FLUX Chroma: https://huggingface.co/lodestones/Chroma

FLUX Chroma (Tensor Art) : https://tensor.art/models/886764918794154122

Unlike base FLUX Schnell , FLUX Chroma uses NAG (Normalized Attentive Guidence) : https://huggingface.co/spaces/ChenDY/NAG_FLUX.1-dev

TLDR; NAG are negatives added to FLUX model

Paper: https://arxiv.org/abs/2505.21179

See FLUX Chroma Huggingface repo for additional changes from base FLUX Schnell model

To help with creating prompts for FLUX , use Joycaptions:https://huggingface.co/spaces/fancyfeast/joy-caption-beta-one

And Danbooru tags: https://donmai.moe/wiki_pages/help:home

The prompt can be up to 512 tokens long , which can be checked at https://sd-tokenizer.rocker.boo/

you are viewing a single comment's thread
view the rest of the comments
[–] 2 points 1 year ago

You probably want a GPU with 12GB of VRAM as that's enough to fit the entire fp8-scaled version. Also a PCIe 4 or 5 NVME SSD if you don't want model load times to be a problem, but that's about it. Linux is great for AI too.

  • source
  • parent