models/Flux Art Fusion - v1.0 fp8 NF4 AiO - v1.0 fp8 NF4 AiO

Flux Art Fusion - v1.0 fp8 NF4 AiO - v1.0 fp8 NF4 AiO

|
10/9/2025
|
9:27:06 AM
| Discussion|
0
Young girl in black-and-white world holding a magical paintbrush, creating vibrant watercolor colors that transform the monochrome environment with trees, birds, and a colorful road.
Young woman sitting on a skateboard in a colorful urban street, wearing a bright orange sports jacket and paint-splattered shorts, with a vivid yellow and red city background.
Cybernetic humanoid wearing a worn red jacket with mechanical and high-tech components, glowing green and orange lights on a black robotic face in a dystopian environment.
A tall, thin young woman with long natural dark red hair, freckles, and big green eyes stands in the aisle of an old urban record shop. She wears a loose cropped tank top and tattered denim shorts in a bohemian style.

Recommended Negative Prompts

distorted, noisy, out of focus, deformed, ugly, blurry

Recommended Parameters

samplers

Euler, Flux Realistic

steps

20 - 30

cfg

1

resolution

768x1280

vae

VAE T5xxl

other models

Flux_art_fusion_fp8nf4 (22d999d3df), anime_fl_Flux_fp8nf4 (0909e9c60f), TQ - Glitch Aura Flux _ Halloween Collection_v.1.5 (e4ee6ecd6ab9)

Tips

Use Low Bits: Automatic (fp16 LoRA) in Diffusion for best results in Forge WebUI.

For Comfy UI with Loras, use only FP8 and FP16 models without converting to NF4.

Don't be afraid to experiment with complex prompts as the model surprises with its capabilities.

NF4 models converted to bnb nf4 by mixing Flux1 dev with VAE, T5xxl and Clip-l full fp32 text encoders. Also added a few of my favorite Loras with very little influence. All included!

  • NF4 and base models work well with the Loras in the Forge WebUI that I create in. Don't forget to select Low Bits: Automatic (fp16 LoRA) in Diffusion.

  • To work in Comfy with Loras, use only FP8 and FP16 models without converting to NF4.

I finally made a GUFF version of the model) I'm sorry for the long wait, I didn't have enough time.

The models handle a variety of art directions very well. They do especially well with painting and drawn art. But it is also good at realism as well. Don't be afraid to experiment. I've spent many weeks exploring the model's capabilities, but it surprises me every time.))

NF4 models are a bit more accurate than the familiar NF4 v2. I've done a lot of generation with complex cues to assert this. And I am completely satisfied with the way these models understand me. With simple cues I didn't notice any difference.

In Forge WebUI, I select Euler or Flux Realistic samplers, schedule type: Simple. CFG: 1, number of steps 20-30.

Generated outputs can be used for personal, scientific, and commercial purposes as described in the flux-1-dev-non-commercial-license

Please upload your images directly from this page. Because the site does not recognize the hash of the model. Thank you all for your support!

Previous
ColorfulAsianGirl Flux 彩璃Flux - Beta
Next
Jib Mix Realistic XL - v17.0 Smoke & Sheen

Model Details

Model type

Checkpoint

Base model

Flux.1 D

Model version

v1.0 fp8 NF4 AiO

Model hash

9801367f85

Creator

Discussion

Please log in to leave a comment.

Images by Flux Art Fusion - v1.0 fp8 NF4 AiO - v1.0 fp8 NF4 AiO

anime Images

art Images

drawing Images

photorealistic Images

sexy Images