adirik/t2i-adapter-sdxl-depth-midas 🖼️📝❓🔢 → 🖼️

▶️ 654.0K runs 📅 Sep 2023 ⚙️ Cog 0.8.3 🔗 GitHub 📄 Paper ⚖️ License

depth-guided image-editing image-to-image

About

Modify images using depth maps

Example Output

Prompt:

"A photo of a room, 4k photo, highly detailed"

Output

Performance Metrics

14.09s Prediction Time

140.75s Total Time

All Input Parameters

{
  "image": "https://replicate.delivery/pbxt/JbnAzlvH84NR20HgqUdfnLlMMwwiU8Fv5N3FSjcRXPH6kmmu/org_mid.jpg",
  "prompt": "A photo of a room, 4k photo, highly detailed",
  "scheduler": "K_EULER_ANCESTRAL",
  "num_samples": 1,
  "guidance_scale": 7.5,
  "negative_prompt": "anime, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured",
  "num_inference_steps": 30,
  "adapter_conditioning_scale": 1,
  "adapter_conditioning_factor": 1
}

Input Parameters

image (required) Type: string: Input image
prompt Type: stringDefault: A photo of a room, 4k photo, highly detailed: Input prompt
scheduler Default: K_EULER_ANCESTRAL: Which scheduler to use
num_samples Type: integerDefault: 1Range: 1 - 4: Number of outputs to generate
random_seed Type: integer: Random seed for reproducibility, leave blank to randomize output
guidance_scale Type: numberDefault: 7.5Range: 0 - 10: Guidance scale to match the prompt
negative_prompt Type: stringDefault: anime, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured: Specify things to not see in the output
num_inference_steps Type: integerDefault: 30Range: 0 - 100: Number of diffusion steps
adapter_conditioning_scale Type: numberDefault: 1Range: 0 - 5: Conditioning scale
adapter_conditioning_factor Type: numberDefault: 1Range: 0 - 1: Factor to scale image by

Output Schema

Output

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

Example Execution Logs

0%|          | 0/30 [00:00<?, ?it/s]
  3%|▎         | 1/30 [00:00<00:05,  5.32it/s]
  7%|▋         | 2/30 [00:00<00:07,  3.76it/s]
 10%|█         | 3/30 [00:00<00:07,  3.43it/s]
 13%|█▎        | 4/30 [00:01<00:07,  3.29it/s]
 17%|█▋        | 5/30 [00:01<00:07,  3.21it/s]
 20%|██        | 6/30 [00:01<00:07,  3.17it/s]
 23%|██▎       | 7/30 [00:02<00:07,  3.14it/s]
 27%|██▋       | 8/30 [00:02<00:07,  3.12it/s]
 30%|███       | 9/30 [00:02<00:06,  3.11it/s]
 33%|███▎      | 10/30 [00:03<00:06,  3.10it/s]
 37%|███▋      | 11/30 [00:03<00:06,  3.09it/s]
 40%|████      | 12/30 [00:03<00:05,  3.09it/s]
 43%|████▎     | 13/30 [00:04<00:05,  3.09it/s]
 47%|████▋     | 14/30 [00:04<00:05,  3.08it/s]
 50%|█████     | 15/30 [00:04<00:04,  3.08it/s]
 53%|█████▎    | 16/30 [00:05<00:04,  3.08it/s]
 57%|█████▋    | 17/30 [00:05<00:04,  3.08it/s]
 60%|██████    | 18/30 [00:05<00:03,  3.08it/s]
 63%|██████▎   | 19/30 [00:06<00:03,  3.08it/s]
 67%|██████▋   | 20/30 [00:06<00:03,  3.07it/s]
 70%|███████   | 21/30 [00:06<00:02,  3.07it/s]
 73%|███████▎  | 22/30 [00:07<00:02,  3.07it/s]
 77%|███████▋  | 23/30 [00:07<00:02,  3.07it/s]
 80%|████████  | 24/30 [00:07<00:01,  3.07it/s]
 83%|████████▎ | 25/30 [00:07<00:01,  3.07it/s]
 87%|████████▋ | 26/30 [00:08<00:01,  3.07it/s]
 90%|█████████ | 27/30 [00:08<00:00,  3.07it/s]
 93%|█████████▎| 28/30 [00:08<00:00,  3.07it/s]
 97%|█████████▋| 29/30 [00:09<00:00,  3.07it/s]
100%|██████████| 30/30 [00:09<00:00,  3.07it/s]
100%|██████████| 30/30 [00:09<00:00,  3.12it/s]

Version Details

Version ID: 8a89b0ab59a050244a751b6475d91041a8582ba33692ae6fab65e0c51b700328
Version Created: October 30, 2023

Run on Replicate →