Skip to content
ModelListedExternal
Download

Chroma Unlocked v48 Detail Calibrated DF11

For more information (including how to compress models yourself), check out and

Sourcehuggingface.co/mingyi456/chroma-unlocked-v48-detail-calibrated-DF11-ComfyUI/tree/77d38986c38a9a73af4b81c00d95a16fd6eb7999
KindUNetBase modellodestones/ChromaVersionBgrade

Model source

Kind
UNet
File size
11.3 GB
Base model
lodestones/Chroma
Version
vchroma-unlocked-v48-detail-calibrated-DF11-old
Updated
Oct 2, 2026
Downloads
54
Tasks
Text to image
Source
Hugging Face

Source description

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

Refer to this model instead.

Compression Details

This is the pattern_dict for compression:

pattern_dict_comfyui = {
    r"distilled_guidance_layer\.layers\.\d+": (
        "in_layer",
        "out_layer"        
    ),
    r"double_blocks\.\d+": (
        "img_attn.qkv",
        "img_attn.proj",
        "img_mlp.0",
        "img_mlp.2",
        "txt_attn.qkv",
        "txt_attn.proj",
        "txt_mlp.0",
        "txt_mlp.2",
    ),
    r"single_blocks\.\d+": (
        "linear1",
        "linear2",
    ),
}

Sources

1 source
Hugging FacePrimaryVersion 77d38986c38a9a73af4b81c00d95a16fd6eb7999
huggingface.co/mingyi456/chroma-unlocked-v48-detail-calibrated-DF11-ComfyUI/tree/77d38986c38a9a73af4b81c00d95a16fd6eb7999

Verified Oct 2

Model artifacts

1 artifact

chroma-unlocked-v48-detail-calibrated-DF11-old.safetensors

safetensors · 11.3 GB · SHA-256 9067dbad67a3…763a · Hugging Face

Download file

Source excerpts

3 excerpts
ReadmeJul 16huggingface.co/mingyi456/chroma-unlocked-v48-detail-calibrated-DF11-ComfyUI

--- license: apache-2.0 language: - en pipeline_tag: text-to-image tags: - comfyui - diffusion-single-file base_model: - lodestones/Chroma 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` Refer to this [model](https://huggingface.co/mingyi456/chroma-unlocked-v48-detail-calibrated-DF11) instead. ### Compression Details This is the `pattern_dict` for compression: ```python pattern_dict_comfyui = { r"distilled_guidance_layer\.layers\.\d+": ( "in_layer", "out_layer" ), r"double_blocks\.\d+": ( "img_attn.qkv", "img_attn.proj", "img_mlp.0", "img_mlp.2", "txt_attn.qkv", "txt_attn.proj", "txt_mlp.0", "txt_mlp.2", ), r"single_blocks\.\d+": ( "linear1", "linear2", ), } ```

NoteOct 2huggingface.co/mingyi456/chroma-unlocked-v48-detail-calibrated-DF11-ComfyUI

Source context: 54 downloads · 0 likes · Pipeline text-to-image · Library diffusion-single-file · Repo mingyi456/chroma-unlocked-v48-detail-calibrated-DF11-ComfyUI

NoteJul 16huggingface.co/mingyi456/chroma-unlocked-v48-detail-calibrated-DF11-ComfyUI

Source context: 42 downloads · 0 likes · Pipeline text-to-image · Library diffusion-single-file · Repo mingyi456/chroma-unlocked-v48-detail-calibrated-DF11-ComfyUI