Anitrait FX - PE

LORA
Original


Updated:

71

Generate simple anime style portraits for Flux Dev.

(Currently Works best for Simple Prompts Only!)

Still in BETA phase, expect instabilities.

BETA is split into 2: E7 and E5. E5 is less "fried" than E7 so you can try and compare them.

Trained on 50 portrait (1:1 ratio) images that is generated via AnimagineXL v3.1.

The purpose of this model is solely based on personal preference since I don't like the original anime style of Flux Dev.

Changelog is available in version info.

Any feedback and any type of roastery is appreciated! Hit me on the comments or Tensor discord server.

Thank you for using this model in your image generation.

Version Detail

FLUX.1
5
A less "fried" version of Anitrait FX. May or may not give you better hands than E7 version. Is this one better than E7? I don't know, you tell me. Trigger words at the end of prompt. For weight you can try 0.6. If flux still gives you realistic stuff, try putting 'anime' in prompt. Changelog (Beta 2): > Improved image quality over Beta 1 > Trigger word changed to ATRFX and anime (anime is for guaranteed trigger, but not using it can sometimes mix the style a bit so it's optional) > This one is a bit stronger so if you think 0.6 weight is still kinda too strong, you can try lowering it. Known issue: > Feet sucks, for now > Hand sometimes sucks

Project Permissions

    Use Permissions

  • Use in TENSOR Online

  • As a online training base model on TENSOR

  • Use without crediting me

  • Share merges of this model

  • Use different permissions on merges

    Commercial Use

  • Sell generated contents

  • Use on generation services

  • Sell this model or merges

Comments

Related Posts

Describe the image you want to generate, then press Enter to send.