DFloat11 / FLUX.1-dev-DF11

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

This is a losslessly compressed version of black-forest-labs/FLUX.1-dev using our custom DFloat11 format. The outputs of this compressed model are bit-for-bit identical to the original BFloat16 model, while reducing GPU memory consumption by approximately 30% .

🔍 How It Works

DFloat11 compresses model weights using Huffman coding of BFloat16 exponent bits, combined with hardware-aware algorithmic designs that enable efficient on-the-fly decompression directly on the GPU. During inference, the weights remain compressed in GPU memory and are decompressed just before matrix multiplications , then immediately discarded after use to minimize memory footprint.

Key benefits:

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

   pip install dfloat11[cuda12]
   # or if you have CUDA version 11:
   # pip install dfloat11[cuda11]
   

2. To use the DFloat11 model, run the following example code in Python:

   import torch
   from diffusers import FluxPipeline
   from dfloat11 import DFloat11Model
   
   pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16)
   pipe.enable_model_cpu_offload()
   
   DFloat11Model.from_pretrained('DFloat11/FLUX.1-dev-DF11', device='cpu', bfloat16_model=pipe.transformer)
   
   prompt = "A futuristic cityscape at sunset, with flying cars, neon lights, and reflective water canals"
   image = pipe(
       prompt,
       width=1920,
       height=1440,
       guidance_scale=3.5,
       num_inference_steps=50,
       max_sequence_length=512,
       generator=torch.Generator(device="cuda").manual_seed(0)
   ).images[0]
   
   image.save("image.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