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

|
10/10/2025
|
10:47:07 PM
| Discussion|
0
A young girl in black-and-white attire waves a magical paintbrush, releasing vibrant watercolor colors that transform a grayscale environment into a lively, colorful scene with trees and birds.
Young woman sitting on a skateboard wearing a bright orange sports jacket and shorts, decorated with colorful paint splatters, set in an urban street with vibrant yellow and red buildings under a bright sky.
Futuristic cybernetic humanoid wearing a bright red jacket with warning signs, featuring a robotic face covered in intricate mechanical parts and glowing green and orange lights.
A film fashion portrait of a tall, thin young woman with long natural dark red hair and big green eyes, standing in an aisle of an urban record shop wearing a cropped tank top and denim shorts.

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 - unspecified

other models

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

Tips

Select Low Bits: Automatic (fp16 LoRA) in Diffusion when using NF4 and base models with LoRas in Forge WebUI.

Use only FP8 and FP16 models without converting to NF4 for compatibility with Comfy WebUI.

Experiment with the model across different art styles as it handles them very well.

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
Pablo Oliveira Style - Flux1.D - v1.0
Next
MagicalPony - MagicalPony3

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