Lens Turbo DF11

--- license: mit language: - en pipeline_tag: text-to-image tags: - comfyui - diffusion-single-file base_model: - microsoft/Lens-Turbo base_model_relation: quantized --- 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 Install the ComfyUI DFloat11 Extended node via the ComfyUI manager. After installing, simply replace the "Load Diffusion Model" node of an existing workflow with the "Load Diffusion Model" node. If you run into any issues, feel free to leave a comment. #### `diffusers` Currently, this model is not supported in `diffusers`. ### Compression Details This is the `pattern_dict` for compression: ```python pattern_dict_comfyui = { r"txt_in": [], r"transformer_blocks\.\d+": ( "attn.img_qkv", "attn.txt_qkv", "attn.to_out.0", "img_mod.1", "img_mlp.w1", "img_mlp.w2", "img_mlp.w3", "txt_mod.1", "txt_mlp.w1", "txt_mlp.w2", "txt_mlp.w3", ), } ```

Source context: 9 downloads · 1 likes · Pipeline text-to-image · Library diffusion-single-file · Repo mingyi456/Lens-Turbo-DF11-ComfyUI

Source context: 88 downloads · 1 likes · Pipeline text-to-image · Library diffusion-single-file · Repo mingyi456/Lens-Turbo-DF11-ComfyUI