fermatresearch/photorealistic-fx-controlnet 🔢🖼️📝❓ → 🖼️

▶️ 2.6K runs 📅 Jun 2023 ⚙️ Cog 0.7.2

image-to-image sketch-to-image

About

ControlNet implementation for RunDiffusion's PhotorealisticFX model.

Example Output

Prompt:

"a photo of a brightly colored turtle"

Output

Performance Metrics

5.70s Prediction Time

181.13s Total Time

All Input Parameters

{
  "image": "https://replicate.delivery/pbxt/IzhXiQKcw0bDVYSr36ud9eCHakjdzCeXPylw2CVube3y7Tlh/user_1.png",
  "scale": 9,
  "steps": 20,
  "prompt": "a photo of a brightly colored turtle",
  "a_prompt": "Best quality, extremely detailed",
  "n_prompt": "(semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck",
  "structure": "scribble",
  "num_samples": "1",
  "low_threshold": 100,
  "high_threshold": 200,
  "image_resolution": "512"
}

Input Parameters

eta Type: numberDefault: 0: Controls the amount of noise that is added to the input data during the denoising diffusion process. Higher value -> more noise
seed Type: integer: Seed
image (required) Type: string: Input image
scale Type: numberDefault: 9Range: 0.1 - 30: Scale for classifier-free guidance
steps Type: integerDefault: 20: Steps
prompt Type: stringDefault: a zoo in space: Prompt for the model
a_prompt Type: stringDefault: Best quality, extremely detailed: Additional text to be appended to prompt
n_prompt Type: stringDefault: (semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck: Negative prompt
structure Default: canny: Structure to condition on
num_samples Default: 1: Number of samples (higher values may OOM)
low_threshold Type: integerDefault: 100Range: 1 - 255: [canny only] Line detection low threshold
high_threshold Type: integerDefault: 200Range: 1 - 255: [canny only] Line detection high threshold
image_resolution Default: 512: Resolution of image (square)

Output Schema

Output

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

Example Execution Logs

Using seed: 50831
  0%|          | 0/20 [00:00<?, ?it/s]
  5%|▌         | 1/20 [00:01<00:22,  1.18s/it]
 15%|█▌        | 3/20 [00:01<00:07,  2.33it/s]
 25%|██▌       | 5/20 [00:01<00:03,  3.92it/s]
 35%|███▌      | 7/20 [00:01<00:02,  5.40it/s]
 45%|████▌     | 9/20 [00:02<00:01,  6.66it/s]
 55%|█████▌    | 11/20 [00:02<00:01,  7.73it/s]
 65%|██████▌   | 13/20 [00:02<00:00,  8.54it/s]
 75%|███████▌  | 15/20 [00:02<00:00,  9.20it/s]
 85%|████████▌ | 17/20 [00:02<00:00,  9.80it/s]
 95%|█████████▌| 19/20 [00:02<00:00, 10.18it/s]
100%|██████████| 20/20 [00:03<00:00,  6.55it/s]

Version Details

Version ID: 667615bff074702df10cd0ac9d316cd1b68b0253b01b313306dc9a556ed36920
Version Created: June 13, 2023

Run on Replicate →