this post was submitted on 29 Jan 2026
4 points (100.0% liked)

Stable Diffusion

5337 readers
3 users here now

Discuss matters related to our favourite AI Art generation technology

Also see

Other communities

founded 2 years ago
MODERATORS
db0@lemmy.dbzer0.com
Even_Adder@lemmy.dbzer0.com
4
Abrahamm3r/Z-Image-SDNQ-uint4-svd-r32 · A 4-bit quantized version of Tongyi-MAI/Z-Image using SDNQ (Structured Decomposable Neural Quantization) (huggingface.co)
submitted 1 day ago by Even_Adder@lemmy.dbzer0.com to c/stable_diffusion@lemmy.dbzer0.com
4 comments fedilink hide all child comments
 

You need comfyui-sdnq to load SDNQ quantized models in ComfyUI: https://github.com/EnragedAntelope/comfyui-sdnq

top 4 comments
sorted by: hot top controversial new old
[–] db0@lemmy.dbzer0.com 2 points 23 hours ago (1 children)

What are the tradeoffs? I can't believe a 50% to 75% RAM reduction is free. Is this like quantization?

[–] Even_Adder@lemmy.dbzer0.com 2 points 23 hours ago* (last edited 23 hours ago) (1 children)

Yeah, it's a different form of quantization. I think it's supposed to look a little better than conventional quants, but it still has all the tradeoffs of a quant.

[–] db0@lemmy.dbzer0.com 2 points 23 hours ago (1 children)

gotcha, so this downloads its own custom quantization models?