jagilley/controlnet-depth2img 🔢🖼️📝❓ → 🖼️

▶️ 679.8K runs 📅 Feb 2023 ⚙️ Cog 0.6.1 🔗 GitHub ⚖️ License

controlnet image-editing image-to-image

About

Modify images using depth maps

Example Output

Prompt:

"a stormtrooper giving a lecture at a university"

Output

Performance Metrics

20.90s Prediction Time

151.31s Total Time

All Input Parameters

{
  "image": "https://replicate.delivery/pbxt/IKFvJn5EpLuDDsFysOP4B1J9HvKDbMBCwZUK9n6p9mIPoQwG/sd.png",
  "scale": 9,
  "prompt": "a stormtrooper giving a lecture at a university",
  "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",
  "ddim_steps": 20,
  "num_samples": "1",
  "image_resolution": "512",
  "detect_resolution": 512
}

Input Parameters

eta Type: numberDefault: 0: eta (DDIM)
seed Type: integer: Seed
image (required) Type: string: Input image
scale Type: numberDefault: 9Range: 0.1 - 30: Guidance Scale
prompt (required) Type: string: Prompt for the model
a_prompt Type: stringDefault: best quality, extremely detailed: Added Prompt
n_prompt Type: stringDefault: longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality: Negative Prompt
ddim_steps Type: integerDefault: 20: Steps
num_samples Default: 1: Number of samples (higher values may OOM)
image_resolution Default: 512: Image resolution to be generated
detect_resolution Type: integerDefault: 512Range: 128 - 1024: Resolution for detection)

Output Schema

Output

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

Example Execution Logs

Global seed set to 625452
Data shape for DDIM sampling is (1, 4, 64, 64), eta 0.0
Running DDIM Sampling with 20 timesteps
DDIM Sampler:   0%|          | 0/20 [00:00<?, ?it/s]
DDIM Sampler:   5%|▌         | 1/20 [00:00<00:17,  1.10it/s]
DDIM Sampler:  10%|█         | 2/20 [00:01<00:14,  1.26it/s]
DDIM Sampler:  15%|█▌        | 3/20 [00:02<00:12,  1.32it/s]
DDIM Sampler:  20%|██        | 4/20 [00:03<00:11,  1.35it/s]
DDIM Sampler:  25%|██▌       | 5/20 [00:03<00:10,  1.37it/s]
DDIM Sampler:  30%|███       | 6/20 [00:04<00:10,  1.38it/s]
DDIM Sampler:  35%|███▌      | 7/20 [00:05<00:09,  1.39it/s]
DDIM Sampler:  40%|████      | 8/20 [00:05<00:08,  1.39it/s]
DDIM Sampler:  45%|████▌     | 9/20 [00:06<00:07,  1.39it/s]
DDIM Sampler:  50%|█████     | 10/20 [00:07<00:07,  1.39it/s]
DDIM Sampler:  55%|█████▌    | 11/20 [00:08<00:06,  1.39it/s]
DDIM Sampler:  60%|██████    | 12/20 [00:08<00:05,  1.39it/s]
DDIM Sampler:  65%|██████▌   | 13/20 [00:09<00:05,  1.39it/s]
DDIM Sampler:  70%|███████   | 14/20 [00:10<00:04,  1.39it/s]
DDIM Sampler:  75%|███████▌  | 15/20 [00:10<00:03,  1.38it/s]
DDIM Sampler:  80%|████████  | 16/20 [00:11<00:02,  1.38it/s]
DDIM Sampler:  85%|████████▌ | 17/20 [00:12<00:02,  1.38it/s]
DDIM Sampler:  90%|█████████ | 18/20 [00:13<00:01,  1.38it/s]
DDIM Sampler:  95%|█████████▌| 19/20 [00:13<00:00,  1.38it/s]
DDIM Sampler: 100%|██████████| 20/20 [00:14<00:00,  1.38it/s]
DDIM Sampler: 100%|██████████| 20/20 [00:14<00:00,  1.37it/s]

Version Details

Version ID: 922c7bb67b87ec32cbc2fd11b1d5f94f0ba4f5519c4dbd02856376444127cc60
Version Created: February 16, 2023

Run on Replicate →