modelli/CRUX - CRUX-v1

CRUX - CRUX-v1

|
2/16/2026
|
9:17:58 PM
| Discussion|
0
Sunset over a city visible through dense forest trees with lush green foliage in the foreground
Digital painting of a young woman angel in abstract darkness with deep red and black background, inspired by Ashley Wood's style.

Prompt Negativi Consigliati

negative prompts

Parametri Consigliati

samplers

res_2m, Euler

steps

28 - 42

Suggerimenti

Can be used with Chroma or FLUX de-distilled workflows (CFG enabled).

Increase FluxGuidance > 4 for adherence when using flux.1-dev workflows.

Preferred usage is with CHROMA or classic CFG enabled workflows including negative prompts.

Testing with flux LoRA is ongoing for effectiveness.

Model has only been tested with ComfyUI inference tool; results may vary with others.

Punti Salienti della Versione

The first release of CRUX - let us know what you think and be sure to share your generations below!

Sponsor del Creatore

Like our work? Buy us a coffee: https://ko-fi.com/dr34msc4pe

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)

===========================================================================

Contributore

Precedente
Joseph Pennell Style XL Nr. 1 - v1.0
Successivo
Epic Landscape Generator XL - Epic Landscape Generator XL

Dettagli del Modello

Tipo di modello

Checkpoint

Modello base

Flux.1 D

Versione del modello

CRUX-v1

Hash del modello

81984ba629

Creatore

Discussione

Per favore log in per lasciare un commento.

Immagini di CRUX - CRUX-v1

Sunset over a city visible through dense forest trees with lush green foliage in the foreground
Digital painting of a young woman angel in abstract darkness with deep red and black background, inspired by Ashley Wood's style.

Immagini con modello base

Photorealistic scene of undead characters including zombies and skeletons walking through a spooky Halloween cemetery filled with glowing jack-o'-lantern pumpkins and desiccated trees in a dark, foggy atmosphere.

Immagini con chroma

A powerful flaming tiger roaring with intensity, surrounded by vibrant blue and orange flames, created using stable diffusion AI technology.
A highly detailed, AI generated dark fantasy image of a ferocious werewolf roaring under a stormy night sky, using Stable Diffusion.

Immagini con flux

A sultry steampunk heroine wearing bronze goggles on her forehead, dressed in a revealing mechanic outfit with a leather jacket, standing in an industrial workshop surrounded by intricate machinery.
A Windwaker style cartoon featuring a small boy standing at a fork in the road with a bright castle labeled 'Family, Friends, Happiness' on the left and a dark castle with flames and the word 'Flux' on the right.
A sweeping aerial view of a futuristic desert metropolis with towering bio-engineered structures featuring reflective glass and organic curves, set amidst sand dunes and ancient ruins with a winding geothermal channel.
Close-up of Itachi with pale skin, bright red eyes, and long dark hair wearing a headband with the Konoha symbol and a black cloak with red cloud patterns, surrounded by flying crows.
Young woman with short black hair wearing a tank top and shorts, sitting drunk against a green tiled wall on a concrete floor in an underground club, with empty beer bottles nearby.
A tired market vendor wearing a dark hoodie sits behind a cluttered counter in a dimly lit, dystopian setting with a hanging light bulb illuminating tools and supplies.
Delicate watercolor depiction of crystallized hoarfrost formations clinging to bare winter branches, featuring soft blue-white luminescence and a lavender-cerulean background.
A person in a hoodie interacts with an abstract scene dominated by a vibrant lightning bolt, surrounded by swirling patterns and glowing orbs.

Immagini con hybrid

Adorable pink and purple hybrid dragon creature with fluffy scales and large expressive eyes sitting on a log in a vivid enchanted forest
A creepy mechanical chimera blending a bee, terminator, and fan with robotic limbs and large cartoonish eyes, showing a humorous caricature style.
A colossal biomechanical hybrid with glowing orange eyes looms over a lone human figure standing in a dark, eerie landscape illuminated by fiery light.
A furry hybrid cat lounging on a sofa in a tree house with medieval fantasy elements, wearing a dress under low light.
Cute bee on a dripping honeycomb, AI generated image using stable diffusion.