tstramer/material-diffusion 🖼️🔢❓📝 → 🖼️

▶️ 2.3M runs 📅 Nov 2022 ⚙️ Cog 0.4.4

About

Stable diffusion fork for generating tileable outputs using v1.5 model

Example Output

Prompt:

"Mossy Runic Bricks seamless texture, trending on artstation, stone, moss, base color, albedo, 4k"

Output

Performance Metrics

9.27s Prediction Time

254.16s Total Time

All Input Parameters

{
  "width": 512,
  "height": 512,
  "prompt": "Mossy Runic Bricks seamless texture, trending on artstation, stone, moss, base color, albedo, 4k",
  "scheduler": "K-LMS",
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}

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. Tends to work better with prompt strength of 0.5-0.7. Consider using https://replicate.com/andreasjansson/stable-diffusion-inpainting instead.
seed Type: integer: Random seed. Leave blank to randomize the seed
width Default: 512: Width of output image. Maximum size is 1024x768 or 768x1024 because of memory limits
height Default: 512: Height of output image. Maximum size is 1024x768 or 768x1024 because of memory limits
prompt Type: stringDefault:: Input prompt
scheduler Default: K-LMS: Choose a scheduler. If you use an init image, PNDM will be used
init_image Type: string: Inital image to generate variations of. Will be resized to the specified width and height
num_outputs Type: integerDefault: 1Range: 1 - 10: Number of images to output. If the NSFW filter is triggered, you may get fewer outputs than this.
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: 52336
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:03<02:57,  3.63s/it]
  6%|▌         | 3/50 [00:03<00:47,  1.00s/it]
 10%|█         | 5/50 [00:03<00:23,  1.90it/s]
 14%|█▍        | 7/50 [00:04<00:14,  2.98it/s]
 18%|█▊        | 9/50 [00:04<00:09,  4.22it/s]
 22%|██▏       | 11/50 [00:04<00:07,  5.54it/s]
 26%|██▌       | 13/50 [00:04<00:05,  6.88it/s]
 30%|███       | 15/50 [00:04<00:04,  8.07it/s]
 34%|███▍      | 17/50 [00:04<00:03,  9.02it/s]
 38%|███▊      | 19/50 [00:05<00:03, 10.04it/s]
 42%|████▏     | 21/50 [00:05<00:02, 10.78it/s]
 46%|████▌     | 23/50 [00:05<00:02, 11.48it/s]
 50%|█████     | 25/50 [00:05<00:02, 12.04it/s]
 54%|█████▍    | 27/50 [00:05<00:01, 12.43it/s]
 58%|█████▊    | 29/50 [00:05<00:01, 12.67it/s]
 62%|██████▏   | 31/50 [00:05<00:01, 12.72it/s]
 66%|██████▌   | 33/50 [00:06<00:01, 12.94it/s]
 70%|███████   | 35/50 [00:06<00:01, 13.11it/s]
 74%|███████▍  | 37/50 [00:06<00:00, 13.23it/s]
 78%|███████▊  | 39/50 [00:06<00:00, 13.30it/s]
 82%|████████▏ | 41/50 [00:06<00:00, 13.38it/s]
 86%|████████▌ | 43/50 [00:06<00:00, 13.29it/s]
 90%|█████████ | 45/50 [00:06<00:00, 13.07it/s]
 94%|█████████▍| 47/50 [00:07<00:00, 13.14it/s]
 98%|█████████▊| 49/50 [00:07<00:00, 13.14it/s]
100%|██████████| 50/50 [00:07<00:00,  6.79it/s]

Version Details

Version ID: a42692c54c0f407f803a0a8a9066160976baedb77c91171a01730f9b0d7beeff
Version Created: November 13, 2022

Run on Replicate →