CRUX - CRUX-v1
Recommended Negative Prompts
Use negative prompts for CFG enabled workflows
Recommended Parameters
samplers
steps
Tips
Can be used with Chroma or Flux de-distilled workflows with CFG enabled.
Increase FluxGuidance to >4 when using flux.1-dev workflows for better adherence.
Recommended to use Chroma or classic CFG workflows including negative prompts instead of Flux unless researching boundaries.
FLUX LoRA compatibility is promising but under testing.
Only tested with ComfyUI inference tool so far; results may vary.
Supports NSFW content and advanced female anatomy generation.
Tuned for specific anime/illustration styles introducing lost artistic concepts.
Version Highlights
The first release of CRUX - let us know what you think and be sure to share your generations below!
Creator Sponsors
V1 - 6/23 - Initial Release - GGUF'S ARE HERE!
===========================================================================
CRUX (chroma/flux) hybrid models are created by DR34MSC4PE with the best of both worlds:
In a blurb? It is a hybrid model between Chroma/Flux that puts back the removed components (modulation layers, etc) from FLUX.1-dev by selectively merging it with a special variant of C4PACITOR but, importantly, keeping Chroma's de-distilled (unchained) nature and output layers.
Can be used with Chroma or FLUX de-distilled workflows (CFG enabled)
Can even be used with flux.1-dev workflows, but you'll need to increase the FluxGuidance to > 4 for adherence most times. Sampler research into "what all works" is ongoing but has been surprising!
For the moment, it is recommended to use CHROMA or classic CFG enabled workflows (including negative prompts!) vs. FLUX unless you want to help research the boundaries with us!
Specific anime/illustration tuning to introduce some lost artistic concepts
NSFW tuned and capable of realism and artistic/anime images. Female anatomy is well represented as a result of CHROMA + C4PACITOR's advance knowledge on these subjects. It tends to lean toward the latter's style.
FLUX LoRA seem to work but testing is ongoing for efficacy.
We have not tested this in any inference tool except ComfyUI yet - YMMV! Keep us posted!
Like our work? Buy us a coffee: https://ko-fi.com/dr34msc4pe
===========================================================================
DR34MSC4PE is
c0ur4ge (training/qa/inference code) /
eraser851 (training/captions/tooling code/data/qa)
===========================================================================
Contributor
Model Details
Discussion
Please log in to leave a comment.




