Alissonerdx's picture
Update README.md
57a101e verified
metadata
base_model:
  - wikeeyang/SRPO-Refine-Quantized-v1.0
  - rockerBOO/flux.1-dev-SRPO
  - tencent/SRPO
tags:
  - srpo
  - flux-dev
  - flux
pipeline_tag: text-to-image
library_name: diffusers

Flux.1-Dev SRPO LoRAs

These LoRAs were extracted from three sources:

  • the original SRPO (Flux.1-Dev): tencent/SRPO
  • community checkpoint: rockerBOO/flux.1-dev-SRPO
  • community checkpoint (quantized/refined): wikeeyang/SRPO-Refine-Quantized-v1.0

They are designed to provide modular, lightweight adaptations you can mix with other LoRAs, reducing storage and enabling fast experimentation across ranks (8, 16, 32, 64, 128).

Comparison Comparison Comparison Comparison Comparison Comparison Comparison Comparison Comparison Comparison Comparison Comparison Comparison

Example comparison between Flux1-Dev baseline and LoRA extractions

use with 🧨diffusers:

import torch
from diffusers import FluxPipeline

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

pipe.load_lora_weights('Alissonerdx/flux.1-dev-SRPO-LoRas', weight_name='srpo_128_base_R%26Q_model_fp16.safetensors')
pipe.to("cuda")

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

image = pipe(
    prompt, 
    num_inference_steps=28, 
    guidance_scale=5.0,
    generator=torch.Generator("cpu").manual_seed(0)
).images[0]