Рет қаралды 19,705
Discover the power of 'reference_adain+attn' in ControlNet! This video reveals how 'reference_adain+attn' outperforms reference_only in image generation. Witness the superior performance of this new preprocessor in creating stunning images that closely resemble the input inside stable diffusion
Socials 📱
- Instagram: / lemonscript.io
- TikTok: / lemonscript
- GitHub: github.com/lemonscript101
Timestamps ⏳
00:00 | Introduction
00:11 | Updating to newest ControlNet version
00:44 | General Stable Diffusion settings
01:08 | ControlNet settings
01:41 | Prompts
02:20 | First render with new method
02:55 | reference_adain+attn vs. reference_only
04:51 | reference_adain+attn settings
The reference image is a Photo by Andre Sebastian: unsplash.com/@andreonbrand?ut..." on Unsplash: unsplash.com/photos/3_I3GXWld...
Negative Prompt
((((ugly)))), (((duplicate))), ((morbid)), ((mutilated)), [out of frame], extra fingers, mutated hands, ((poorly drawn hands)), ((poorly drawn face)), (((mutation))), (((deformed))), blurry, ((bad anatomy)), (((bad proportions))), ((extra limbs)), cloned face, (((disfigured))), gross proportions, (malformed limbs), ((missing arms)), ((missing legs)), (((extra arms))), (((extra legs))), (fused fingers), (too many fingers), (((long neck)))
#ControlNet #stablediffusion #AI #Technology