Verus_Vision_1.0b / README.md
SG161222's picture
Update README.md
19bbe6c verified
|
raw
history blame
1.37 kB
metadata
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md

Verus Vision — Model for Realistic Image Generation

Overview

Verus Vision is a fine-tuned model designed for generating high-quality, realistic images. Built on the Flux Dev (de-distill) model with 12 billion parameters.

You can support me directly on my Boosty


How to Use Transformer Version

For ComfyUI:

  • Place the AE in the following path: ComfyUI_windows_portable\ComfyUI\models\vae
  • Place Clip-L and T5XXL in the following path: ComfyUI_windows_portable\ComfyUI\models\clip
  • Place the Transformer in the following path: ComfyUI_windows_portable\ComfyUI\models\unet or ComfyUI_windows_portable\ComfyUI\models\diffusion_models

Optimal Generation Settings

  • Sampling Method and Schedule Type: Euler Beta
  • Sampling Steps: 25+
  • CFG Scale: 3.5

Warning: Do not use a negative prompt as it can lead to the generation of images with artifacts and distortions.


Limitations

  • This version of the model does not have a variety of styles and is intended for realism and photorealism.
  • There may be issues with anatomy and text.