• Stefy Lanza (nextime / spora )'s avatar
    Fix base model detection for Wan LoRA adapters · 410f97e9
    Stefy Lanza (nextime / spora ) authored
    For Wan LoRA adapters, skip reading base_model from stored config
    (which may have incorrect values like T2V instead of I2V).
    Instead, always infer from LoRA ID by checking for 'i2v' in the name.
    
    This ensures wan2_2_i2v_general_nsfw_lora uses the correct
    Wan-AI/Wan2.2-I2V-A14B-Diffusers base model instead of the
    incorrect Wan-AI/Wan2.2-T2V-A14B-Diffusers.
    410f97e9
Name
Last commit
Last update
static Loading commit data...
templates Loading commit data...
.gitignore Loading commit data...
EXAMPLES.md Loading commit data...
LICENSE.md Loading commit data...
README.md Loading commit data...
SKILL.md Loading commit data...
check_model.py Loading commit data...
check_pipelines.py Loading commit data...
debug_model_select.py Loading commit data...
logo.png Loading commit data...
requirements.txt Loading commit data...
screenshot.png Loading commit data...
videogen.py Loading commit data...
videogen_mcp_server.py Loading commit data...
videogen_models.json Loading commit data...
webapp.py Loading commit data...