humanvideointeraction/t2i-adapter-sketch-sdxl 🔢🖼️📝 → 🖼️
About
ControlNet Scribble for SDXL
Example Output
Prompt:
"a robot, mount fuji in the background, 4k photo, highly detailed"
Output

Performance Metrics
5.42s
Prediction Time
90.13s
Total Time
All Input Parameters
{
"seed": 0,
"image": "https://replicate.delivery/pbxt/JYjxKVHsb0DIcjKhGwECMW6QoDChBXZfvTpHKpkBckay804G/org_sketch.png",
"prompt": "a robot, mount fuji in the background, 4k photo, highly detailed",
"guidance_scale": 7.5,
"negative_prompt": "extra digit, fewer digits, cropped, worst quality, low quality, glitch, deformed, mutated, ugly, disfigured",
"num_inference_steps": 30,
"adapter_condition_scale": 0.9
}
Input Parameters
- seed
- Random seed. Set to 0 to randomize the seed
- image
- Input image
- prompt
- Input prompt
- guidance_scale
- Scale for classifier-free guidance
- negative_prompt
- Input Negative Prompt
- num_inference_steps
- Number of denoising steps
- adapter_condition_scale
- conditioning scale for generalization
Output Schema
Output
Example Execution Logs
Using seed: 64369 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:00<00:04, 6.74it/s] 10%|█ | 3/30 [00:00<00:02, 9.87it/s] 17%|█▋ | 5/30 [00:00<00:02, 10.83it/s] 23%|██▎ | 7/30 [00:00<00:02, 11.34it/s] 30%|███ | 9/30 [00:00<00:01, 11.97it/s] 37%|███▋ | 11/30 [00:00<00:01, 11.96it/s] 43%|████▎ | 13/30 [00:01<00:01, 11.99it/s] 50%|█████ | 15/30 [00:01<00:01, 12.00it/s] 57%|█████▋ | 17/30 [00:01<00:01, 12.01it/s] 63%|██████▎ | 19/30 [00:01<00:00, 12.02it/s] 70%|███████ | 21/30 [00:01<00:00, 12.02it/s] 77%|███████▋ | 23/30 [00:01<00:00, 12.02it/s] 83%|████████▎ | 25/30 [00:02<00:00, 12.01it/s] 90%|█████████ | 27/30 [00:02<00:00, 11.99it/s] 97%|█████████▋| 29/30 [00:02<00:00, 11.99it/s] 100%|██████████| 30/30 [00:02<00:00, 11.76it/s]
Version Details
- Version ID
00e7103b21053a327f8e00e6a861f4df08136b6c585fa0d3c7ab3128777e255a- Version Created
- September 20, 2023