ComfyUI Node: Realtime LoRA Trainer (SDXL - sd-scripts)

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

Inputs

inputcount INT
images_path STRING
sd_scripts_path STRING
ckpt_name
    caption STRING
    training_steps INT
    learning_rate FLOAT
    lora_rank INT
    vram_mode
    • Min (512px)
    • Low (768px)
    • Max (1024px)
    keep_lora BOOLEAN
    output_name STRING
    custom_python_exe STRING
    no_half_vae BOOLEAN
    image_1 IMAGE
    caption_1 STRING
    image_2 IMAGE
    caption_2 STRING
    image_3 IMAGE
    caption_3 STRING
    image_4 IMAGE
    caption_4 STRING

    Outputs

    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 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