README.md

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
language:
  - en
library_name: diffusers
pipeline_tag: text-to-image
tags:
  - text-to-image
  - diffusers-training
  - diffusers
  - lora
  - flux-diffusers
  - Flux.1-dev
  - image-generation

FLUX.1-dev-LoRA-collections

This repository contains popular LoRAs for FLUX.1-dev model trained by our users at Shakker AI.

Model Cards

• FLUX-dev-lora-blended_realistic_illustration.safetensors
  

1. A style LoRA for blended realistic illustration, by Muertu.
2. The recommended LoRA scale is 1.0, with artistic style blends reality and illustration elements. as tagger word.
3. Find more testing prompts at Shakker-Labs/FLUX.1-dev-LoRA-blended-realistic-illustration.

• FLUX-dev-lora-Black_Myth_Wukong_hyperrealism_v1.safetensors
  

1. A character LoRA for Black Myth: Wukong, by xiongmaowf.
2. The recommended LoRA scale is 1.2, with aiyouxiketang as tagger word.
3. Try testing prompts: a man in armor with a beard and a beard, a man in a costume holding a ball.

Inference

import torch
from diffusers import FluxPipeline

pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16)

# Black Myth: Wukong
pipe.load_lora_weights('Shakker-Labs/FLUX.1-dev-LoRA-collections', weight_name='FLUX-dev-lora-Black_Myth_Wukong_hyperrealism_v1.safetensors')
pipe.fuse_lora(lora_scale=1.2)
pipe.to("cuda")

prompt = "aiyouxiketang, a man in armor with a beard and a beard"

image = pipe(
    prompt, 
    num_inference_steps=24, 
    guidance_scale=5.0,
    generator=torch.Generator("cpu").manual_seed(0)
).images[0]

Acknowledgements

All these models are trained by our copyrighted users. We release these model under their permissions.