Is there any plan to release the checkpoint or the pretrain checkpoint

[trouble-maker007]

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"

[G-U-N]

Please check https://huggingface.co/wangfuyun/Motion-I2V.

[trouble-maker007]

@G-U-N thanks for the quick response, and does checkpoint support for more frame finetune and generate longer video such as 6s?

[TomSuen]

Please check https://huggingface.co/wangfuyun/Motion-I2V.

Hi, I want to know

Motion-I2V/scripts/app.py

Line 408 in 55a4d02

personalized_unet_path = "models/stage2/DreamBooth_LoRA/realistic_unet.ckpt"

Could the personalized_unet_path be changed to any other unet that trained from sd1.5?