mingyi456/

PixelWave_FLUX.1-schnell_04-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 3from dfloat11 import DFloat11Model 4pipe = FluxPipeline.from_pretrained("mikeyandfriends/PixelWave_FLUX.1-schnell_04", torch_dtype=torch.bfloat16) 5pipe.enable_model_cpu_offload() 6DFloat11Model.from_pretrained('mingyi456/PixelWave_FLUX.1-schnell_04-DF11', device='cpu', bfloat16_model=pipe.transformer) 7prompt = "A futuristic cityscape at sunset, with flying cars, neon lights, and reflective water canals" 8image = pipe( 9 prompt, 10 guidance_scale=3.5, 11 num_inference_steps=8, 12 max_sequence_length=256, 13 generator=torch.Generator("cpu").manual_seed(0) 14).images[0] 15image.save("PixelWave_FLUX.1-dev_03.png")

ComfyUI