andreasjansson/stable-diffusion-inpainting 🖼️🔢📝✓ → 🖼️
About
Inpainting using RunwayML's stable-diffusion-inpainting checkpoint

Example Output
Prompt:
"a herd of grazing sheep"
Output

Performance Metrics
8.51s
Prediction Time
8.56s
Total Time
All Input Parameters
{ "mask": "https://replicate.delivery/mgxm/188d0097-6a6f-4488-a058-b0b7a66e5677/desktop-mask.png", "image": "https://replicate.delivery/mgxm/f8c9cb3a-8ee8-41a7-9ef6-c65b37acc8af/desktop.png", "prompt": "a herd of grazing sheep", "num_outputs": 1, "guidance_scale": 7.5, "num_inference_steps": 50 }
Input Parameters
- mask (required)
- Black and white image to use as mask. White pixels are inpainted and black pixels are preserved.
- seed
- Random seed. Leave blank to randomize the seed
- image (required)
- Input image to in-paint. Width and height should both be divisible by 8. If they're not, the image will be center cropped to the nearest width and height divisible by 8
- prompt
- Input prompt
- invert_mask
- If this is true, then black pixels are inpainted and white pixels are preserved.
- num_outputs
- Number of images to output. NSFW filter in enabled, so you may get fewer outputs than requested if flagged
- guidance_scale
- Scale for classifier-free guidance
- negative_prompt
- The prompt or prompts not to guide the image generation. Ignored when not using guidance (i.e., ignored if `guidance_scale` is less than `1`).
- num_inference_steps
- Number of denoising steps
Output Schema
Output
Example Execution Logs
Using seed: 42606 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:09, 5.01it/s] 4%|▍ | 2/50 [00:00<00:08, 5.91it/s] 6%|▌ | 3/50 [00:00<00:07, 6.28it/s] 8%|▊ | 4/50 [00:00<00:07, 6.47it/s] 10%|█ | 5/50 [00:00<00:06, 6.58it/s] 12%|█▏ | 6/50 [00:00<00:06, 6.65it/s] 14%|█▍ | 7/50 [00:01<00:06, 6.70it/s] 16%|█▌ | 8/50 [00:01<00:06, 6.73it/s] 18%|█▊ | 9/50 [00:01<00:06, 6.75it/s] 20%|██ | 10/50 [00:01<00:05, 6.76it/s] 22%|██▏ | 11/50 [00:01<00:05, 6.77it/s] 24%|██▍ | 12/50 [00:01<00:05, 6.77it/s] 26%|██▌ | 13/50 [00:01<00:05, 6.78it/s] 28%|██▊ | 14/50 [00:02<00:05, 6.78it/s] 30%|███ | 15/50 [00:02<00:05, 6.78it/s] 32%|███▏ | 16/50 [00:02<00:05, 6.78it/s] 34%|███▍ | 17/50 [00:02<00:04, 6.79it/s] 36%|███▌ | 18/50 [00:02<00:04, 6.79it/s] 38%|███▊ | 19/50 [00:02<00:04, 6.79it/s] 40%|████ | 20/50 [00:02<00:04, 6.79it/s] 42%|████▏ | 21/50 [00:03<00:04, 6.79it/s] 44%|████▍ | 22/50 [00:03<00:04, 6.79it/s] 46%|████▌ | 23/50 [00:03<00:03, 6.79it/s] 48%|████▊ | 24/50 [00:03<00:03, 6.79it/s] 50%|█████ | 25/50 [00:03<00:03, 6.80it/s] 52%|█████▏ | 26/50 [00:03<00:03, 6.79it/s] 54%|█████▍ | 27/50 [00:04<00:03, 6.78it/s] 56%|█████▌ | 28/50 [00:04<00:03, 6.77it/s] 58%|█████▊ | 29/50 [00:04<00:03, 6.77it/s] 60%|██████ | 30/50 [00:04<00:02, 6.77it/s] 62%|██████▏ | 31/50 [00:04<00:02, 6.78it/s] 64%|██████▍ | 32/50 [00:04<00:02, 6.78it/s] 66%|██████▌ | 33/50 [00:04<00:02, 6.78it/s] 68%|██████▊ | 34/50 [00:05<00:02, 6.78it/s] 70%|███████ | 35/50 [00:05<00:02, 6.78it/s] 72%|███████▏ | 36/50 [00:05<00:02, 6.78it/s] 74%|███████▍ | 37/50 [00:05<00:01, 6.78it/s] 76%|███████▌ | 38/50 [00:05<00:01, 6.78it/s] 78%|███████▊ | 39/50 [00:05<00:01, 6.78it/s] 80%|████████ | 40/50 [00:05<00:01, 6.79it/s] 82%|████████▏ | 41/50 [00:06<00:01, 6.79it/s] 84%|████████▍ | 42/50 [00:06<00:01, 6.79it/s] 86%|████████▌ | 43/50 [00:06<00:01, 6.79it/s] 88%|████████▊ | 44/50 [00:06<00:00, 6.78it/s] 90%|█████████ | 45/50 [00:06<00:00, 6.78it/s] 92%|█████████▏| 46/50 [00:06<00:00, 6.78it/s] 94%|█████████▍| 47/50 [00:06<00:00, 6.78it/s] 96%|█████████▌| 48/50 [00:07<00:00, 6.78it/s] 98%|█████████▊| 49/50 [00:07<00:00, 6.77it/s] 100%|██████████| 50/50 [00:07<00:00, 6.77it/s] 100%|██████████| 50/50 [00:07<00:00, 6.73it/s]
Version Details
- Version ID
e490d072a34a94a11e9711ed5a6ba621c3fab884eda1665d9d3a282d65a21180
- Version Created
- January 6, 2023