DFloat11/

FLUX.1-Canny-dev-DF11

DFloat11 Compressed Model: black-forest-labs/FLUX.1-Canny-dev

🔍 How It Works

• No CPU decompression or host-device data transfer: all operations are handled entirely on the GPU.
• DFloat11 is much faster than CPU-offloading approaches, enabling practical deployment in memory-constrained environments.
• The compression is fully lossless, guaranteeing that the model’s outputs are bit-for-bit identical to those of the original model.

🔧 How to Use

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

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

   1import torch 2from controlnet_aux import CannyDetector 3from diffusers import FluxControlPipeline 4from diffusers.utils import load_image 5from dfloat11 import DFloat11Model 6 7pipe = FluxControlPipeline.from_pretrained("black-forest-labs/FLUX.1-Canny-dev", torch_dtype=torch.bfloat16) 8pipe.enable_model_cpu_offload() 9 10DFloat11Model.from_pretrained('DFloat11/FLUX.1-Canny-dev-DF11', device='cpu', bfloat16_model=pipe.transformer) 11 12prompt = "A robot made of exotic candies and chocolates of different kinds. The background is filled with confetti and celebratory gifts." 13control_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/robot.png") 14 15processor = CannyDetector() 16control_image = processor(control_image, low_threshold=50, high_threshold=200, detect_resolution=1024, image_resolution=1024) 17 18image = pipe( 19 prompt=prompt, 20 control_image=control_image, 21 height=1024, 22 width=1024, 23 num_inference_steps=50, 24 guidance_scale=30.0, 25).images[0] 26image.save("output.png")

📄 Learn More

• Paper: 70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float
• GitHub: https://github.com/LeanModels/DFloat11
• HuggingFace: https://huggingface.co/DFloat11