adirik/sdxl-prompt-to-prompt 🔢🖼️📝❓ → 🖼️

▶️ 261 runs 📅 Dec 2023 ⚙️ Cog 0.8.3 📄 Paper

image-editing image-to-image

About

Image editing with Prompt-to-Prompt for SDXL

Example Output

Output

Performance Metrics

31.77s Prediction Time

31.81s Total Time

All Input Parameters

{
  "seed": 864,
  "edited_prompt": "a pink dragon riding a bicycle on the beach",
  "original_prompt": "a pink bear riding a bicycle on the beach",
  "prompt_edit_type": "Replacement",
  "self_replace_steps": 0.4,
  "cross_replace_steps": 0.8
}

Input Parameters

seed Type: integerRange: 0 - 65535: Random seed. Leave blank to randomize the seed for original output.
image Type: string: Optional input image. If provided, DDIM inversion is performed to retrieve initial latents for image generation.
local_edit Type: string: Comma seperated words to determine which area should be changed. If None, then the whole image can be changed.
edited_prompt Type: string: Prompt used for editing the original sdxl output image. If prompt_edit_type above is `Re-weight`, you can leave this empty.
guidance_scale Type: numberDefault: 7.5: Text guidance scale, use higher values for better alignment with input prompt.
equalizer_words Type: string: Words to be re-weighted (either enhancement or diminishment). Provide the words in the format of 'word1, word2, word3'. If you are not using reweight, leave this empty.
original_prompt (required) Type: string: Prompt to generate image with SDXL
prompt_edit_type (required): Choose the type of the prompt editing, can be either of `Replacement`, `Refinement`, `Re-weight`
self_replace_steps Type: numberDefault: 0.4Range: 0 - 1: Number of diffusion steps in which self attention should be replaced
cross_replace_steps Type: numberDefault: 0.8Range: 0 - 1: Number of diffusion steps in which cross attention should be replaced
equalizer_strengths Type: string: Strengths for the words to be re-weighted. It can be positive or negative values. Provide the strengths in the format of 'strength1, strength2, strength3', for respective equalizer_words. If you are not using reweight, leave this empty.
num_inference_steps Type: integerDefault: 50Range: 0 - 100: Number of diffusion denoising steps for image generation.
num_inversion_steps Type: integerDefault: 50Range: 0 - 100: Number of diffusion denoising steps for inversion.

Output Schema

Output

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

Example Execution Logs

Using seed: 864
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:00<00:26,  1.88it/s]
  4%|▍         | 2/50 [00:01<00:26,  1.83it/s]
  6%|▌         | 3/50 [00:01<00:25,  1.81it/s]
  8%|▊         | 4/50 [00:02<00:25,  1.80it/s]
 10%|█         | 5/50 [00:02<00:25,  1.80it/s]
 12%|█▏        | 6/50 [00:03<00:24,  1.80it/s]
 14%|█▍        | 7/50 [00:03<00:23,  1.79it/s]
 16%|█▌        | 8/50 [00:04<00:23,  1.79it/s]
 18%|█▊        | 9/50 [00:04<00:22,  1.79it/s]
 20%|██        | 10/50 [00:05<00:22,  1.79it/s]
 22%|██▏       | 11/50 [00:06<00:21,  1.80it/s]
 24%|██▍       | 12/50 [00:06<00:21,  1.80it/s]
 26%|██▌       | 13/50 [00:07<00:20,  1.80it/s]
 28%|██▊       | 14/50 [00:07<00:20,  1.80it/s]
 30%|███       | 15/50 [00:08<00:19,  1.80it/s]
 32%|███▏      | 16/50 [00:08<00:18,  1.80it/s]
 34%|███▍      | 17/50 [00:09<00:18,  1.80it/s]
 36%|███▌      | 18/50 [00:10<00:17,  1.80it/s]
 38%|███▊      | 19/50 [00:10<00:17,  1.80it/s]
 40%|████      | 20/50 [00:11<00:16,  1.80it/s]
 42%|████▏     | 21/50 [00:11<00:16,  1.80it/s]
 44%|████▍     | 22/50 [00:12<00:15,  1.81it/s]
 46%|████▌     | 23/50 [00:12<00:14,  1.81it/s]
 48%|████▊     | 24/50 [00:13<00:14,  1.81it/s]
 50%|█████     | 25/50 [00:13<00:13,  1.81it/s]
 52%|█████▏    | 26/50 [00:14<00:13,  1.81it/s]
 54%|█████▍    | 27/50 [00:14<00:12,  1.81it/s]
 56%|█████▌    | 28/50 [00:15<00:12,  1.82it/s]
 58%|█████▊    | 29/50 [00:16<00:11,  1.81it/s]
 60%|██████    | 30/50 [00:16<00:11,  1.81it/s]
 62%|██████▏   | 31/50 [00:17<00:10,  1.82it/s]
 64%|██████▍   | 32/50 [00:17<00:09,  1.81it/s]
 66%|██████▌   | 33/50 [00:18<00:09,  1.81it/s]
 68%|██████▊   | 34/50 [00:18<00:08,  1.81it/s]
 70%|███████   | 35/50 [00:19<00:08,  1.81it/s]
 72%|███████▏  | 36/50 [00:19<00:07,  1.81it/s]
 74%|███████▍  | 37/50 [00:20<00:07,  1.81it/s]
 76%|███████▌  | 38/50 [00:21<00:06,  1.81it/s]
 78%|███████▊  | 39/50 [00:21<00:06,  1.81it/s]
 80%|████████  | 40/50 [00:22<00:05,  1.81it/s]
 82%|████████▏ | 41/50 [00:22<00:04,  1.81it/s]
 84%|████████▍ | 42/50 [00:23<00:04,  1.81it/s]
 86%|████████▌ | 43/50 [00:23<00:03,  1.81it/s]
 88%|████████▊ | 44/50 [00:24<00:03,  1.81it/s]
 90%|█████████ | 45/50 [00:24<00:02,  1.81it/s]
 92%|█████████▏| 46/50 [00:25<00:02,  1.81it/s]
 94%|█████████▍| 47/50 [00:26<00:01,  1.81it/s]
 96%|█████████▌| 48/50 [00:26<00:01,  1.81it/s]
 98%|█████████▊| 49/50 [00:27<00:00,  1.81it/s]
100%|██████████| 50/50 [00:27<00:00,  1.81it/s]
100%|██████████| 50/50 [00:27<00:00,  1.81it/s]
Number of output images: 2

Version Details

Version ID: 2079d6f8b096cd722cef30086a280a8d4865018bd3a8c12bbe039580c19a722b
Version Created: March 16, 2024

Run on Replicate →