andreasjansson/stable-diffusion-wip 🖼️🔢❓📝 → 🖼️

▶️ 13.4K runs 📅 Aug 2022 ⚙️ Cog 0.4.2

image-inpainting image-to-image

About

(development branch) Inpainting for Stable Diffusion

Example Output

Prompt:

"angry godzilla"

Output

Performance Metrics

7.74s Prediction Time

7.95s Total Time

All Input Parameters

{
  "mask": "https://replicate.delivery/mgxm/dc5488e0-d589-480b-825f-c02596700731/nyc-mask.png",
  "width": 512,
  "height": 512,
  "prompt": "angry godzilla",
  "init_image": "https://replicate.delivery/mgxm/d8f4574e-5c9a-4291-88ac-4eb53095f8d9/nyc-4854718_1280.png",
  "num_outputs": "1",
  "guidance_scale": 7.5,
  "prompt_strength": 0.7,
  "num_inference_steps": "100"
}

Input Parameters

mask Type: string: Black and white image to use as mask for inpainting over init_image. Black pixels are inpainted and white pixels are preserved. Experimental feature, tends to work better with prompt strength of 0.5-0.7
seed Type: integer: Random seed. Leave blank to randomize the seed
width Default: 512: Width of output image
height Default: 512: Height of output image
prompt Type: stringDefault:: Input prompt
init_image Type: string: Inital image to generate variations of. Will be resized to the specified width and height
num_outputs Default: 1: Number of images to output
guidance_scale Type: numberDefault: 7.5Range: 1 - 20: Scale for classifier-free guidance
prompt_strength Type: numberDefault: 0.8: Prompt strength when using init image. 1.0 corresponds to full destruction of information in init image
num_inference_steps Type: integerDefault: 50Range: 1 - 500: Number of denoising steps

Output Schema

Output

Type: array • Items Type: string • Items Format: uri

Example Execution Logs

Using seed: 7913

0it [00:00, ?it/s]
1it [00:00,  9.70it/s]
3it [00:00, 11.43it/s]
5it [00:00, 11.63it/s]
7it [00:00, 11.74it/s]
9it [00:00, 12.19it/s]
11it [00:00, 12.42it/s]
13it [00:01, 12.46it/s]
15it [00:01, 12.71it/s]
17it [00:01, 12.79it/s]
19it [00:01, 12.43it/s]
21it [00:01, 12.03it/s]
23it [00:01, 12.17it/s]
25it [00:02, 12.17it/s]
27it [00:02, 12.34it/s]
29it [00:02, 12.41it/s]
31it [00:02, 12.58it/s]
33it [00:02, 12.28it/s]
35it [00:02, 12.09it/s]
37it [00:03, 12.08it/s]
39it [00:03, 12.16it/s]
41it [00:03, 11.80it/s]
43it [00:03, 11.78it/s]
45it [00:03, 12.09it/s]
47it [00:03, 12.46it/s]
49it [00:04, 12.67it/s]
51it [00:04, 12.24it/s]
53it [00:04, 12.01it/s]
55it [00:04, 11.80it/s]
57it [00:04, 11.93it/s]
59it [00:04, 11.81it/s]
61it [00:05, 11.77it/s]
63it [00:05, 11.70it/s]
65it [00:05, 11.96it/s]
67it [00:05, 11.72it/s]
69it [00:05, 11.95it/s]
71it [00:05, 12.40it/s]
73it [00:06, 12.20it/s]
75it [00:06, 11.99it/s]
77it [00:06, 11.79it/s]
79it [00:06, 11.72it/s]
79it [00:06, 12.07it/s]

Version Details

Version ID: 5c17c98e8b490e89dc2d799ad4c6a45f580a8e0d7a2af80e5162dfff1ced6aea
Version Created: August 26, 2022

Run on Replicate →