SD3.5 Released!
Added 2024-10-22 20:33:03 +0000 UTCVideo coming soon!
Stability AI: https://stability.ai/news/introducing-stable-diffusion-3-5
ComfyUI Examples: https://comfyanonymous.github.io/ComfyUI_examples/sd3/
Yes, it's finally here - SD3.5 Large! But is it any good? Short answer... I think we'll have to wait and see.
As for the best settings, it's only been a few hours so I'm experimenting, but setting the SD3 Model Sampling to something LOWER than the default 3 seems to work well. Dpm++2m is a firm favourite, and a decent number of steps looks to be 30+
Being large, you'll need a decent amount of VRAM, but offloading CLIP to CPU can help there.
Have a play and see what you think ;)
As usual, the workflow used in the video is attached to this post.
Comments
:D
Nerdy Rodent
2024-10-26 10:14:10 +0000 UTCSure! Text-2-Image / Image-2-Image example has been attached :)
Nerdy Rodent
2024-10-26 10:13:57 +0000 UTCnice do we get image to image workflow with SD3.5
Rart
2024-10-26 06:36:00 +0000 UTCGreat job on getting this so quickly! Awesome, 2025 will be wild. A few years ago, we were playing around with CLIP diffusion
Lord Banzai
2024-10-23 01:55:03 +0000 UTC
