt
- low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement
- num_refine_steps
- 10
- num_inference_steps
- 40
{ "image": "https://replicate.delivery/pbxt/KJSzqfNTVeHIsEyY6uezdfN2gy4Vcy9A5GaVRpEChRw9OOEX/zaino-furrr-sharks-in-paris-dlxv.jpg", "prompt": "a bag on a little sofa in a luxury retail", "img_size": "1024, 1024", "apply_img": true, "scheduler": "DPMSolverMultistep", "product_fill": "40", "guidance_scale": 7.5, "condition_scale": 0.9, "negative_prompt": "low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement", "num_refine_steps": 10, "num_inference_steps": 40 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run alexgenovese/bg-remover using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "alexgenovese/bg-remover:14684746943de5846e0e641b6cd1797e44843bf6537ec5aed0170d3c95345ac1", { input: { image: "https://replicate.delivery/pbxt/KJSzqfNTVeHIsEyY6uezdfN2gy4Vcy9A5GaVRpEChRw9OOEX/zaino-furrr-sharks-in-paris-dlxv.jpg", prompt: "a bag on a little sofa in a luxury retail", img_size: "1024, 1024", apply_img: true, scheduler: "DPMSolverMultistep", product_fill: "40", guidance_scale: 7.5, condition_scale: 0.9, negative_prompt: "low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement", num_refine_steps: 10, num_inference_steps: 40 } } ); // 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 replicateImport the client:import replicateRun alexgenovese/bg-remover using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "alexgenovese/bg-remover:14684746943de5846e0e641b6cd1797e44843bf6537ec5aed0170d3c95345ac1", input={ "image": "https://replicate.delivery/pbxt/KJSzqfNTVeHIsEyY6uezdfN2gy4Vcy9A5GaVRpEChRw9OOEX/zaino-furrr-sharks-in-paris-dlxv.jpg", "prompt": "a bag on a little sofa in a luxury retail", "img_size": "1024, 1024", "apply_img": True, "scheduler": "DPMSolverMultistep", "product_fill": "40", "guidance_scale": 7.5, "condition_scale": 0.9, "negative_prompt": "low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement", "num_refine_steps": 10, "num_inference_steps": 40 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run alexgenovese/bg-remover 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": "alexgenovese/bg-remover:14684746943de5846e0e641b6cd1797e44843bf6537ec5aed0170d3c95345ac1", "input": { "image": "https://replicate.delivery/pbxt/KJSzqfNTVeHIsEyY6uezdfN2gy4Vcy9A5GaVRpEChRw9OOEX/zaino-furrr-sharks-in-paris-dlxv.jpg", "prompt": "a bag on a little sofa in a luxury retail", "img_size": "1024, 1024", "apply_img": true, "scheduler": "DPMSolverMultistep", "product_fill": "40", "guidance_scale": 7.5, "condition_scale": 0.9, "negative_prompt": "low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement", "num_refine_steps": 10, "num_inference_steps": 40 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-01-29T22:29:44.918001Z", "created_at": "2024-01-29T22:28:44.858940Z", "data_removed": false, "error": null, "id": "anekfrlbbebwh7cvmrfbmwslce", "input": { "image": "https://replicate.delivery/pbxt/KJSzqfNTVeHIsEyY6uezdfN2gy4Vcy9A5GaVRpEChRw9OOEX/zaino-furrr-sharks-in-paris-dlxv.jpg", "prompt": "a bag on a little sofa in a luxury retail", "img_size": "1024, 1024", "apply_img": true, "scheduler": "DPMSolverMultistep", "product_fill": "40", "guidance_scale": 7.5, "condition_scale": 0.9, "negative_prompt": "low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement", "num_refine_steps": 10, "num_inference_steps": 40 }, "logs": "Using seed: 42197\nProduct img W:1000, H:1300\nScale factor: 0.4\nFinal img W: 1024, H:1024\n 0%| | 0/40 [00:00<?, ?it/s]\n 2%|▎ | 1/40 [00:00<00:11, 3.38it/s]\n 5%|▌ | 2/40 [00:00<00:11, 3.37it/s]\n 8%|▊ | 3/40 [00:00<00:11, 3.36it/s]\n 10%|█ | 4/40 [00:01<00:10, 3.35it/s]\n 12%|█▎ | 5/40 [00:01<00:10, 3.35it/s]\n 15%|█▌ | 6/40 [00:01<00:10, 3.35it/s]\n 18%|█▊ | 7/40 [00:02<00:09, 3.35it/s]\n 20%|██ | 8/40 [00:02<00:09, 3.34it/s]\n 22%|██▎ | 9/40 [00:02<00:09, 3.34it/s]\n 25%|██▌ | 10/40 [00:02<00:08, 3.34it/s]\n 28%|██▊ | 11/40 [00:03<00:08, 3.34it/s]\n 30%|███ | 12/40 [00:03<00:08, 3.34it/s]\n 32%|███▎ | 13/40 [00:03<00:08, 3.34it/s]\n 35%|███▌ | 14/40 [00:04<00:07, 3.33it/s]\n 38%|███▊ | 15/40 [00:04<00:07, 3.33it/s]\n 40%|████ | 16/40 [00:04<00:07, 3.33it/s]\n 42%|████▎ | 17/40 [00:05<00:06, 3.33it/s]\n 45%|████▌ | 18/40 [00:05<00:06, 3.33it/s]\n 48%|████▊ | 19/40 [00:05<00:06, 3.34it/s]\n 50%|█████ | 20/40 [00:05<00:05, 3.34it/s]\n 52%|█████▎ | 21/40 [00:06<00:05, 3.34it/s]\n 55%|█████▌ | 22/40 [00:06<00:05, 3.34it/s]\n 57%|█████▊ | 23/40 [00:06<00:05, 3.34it/s]\n 60%|██████ | 24/40 [00:07<00:04, 3.34it/s]\n 62%|██████▎ | 25/40 [00:07<00:04, 3.34it/s]\n 65%|██████▌ | 26/40 [00:07<00:04, 3.34it/s]\n 68%|██████▊ | 27/40 [00:08<00:03, 3.33it/s]\n 70%|███████ | 28/40 [00:08<00:03, 3.33it/s]\n 72%|███████▎ | 29/40 [00:08<00:03, 3.33it/s]\n 75%|███████▌ | 30/40 [00:08<00:02, 3.33it/s]\n 78%|███████▊ | 31/40 [00:09<00:02, 3.33it/s]\n 80%|████████ | 32/40 [00:09<00:02, 3.34it/s]\n 82%|████████▎ | 33/40 [00:09<00:02, 3.33it/s]\n 85%|████████▌ | 34/40 [00:10<00:01, 3.33it/s]\n 88%|████████▊ | 35/40 [00:10<00:01, 3.34it/s]\n 90%|█████████ | 36/40 [00:10<00:01, 3.34it/s]\n 92%|█████████▎| 37/40 [00:11<00:00, 3.33it/s]\n 95%|█████████▌| 38/40 [00:11<00:00, 3.33it/s]\n 98%|█████████▊| 39/40 [00:11<00:00, 3.31it/s]\n100%|██████████| 40/40 [00:11<00:00, 3.31it/s]\n100%|██████████| 40/40 [00:11<00:00, 3.33it/s]\n 0%| | 0/3 [00:00<?, ?it/s]\n 33%|███▎ | 1/3 [00:00<00:00, 4.30it/s]\n 67%|██████▋ | 2/3 [00:00<00:00, 4.30it/s]\n100%|██████████| 3/3 [00:00<00:00, 4.30it/s]\n100%|██████████| 3/3 [00:00<00:00, 4.30it/s]", "metrics": { "predict_time": 18.585888, "total_time": 60.059061 }, "output": "https://replicate.delivery/pbxt/r1pogO9uHipgMpvzZman7jffqoWLlmGQfnaWA3eqolHiN2FJB/8-out.png", "started_at": "2024-01-29T22:29:26.332113Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/anekfrlbbebwh7cvmrfbmwslce", "cancel": "https://api.replicate.com/v1/predictions/anekfrlbbebwh7cvmrfbmwslce/cancel" }, "version": "14684746943de5846e0e641b6cd1797e44843bf6537ec5aed0170d3c95345ac1" }Generated inUsing seed: 42197 Product img W:1000, H:1300 Scale factor: 0.4 Final img W: 1024, H:1024 0%| | 0/40 [00:00<?, ?it/s] 2%|▎ | 1/40 [00:00<00:11, 3.38it/s] 5%|▌ | 2/40 [00:00<00:11, 3.37it/s] 8%|▊ | 3/40 [00:00<00:11, 3.36it/s] 10%|█ | 4/40 [00:01<00:10, 3.35it/s] 12%|█▎ | 5/40 [00:01<00:10, 3.35it/s] 15%|█▌ | 6/40 [00:01<00:10, 3.35it/s] 18%|█▊ | 7/40 [00:02<00:09, 3.35it/s] 20%|██ | 8/40 [00:02<00:09, 3.34it/s] 22%|██▎ | 9/40 [00:02<00:09, 3.34it/s] 25%|██▌ | 10/40 [00:02<00:08, 3.34it/s] 28%|██▊ | 11/40 [00:03<00:08, 3.34it/s] 30%|███ | 12/40 [00:03<00:08, 3.34it/s] 32%|███▎ | 13/40 [00:03<00:08, 3.34it/s] 35%|███▌ | 14/40 [00:04<00:07, 3.33it/s] 38%|███▊ | 15/40 [00:04<00:07, 3.33it/s] 40%|████ | 16/40 [00:04<00:07, 3.33it/s] 42%|████▎ | 17/40 [00:05<00:06, 3.33it/s] 45%|████▌ | 18/40 [00:05<00:06, 3.33it/s] 48%|████▊ | 19/40 [00:05<00:06, 3.34it/s] 50%|█████ | 20/40 [00:05<00:05, 3.34it/s] 52%|█████▎ | 21/40 [00:06<00:05, 3.34it/s] 55%|█████▌ | 22/40 [00:06<00:05, 3.34it/s] 57%|█████▊ | 23/40 [00:06<00:05, 3.34it/s] 60%|██████ | 24/40 [00:07<00:04, 3.34it/s] 62%|██████▎ | 25/40 [00:07<00:04, 3.34it/s] 65%|██████▌ | 26/40 [00:07<00:04, 3.34it/s] 68%|██████▊ | 27/40 [00:08<00:03, 3.33it/s] 70%|███████ | 28/40 [00:08<00:03, 3.33it/s] 72%|███████▎ | 29/40 [00:08<00:03, 3.33it/s] 75%|███████▌ | 30/40 [00:08<00:02, 3.33it/s] 78%|███████▊ | 31/40 [00:09<00:02, 3.33it/s] 80%|████████ | 32/40 [00:09<00:02, 3.34it/s] 82%|████████▎ | 33/40 [00:09<00:02, 3.33it/s] 85%|████████▌ | 34/40 [00:10<00:01, 3.33it/s] 88%|████████▊ | 35/40 [00:10<00:01, 3.34it/s] 90%|█████████ | 36/40 [00:10<00:01, 3.34it/s] 92%|█████████▎| 37/40 [00:11<00:00, 3.33it/s] 95%|█████████▌| 38/40 [00:11<00:00, 3.33it/s] 98%|█████████▊| 39/40 [00:11<00:00, 3.31it/s] 100%|██████████| 40/40 [00:11<00:00, 3.31it/s] 100%|██████████| 40/40 [00:11<00:00, 3.33it/s] 0%| | 0/3 [00:00<?, ?it/s] 33%|███▎ | 1/3 [00:00<00:00, 4.30it/s] 67%|██████▋ | 2/3 [00:00<00:00, 4.30it/s] 100%|██████████| 3/3 [00:00<00:00, 4.30it/s] 100%|██████████| 3/3 [00:00<00:00, 4.30it/s]
Want to make some of these yourself?
Run this model
