jagilley/controlnet-pose 🔢🖼️📝❓ → 🖼️

▶️ 175.4K runs 📅 Feb 2023 ⚙️ Cog 0.6.1 🔗 GitHub ⚖️ License

controlnet image-to-image pose-guided-generation

About

Modify images with humans using pose detection

Example Output

Prompt:

"an astronaut on the moon, digital art"

Output

Performance Metrics

34.53s Prediction Time

34.67s Total Time

All Input Parameters

{
  "image": "https://replicate.delivery/pbxt/IKJO0Z6768YQahgAfgUF00iJCi2wPNVB8EwefQWodZagisYt/pose2.png",
  "scale": 9,
  "prompt": "an astronaut on the moon, digital art",
  "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: 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
prompt (required) Type: string: Prompt for the model
a_prompt Type: stringDefault: best quality, extremely detailed: Additional text to be appended to 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)
low_threshold Type: integerDefault: 100Range: 1 - 255: Canny line detection low threshold
high_threshold Type: integerDefault: 200Range: 1 - 255: Canny line detection high threshold
image_resolution Default: 512: Image resolution to be generated
detect_resolution Type: integerDefault: 512Range: 128 - 1024: Resolution at which detection method will be applied)

Output Schema

Output

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

Example Execution Logs

Global seed set to 962031
Data shape for DDIM sampling is (1, 4, 96, 64), eta 0.0
Running DDIM Sampling with 20 timesteps
DDIM Sampler:   0%|          | 0/20 [00:00<?, ?it/s]
DDIM Sampler:   5%|▌         | 1/20 [00:01<00:30,  1.59s/it]
DDIM Sampler:  10%|█         | 2/20 [00:02<00:25,  1.44s/it]
DDIM Sampler:  15%|█▌        | 3/20 [00:04<00:23,  1.39s/it]
DDIM Sampler:  20%|██        | 4/20 [00:05<00:21,  1.37s/it]
DDIM Sampler:  25%|██▌       | 5/20 [00:06<00:20,  1.36s/it]
DDIM Sampler:  30%|███       | 6/20 [00:08<00:18,  1.36s/it]
DDIM Sampler:  35%|███▌      | 7/20 [00:09<00:17,  1.35s/it]
DDIM Sampler:  40%|████      | 8/20 [00:10<00:16,  1.35s/it]
DDIM Sampler:  45%|████▌     | 9/20 [00:12<00:14,  1.36s/it]
DDIM Sampler:  50%|█████     | 10/20 [00:13<00:13,  1.36s/it]
DDIM Sampler:  55%|█████▌    | 11/20 [00:15<00:12,  1.36s/it]
DDIM Sampler:  60%|██████    | 12/20 [00:16<00:10,  1.36s/it]
DDIM Sampler:  65%|██████▌   | 13/20 [00:17<00:09,  1.36s/it]
DDIM Sampler:  70%|███████   | 14/20 [00:19<00:08,  1.36s/it]
DDIM Sampler:  75%|███████▌  | 15/20 [00:20<00:06,  1.36s/it]
DDIM Sampler:  80%|████████  | 16/20 [00:21<00:05,  1.36s/it]
DDIM Sampler:  85%|████████▌ | 17/20 [00:23<00:04,  1.37s/it]
DDIM Sampler:  90%|█████████ | 18/20 [00:24<00:02,  1.37s/it]
DDIM Sampler:  95%|█████████▌| 19/20 [00:26<00:01,  1.37s/it]
DDIM Sampler: 100%|██████████| 20/20 [00:27<00:00,  1.37s/it]
DDIM Sampler: 100%|██████████| 20/20 [00:27<00:00,  1.37s/it]

Version Details

Version ID: 0304f7f774ba7341ef754231f794b1ba3d129e3c46af3022241325ae0c50fb99
Version Created: February 23, 2023

Run on Replicate →