rossjillian/controlnet 🔢🖼️📝❓✓ → 🖼️

▶️ 7.6M runs 📅 Mar 2023 ⚙️ Cog 0.8.0-beta8 🔗 GitHub 📄 Paper ⚖️ License

controlnet image-to-image sketch-to-image

About

Control diffusion models

Example Output

Prompt:

"a photo of a brightly colored turtle"

Output

Performance Metrics

3.97s Prediction Time

4.53s Total Time

All Input Parameters

{
  "seed": 20,
  "image": "https://replicate.delivery/pbxt/IYQLHLFDraqCrjDUoiwpM9xBhQM1eQVHbxBiNxcbwctUamzb/user_1.png",
  "scale": 9,
  "steps": 20,
  "prompt": "a photo of a brightly colored turtle",
  "a_prompt": "Best quality, extremely detailed",
  "n_prompt": "Longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
  "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 (required) Type: string: Prompt for the model
scheduler Default: DDIM: Choose a scheduler.
structure (required): Controlnet structure to condition on
num_outputs Type: integerDefault: 1Range: 1 - 4: Number of images to output (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
negative_prompt Type: stringDefault: Longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality: Negative prompt
image_resolution Default: 512: Resolution of output image (will be scaled to this as its smaller dimension)
return_reference_image Type: booleanDefault: false: whether to return the reference image along with the output

Output Schema

Output

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

Example Execution Logs

Using seed: 20
  0%|          | 0/20 [00:00<?, ?it/s]
  5%|▌         | 1/20 [00:00<00:01,  9.69it/s]
 10%|█         | 2/20 [00:00<00:01,  9.44it/s]
 15%|█▌        | 3/20 [00:00<00:01,  9.48it/s]
 20%|██        | 4/20 [00:00<00:01,  9.51it/s]
 25%|██▌       | 5/20 [00:00<00:01,  9.59it/s]
 30%|███       | 6/20 [00:00<00:01,  9.50it/s]
 35%|███▌      | 7/20 [00:00<00:01,  9.44it/s]
 40%|████      | 8/20 [00:00<00:01,  9.59it/s]
 50%|█████     | 10/20 [00:01<00:01,  9.97it/s]
 60%|██████    | 12/20 [00:01<00:00,  9.88it/s]
 65%|██████▌   | 13/20 [00:01<00:00,  9.52it/s]
 70%|███████   | 14/20 [00:01<00:00,  9.24it/s]
 75%|███████▌  | 15/20 [00:01<00:00,  9.05it/s]
 80%|████████  | 16/20 [00:01<00:00,  8.78it/s]
 85%|████████▌ | 17/20 [00:01<00:00,  8.37it/s]
 90%|█████████ | 18/20 [00:01<00:00,  8.09it/s]
 95%|█████████▌| 19/20 [00:02<00:00,  8.22it/s]
100%|██████████| 20/20 [00:02<00:00,  8.31it/s]
100%|██████████| 20/20 [00:02<00:00,  9.03it/s]

Version Details

Version ID: 795433b19458d0f4fa172a7ccf93178d2adb1cb8ab2ad6c8fdc33fdbcd49f477
Version Created: July 1, 2023

Run on Replicate →