Aller au contenu
ModelPrésentéExterne
Télécharger

Ace Step1.5 DF11

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

TypeText modelModèle de baseACE-Step/Ace-Step1.5VersionBClasse

Source du modèle

Type
Text model
Taille du fichier
3,04 GB
Modèle de base
ACE-Step/Ace-Step1.5
Version
vacestep_v1.5_base-DF11
Mis à jour
26 oct. 2026
Téléchargements
322
Source
Hugging Face

Description de la source

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.

Official implementation

This is coming soon, but I suspect that these existing compressed weights might be compatible out-of-the-box with the official implementation.

Compression Details

This is the pattern_dict for compressing ACEStep15-based models in ComfyUI:

pattern_dict_comfyui = {
    r"decoder\.time_embed": (
        "linear_1",
        "linear_2",
        "time_proj",
    ),
    r"decoder\.time_embed_r": (
        "linear_1",
        "linear_2",
        "time_proj",
    ),
    
    r"decoder\.layers\.\d+": (
        "self_attn.q_proj",
        "self_attn.k_proj",
        "self_attn.v_proj",
        "self_attn.o_proj",
        "cross_attn.q_proj",
        "cross_attn.k_proj",
        "cross_attn.v_proj",
        "cross_attn.o_proj",
        "mlp.gate_proj",
        "mlp.up_proj",
        "mlp.down_proj",
    ),
    
    r"encoder\.lyric_encoder\.layers\.\d++": (
        "self_attn.q_proj",
        "self_attn.k_proj",
        "self_attn.v_proj",
        "self_attn.o_proj",
        "mlp.gate_proj",
        "mlp.up_proj",
        "mlp.down_proj",
    ),
    r"encoder\.timbre_encoder\.layers\.\d+": (
        "self_attn.q_proj",
        "self_attn.k_proj",
        "self_attn.v_proj",
        "self_attn.o_proj",
        "mlp.gate_proj",
        "mlp.up_proj",
        "mlp.down_proj",
    ),

    r"tokenizer\.attention_pooler\.layers\.\d+": (
        "self_attn.q_proj",
        "self_attn.k_proj",
        "self_attn.v_proj",
        "self_attn.o_proj",
        "mlp.gate_proj",
        "mlp.up_proj",
        "mlp.down_proj",
    ),

    r"detokenizer\.layers\.\d+": (
        "self_attn.q_proj",
        "self_attn.k_proj",
        "self_attn.v_proj",
        "self_attn.o_proj",
        "mlp.gate_proj",
        "mlp.up_proj",
        "mlp.down_proj",
    ),
}

Sources

1 source
Hugging FacePrincipalVersion 2850a9b90a35234adb65d3f67d66bd9fbbafee12
huggingface.co/mingyi456/Ace-Step1.5-DF11-ComfyUI/tree/2850a9b90a35234adb65d3f67d66bd9fbbafee12

Vérifié 26 oct.

Artefacts du modèle

1 artefact

acestep_v1.5_base-DF11.safetensors

safetensors · 3,04 GB · SHA-256 f9708cf02ebe…8517 · Hugging Face

Télécharger

Extraits de sources

3 extraits

--- license: mit language: - en - zh pipeline_tag: text-to-audio tags: - comfyui - diffusion-single-file base_model: - ACE-Step/Ace-Step1.5 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. #### Official implementation This is coming soon, but I suspect that these existing compressed weights might be compatible out-of-the-box with the official implementation. ### Compression Details This is the `pattern_dict` for compressing ACEStep15-based models in ComfyUI: ```python pattern_dict_comfyui = { r"decoder\.time_embed": ( "linear_1", "linear_2", "time_proj", ), r"decoder\.time_embed_r": ( "linear_1", "linear_2", "time_proj", ), r"decoder\.layers\.\d+": ( "self_attn.q_proj", "self_attn.k_proj", "self_attn.v_proj", "self_attn.o_proj", "cross_attn.q_proj", "cross_attn.k_proj", "cross_attn.v_proj", "cross_attn.o_proj", "mlp.gate_proj", "mlp.up_proj", "mlp.down_proj", ), r"encoder\.lyric_encoder\.layers\.\d++": ( "self_attn.q_proj", "self_attn.k_proj", "self_attn.v_proj", "self_attn.o_proj", "mlp.gate_proj", "mlp.up_proj", "mlp.down_proj", ), r"encoder\.timbre_encoder\.layers\.\d+": ( "self_attn.q_proj", "self_attn.k_proj", "self_attn.v_proj", "self_attn.o_proj", "mlp.gate_proj", "mlp.up_proj", "mlp.down_proj", ), r"tokenizer\.attention_pooler\.layers\.\d+": ( "self_attn.q_proj", "self_attn.k_proj", "self_attn.v_proj", "self_attn.o_proj", "mlp.gate_proj", "mlp.up_proj", "mlp.down_proj", ), r"detokenizer\.layers\.\d+": ( "self_attn.q_proj", "self_attn.k_proj", "self_attn.v_proj", "self_attn.o_proj", "mlp.gate_proj", "mlp.up_proj", "mlp.down_proj", ), } ```

Source context: 322 downloads · 13 likes · Pipeline text-to-audio · Library diffusion-single-file · Repo mingyi456/Ace-Step1.5-DF11-ComfyUI

Source context: 222 downloads · 13 likes · Pipeline text-to-audio · Library diffusion-single-file · Repo mingyi456/Ace-Step1.5-DF11-ComfyUI