mingyi456/

SRPO-DF11

How to Use

diffusers

1. Install the DFloat11 pip package (installs the CUDA kernel automatically; requires a CUDA-compatible GPU and PyTorch installed):
   bash

   1pip install dfloat11[cuda12] 2# or if you have CUDA version 11: 3# pip install dfloat11[cuda11]
2. To use the DFloat11 model, run the following example code in Python:
   python

   1import torch 2from diffusers import FluxPipeline, FluxTransformer2DModel 3from dfloat11 import DFloat11Model 4with no_init_weights(): 5 transformer = FluxTransformer2DModel.from_config( 6 FluxTransformer2DModel.load_config( 7 "black-forest-labs/FLUX.1-dev", 8 subfolder="transformer" 9 ), 10 torch_dtype=torch.bfloat16 11 ).to(torch.bfloat16) 12 13pipe = FluxPipeline.from_pretrained( 14 "black-forest-labs/FLUX.1-dev", 15 transformer=transformer, 16 torch_dtype=torch.bfloat16 17) 18DFloat11Model.from_pretrained('mingyi456/SRPO-DF11', device='cpu', bfloat16_model=pipe.transformer) 19pipe.enable_model_cpu_offload() 20prompt = "A futuristic cityscape at sunset, with flying cars, neon lights, and reflective water canals" 21image = pipe( 22 prompt, 23 guidance_scale=3.5, 24 num_inference_steps=30, 25 max_sequence_length=256, 26 generator=torch.Generator("cpu").manual_seed(0) 27).images[0] 28image.save("SPRO.png")

ComfyUI