timothybrooks/instruct-pix2pix 🔢🖼️📝❓ → 🖼️

▶️ 919.5K runs 📅 Jan 2023 ⚙️ Cog 0.6.1 🔗 GitHub 📄 Paper ⚖️ License
image-editing image-to-image

About

Edit images with human instructions

Example Output

Prompt:

"turn him into cyborg"

Output

Example output

Performance Metrics

8.21s Prediction Time
8.26s Total Time
All Input Parameters
{
  "image": "https://replicate.delivery/pbxt/IBnrzJD8Vvz3rD7yF5W8ODnpeA5wcoNpP1RRiDutqW1nG8eF/example.jpeg",
  "prompt": "turn him into cyborg",
  "scheduler": "K_EULER_ANCESTRAL",
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "num_inference_steps": 100,
  "image_guidance_scale": 1.5
}
Input Parameters
seed Type: integer
Random seed. Leave blank to randomize the seed
image (required) Type: string
An image which will be repainted according to prompt
prompt (required) Type: string
Prompt to guide the image generation
scheduler Default: K_EULER_ANCESTRAL
Choose a scheduler.
num_outputs Default: 1
Number of images to output
guidance_scale Type: numberDefault: 7.5Range: 1 - 20
Scale for classifier-free guidance. Higher guidance scale encourages to generate images that are closely linked to the text prompt, usually at the expense of lower image quality.
negative_prompt Type: string
The prompt or prompts not to guide the image generation (what you do not want to see in the generation). Ignored when not using guidance.
num_inference_steps Type: integerDefault: 100Range: 1 - 500
The number of denoising steps. More denoising steps usually lead to a higher quality image at the expense of slower inference.
image_guidance_scale Type: numberDefault: 1.5Range: 1 - ∞
Image guidance scale is to push the generated image towards the inital image. Higher image guidance scale encourages to generate images that are closely linked to the source image, usually at the expense of lower image quality.
Output Schema

Output

Type: arrayItems Type: stringItems Format: uri

Example Execution Logs
Using seed: 49287
  0%|          | 0/100 [00:00<?, ?it/s]
  2%|▏         | 2/100 [00:00<00:08, 11.55it/s]
  4%|▍         | 4/100 [00:00<00:07, 13.57it/s]
  6%|▌         | 6/100 [00:00<00:06, 14.33it/s]
  8%|▊         | 8/100 [00:00<00:06, 14.36it/s]
 10%|█         | 10/100 [00:00<00:06, 14.37it/s]
 12%|█▏        | 12/100 [00:00<00:06, 14.28it/s]
 14%|█▍        | 14/100 [00:01<00:06, 13.74it/s]
 16%|█▌        | 16/100 [00:01<00:06, 13.40it/s]
 18%|█▊        | 18/100 [00:01<00:06, 13.54it/s]
 20%|██        | 20/100 [00:01<00:05, 13.78it/s]
 22%|██▏       | 22/100 [00:01<00:05, 14.24it/s]
 24%|██▍       | 24/100 [00:01<00:05, 14.35it/s]
 26%|██▌       | 26/100 [00:01<00:05, 14.23it/s]
 28%|██▊       | 28/100 [00:02<00:05, 14.06it/s]
 30%|███       | 30/100 [00:02<00:04, 14.07it/s]
 32%|███▏      | 32/100 [00:02<00:04, 14.57it/s]
 34%|███▍      | 34/100 [00:02<00:04, 14.28it/s]
 36%|███▌      | 36/100 [00:02<00:04, 14.23it/s]
 38%|███▊      | 38/100 [00:02<00:04, 14.30it/s]
 40%|████      | 40/100 [00:02<00:04, 14.16it/s]
 42%|████▏     | 42/100 [00:02<00:04, 14.41it/s]
 44%|████▍     | 44/100 [00:03<00:03, 14.42it/s]
 46%|████▌     | 46/100 [00:03<00:03, 14.46it/s]
 48%|████▊     | 48/100 [00:03<00:03, 14.72it/s]
 50%|█████     | 50/100 [00:03<00:03, 14.77it/s]
 52%|█████▏    | 52/100 [00:03<00:03, 14.87it/s]
 54%|█████▍    | 54/100 [00:03<00:03, 14.31it/s]
 56%|█████▌    | 56/100 [00:03<00:02, 14.74it/s]
 58%|█████▊    | 58/100 [00:04<00:02, 14.89it/s]
 60%|██████    | 60/100 [00:04<00:02, 15.05it/s]
 62%|██████▏   | 62/100 [00:04<00:02, 15.12it/s]
 64%|██████▍   | 64/100 [00:04<00:02, 15.25it/s]
 66%|██████▌   | 66/100 [00:04<00:02, 15.39it/s]
 68%|██████▊   | 68/100 [00:04<00:02, 15.39it/s]
 70%|███████   | 70/100 [00:04<00:01, 15.48it/s]
 72%|███████▏  | 72/100 [00:04<00:01, 15.60it/s]
 74%|███████▍  | 74/100 [00:05<00:01, 15.86it/s]
 76%|███████▌  | 76/100 [00:05<00:01, 15.79it/s]
 78%|███████▊  | 78/100 [00:05<00:01, 15.65it/s]
 80%|████████  | 80/100 [00:05<00:01, 15.12it/s]
 82%|████████▏ | 82/100 [00:05<00:01, 15.35it/s]
 84%|████████▍ | 84/100 [00:05<00:01, 15.28it/s]
 86%|████████▌ | 86/100 [00:05<00:00, 15.38it/s]
 88%|████████▊ | 88/100 [00:05<00:00, 15.53it/s]
 90%|█████████ | 90/100 [00:06<00:00, 15.26it/s]
 92%|█████████▏| 92/100 [00:06<00:00, 14.85it/s]
 94%|█████████▍| 94/100 [00:06<00:00, 14.59it/s]
 96%|█████████▌| 96/100 [00:06<00:00, 14.70it/s]
 98%|█████████▊| 98/100 [00:06<00:00, 14.25it/s]
100%|██████████| 100/100 [00:06<00:00, 14.10it/s]
100%|██████████| 100/100 [00:06<00:00, 14.61it/s]
Version Details
Version ID
30c1d0b916a6f8efce20493f5d61ee27491ab2a60437c13c588468b9810ec23f
Version Created
January 24, 2023
Run on Replicate →