alexgenovese/bg-remover 🔢🖼️📝❓✓ → 🖼️

▶️ 205 runs 📅 Oct 2023 ⚙️ Cog 0.8.6 🔗 GitHub

background-removal image-editing product-photography

About

Improved background remover 2.0 - GroundingDino + SAM + Inpainting SDXL + Controlnet Canny

Example Output

Prompt:

"parfum set on the seaside in a sunny day"

Output

Performance Metrics

18.78s Prediction Time

216.49s Total Time

All Input Parameters

{
  "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
}

Input Parameters

seed Type: integer: Empty or 0 for a random image
image (required) Type: string: Remove background from this image
prompt (required) Type: string: Describe the new setting for your product
img_size Default: 1024, 1024: Possible SDXL image sizes
apply_img Type: booleanDefault: true: Applies the original product image to the final result
scheduler Default: K_EULER: scheduler
product_fill Default: Original: What percentage of the image width to fill with product
guidance_scale Type: numberDefault: 7.5: Guidance Scale
condition_scale Type: numberDefault: 0.9Range: 0.3 - 0.9: controlnet conditioning scale for generalization
negative_prompt Type: stringDefault: low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement: Describe what you do not want in your setting
num_refine_steps Type: integerDefault: 10Range: 0 - 40: Number of steps to refine
num_inference_steps Type: integerDefault: 40: Inference Steps

Output Schema

Output

Type: string • Format: uri

Example Execution Logs

Using 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]

Version Details

Version ID: 9107c8209fb0cae7797c50cf58a2dae725632e71ac1a766435f21d4a6beb4464
Version Created: January 13, 2024

Run on Replicate →