ComfyUI Node: Selective LoRA Loader (Z-Image)

Authored by shootthesound

Created

Updated

538 stars

Run ComfyUI workflows without the setup

No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.

Category

loaders/lora

Inputs

model MODEL
clip CLIP
lora_name
    strength FLOAT
    preset
    • All Layers
    • All Off
    • Late Only (20-29)
    • Mid-Late (15-29)
    • Skip Early (10-29)
    • Mid Only (10-19)
    • Early Only (0-9)
    • Peak Impact (18-25)
    • Face Priority (16-24)
    • Face Priority Aggressive (14-25)
    • Evens Only
    • Odds Only
    • Custom
    layer_0 BOOLEAN
    layer_0_str FLOAT
    layer_1 BOOLEAN
    layer_1_str FLOAT
    layer_2 BOOLEAN
    layer_2_str FLOAT
    layer_3 BOOLEAN
    layer_3_str FLOAT
    layer_4 BOOLEAN
    layer_4_str FLOAT
    layer_5 BOOLEAN
    layer_5_str FLOAT
    layer_6 BOOLEAN
    layer_6_str FLOAT
    layer_7 BOOLEAN
    layer_7_str FLOAT
    layer_8 BOOLEAN
    layer_8_str FLOAT
    layer_9 BOOLEAN
    layer_9_str FLOAT
    layer_10 BOOLEAN
    layer_10_str FLOAT
    layer_11 BOOLEAN
    layer_11_str FLOAT
    layer_12 BOOLEAN
    layer_12_str FLOAT
    layer_13 BOOLEAN
    layer_13_str FLOAT
    layer_14 BOOLEAN
    layer_14_str FLOAT
    layer_15 BOOLEAN
    layer_15_str FLOAT
    layer_16 BOOLEAN
    layer_16_str FLOAT
    layer_17 BOOLEAN
    layer_17_str FLOAT
    layer_18 BOOLEAN
    layer_18_str FLOAT
    layer_19 BOOLEAN
    layer_19_str FLOAT
    layer_20 BOOLEAN
    layer_20_str FLOAT
    layer_21 BOOLEAN
    layer_21_str FLOAT
    layer_22 BOOLEAN
    layer_22_str FLOAT
    layer_23 BOOLEAN
    layer_23_str FLOAT
    layer_24 BOOLEAN
    layer_24_str FLOAT
    layer_25 BOOLEAN
    layer_25_str FLOAT
    layer_26 BOOLEAN
    layer_26_str FLOAT
    layer_27 BOOLEAN
    layer_27_str FLOAT
    layer_28 BOOLEAN
    layer_28_str FLOAT
    layer_29 BOOLEAN
    layer_29_str FLOAT
    other_weights BOOLEAN
    other_weights_str FLOAT
    lora_path_opt STRING
    analysis_json STRING

    Outputs

    MODEL

    CLIP

    STRING

    Extension: Realtime LoRA Trainer

    Train, analyze, selectively load, and extract/merge LoRAs inside ComfyUI. Supports Z-Image, Qwen Image, Qwen Image Edit, SDXL, FLUX, FLUX Klein, Wan 2.2, and SD 1.5. Includes LoRA layer analyzers, selective block loaders, model layer editors, and text-encoder debiasing/inspection tools.

    Authored by shootthesound

    View Nodes

    Looking for a different node?

    More nodes in Realtime LoRA Trainer

    Other loaders/lora nodes

    Run ComfyUI workflows without the setup

    No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.

    Learn more