Update README.md

README.md

@@ -6,4 +6,42 @@ library_name: diffusers
 license: other
 license_name: flux-1-dev-non-commercial-license
 license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
----
+---
+
+For more information (including how to compress models yourself), check out https://huggingface.co/DFloat11
+
+Feel free to request for other models for compression as well, although I currently only know how to compress models based on the Flux architecture.
+
+
+### How to Use
+
+#### `diffusers`
+
+1. Install the DFloat11 pip package *(installs the CUDA kernel automatically; requires a CUDA-compatible GPU and PyTorch installed)*:
+
+    ```bash
+    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:
+    ```python
+    import torch
+    from diffusers import FluxPipeline
+    from dfloat11 import DFloat11Model
+    pipe = FluxPipeline.from_pretrained("mikeyandfriends/PixelWave_FLUX.1-dev_03", torch_dtype=torch.bfloat16)
+    pipe.enable_model_cpu_offload()
+    DFloat11Model.from_pretrained('mingyi456/pixelwave_flux1Dev03-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,
+        guidance_scale=0.0,
+        num_inference_steps=30,
+        max_sequence_length=256,
+        generator=torch.Generator("cpu").manual_seed(0)
+    ).images[0]
+    image.save("PixelWave_FLUX.1-dev_03.png")
+    ```
+#### ComfyUI
+
+Follow the instructions (have not tested myself) here: https://github.com/LeanModels/ComfyUI-DFloat11