|
|
--- |
|
|
license: creativeml-openrail-m |
|
|
language: |
|
|
- en |
|
|
pipeline_tag: text-to-image |
|
|
tags: |
|
|
- comfyui |
|
|
- diffusion-single-file |
|
|
base_model: |
|
|
- cyberdelia/CyberRealisticFlux |
|
|
base_model_relation: quantized |
|
|
--- |
|
|
### Note: Despite the "FP16" in the filename, the original weights [in this repo](https://huggingface.co/cyberdelia/CyberRealisticFlux) are actually in BF16 instead, which makes them safe for DF11 compression. |
|
|
For more information (including how to compress models yourself), check out https://huggingface.co/DFloat11 and https://github.com/LeanModels/DFloat11 |
|
|
|
|
|
Feel free to request for other models for compression as well, although models whose architecture I am unfamiliar with might be slightly tricky for me. |
|
|
|
|
|
### How to Use |
|
|
|
|
|
#### ComfyUI |
|
|
Follow the instructions here: https://github.com/LeanModels/ComfyUI-DFloat11. Alternatively, you can install my own fork of the DF11 ComfyUI custom node: https://github.com/mingyi456/ComfyUI-DFloat11-Extended instead. After installing the DF11 custom node, use the provided workflow [json](CyberRealistic_Flux_V2.5_FP16-DF11-workflow.json), or simply replace the "Load Diffusion Model" node of an existing Kontext workflow with the "DFloat11 Model Loader" node. If you run into any issues, feel free to leave a comment. The workflow is also embedded in the below [png](CyberRealistic_Flux_V2.5_FP16-DF11-workflow.png) image. |
|
|
|
|
|
 |
|
|
|
|
|
#### `diffusers` |
|
|
Refer to this [model](https://huggingface.co/mingyi456/CyberRealisticFlux-DF11) instead. |
|
|
|
|
|
### Compression Details |
|
|
|
|
|
This is the `pattern_dict` for compressing Flux-based models in ComfyUI: |
|
|
|
|
|
```python |
|
|
pattern_dict_comfyui = { |
|
|
"double_blocks\.\d+": ( |
|
|
"img_mod.lin", |
|
|
"img_attn.qkv", |
|
|
"img_attn.proj", |
|
|
"img_mlp.0", |
|
|
"img_mlp.2", |
|
|
"txt_mod.lin", |
|
|
"txt_attn.qkv", |
|
|
"txt_attn.proj", |
|
|
"txt_mlp.0", |
|
|
"txt_mlp.2", |
|
|
), |
|
|
"single_blocks\.\d+": ( |
|
|
"linear1", |
|
|
"linear2", |
|
|
"modulation.lin", |
|
|
), |
|
|
} |
|
|
``` |
