Open trouble-maker007 opened 1 month ago
Please check https://huggingface.co/wangfuyun/Motion-I2V.
@G-U-N thanks for the quick response, and does checkpoint support for more frame finetune and generate longer video such as 6s?
Please check https://huggingface.co/wangfuyun/Motion-I2V.
Hi, I want to know https://github.com/G-U-N/Motion-I2V/blob/55a4d02190a60f0695c3979d637a09ae4fee2609/scripts/app.py#L408
Could thepersonalized_unet_path
be changed to any other unet that trained from sd1.5?
pretrained checkpoint :
output_dir: "outputs_ctrl_flow_gen" pretrained_model_path: "models/stage1/StableDiffusion-FlowGen/" vae_pretrained_path: "models/stage1/StableDiffusion-FlowGen/vae_flow/diffusion_pytorch_model.bin" resumed_model_path: "models/stage1/StableDiffusion-FlowGen/unet/diffusion_pytorch_model.bin"