Saltar al contenido
ModelPublicadoExterno
Descargar

Ace Step1.5 XL DF11

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

TipoText modelModelo baseACE-Step/acestep-v15-xl-baseVersiónBcalidad

Fuente del modelo

Tipo
Text model
Tamaño del archivo
6,33 GB
Modelo base
ACE-Step/acestep-v15-xl-base
Versión
vBF16
Actualizado
7 oct 2026
Descargas
343
Fuente
Hugging Face

Descripción de la fuente

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 compression:

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",
    ),
}

Fuentes

1 fuente
Hugging FacePrincipalVersión a73e1c42054625c4aa3fc6089a8b23cac8a26bcd
huggingface.co/mingyi456/Ace-Step1.5-XL-DF11-ComfyUI/tree/a73e1c42054625c4aa3fc6089a8b23cac8a26bcd

Verificado 3 sept

Artefactos del modelo

1 artefacto

acestep_v1.5_xl_base_bf16-DF11.safetensors

safetensors · BF16 · 6,33 GB · SHA-256 febbef5385da…684b · Hugging Face

Descargar

Extractos de fuentes

3 extractos

--- license: mit language: - en - zh pipeline_tag: text-to-audio tags: - comfyui - diffusion-single-file base_model: - ACE-Step/acestep-v15-xl-sft - ACE-Step/acestep-v15-xl-base - ACE-Step/acestep-v15-xl-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. #### 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 compression: ```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: 343 downloads · 7 likes · Pipeline text-to-audio · Library diffusion-single-file · Repo mingyi456/Ace-Step1.5-XL-DF11-ComfyUI

Source context: 329 downloads · 6 likes · Pipeline text-to-audio · Library diffusion-single-file · Repo mingyi456/Ace-Step1.5-XL-DF11-ComfyUI