ai-hub-models icon indicating copy to clipboard operation
ai-hub-models copied to clipboard

Published 20 hours ago • verified publisher icon quic

[BUG] Controlnet models are providing noisy image outputs

Open kristoftunner opened this issue 2 months ago • 1 comments

Describe the bug The controlnet pipeline is providing me noisy image output, in general it does its thing, but the quality of the image makes it unsable. Prompt: "photo, mid century modern, natural light, pink walls". See the input/output images below: Input: image

Outputs with various seed/guidance scale settings: image_dpmsolver++_23_2048775510 20_7 5 image_dpmsolver++_23_6126326530 61_7 5 image_dpmsolver++_23_10000000000 00_7 5 image_dpmsolver++_35_2660408163 27_12 5

To Reproduce Try to run the demo application with the following settings:

  • dpmsolver++ scheduler
  • 23 or 35 steps
  • guidance scale 7.5 or 12.5
  • seed: between 1e7 - 1e10

I get this noise in every image, the image quality is nowhere compared to the original float controlnet model in here: https://github.com/AUTOMATIC1111/stable-diffusion-webui

Expected behavior Have a comparable output with the original float controlnet model from here: https://github.com/Mikubill/sd-webui-controlnet Something like this: 00001-1497947079

Host configuration:

  • OS and version: Win 11
  • QAI-Hub-Models version: latest controlnet

Am I missing something, shall I use another scheduler with different options or is there a better quantized model for controlnet?

kristoftunner avatar Apr 28 '24 05:04 kristoftunner