Wan2.1 WanMove

Note: All model files and custom nodes below must be downloaded via the client. If you do not have the client, Download >>>

Motion-controllable Video Generation via Latent Trajectory Guidance. The core idea is to represent the motion condition by propagating the first frame’s features along the trajectory, which can be seamlessly integrated into off-the-shelf image-to-video models (e.g., Wan-I2V-14B) without any architecture change or extra motion modules.

Wan2.1 WanMove >2 files

Name	Size	Target Dir
Wan21-WanMove_fp8_scaled_e4m3fn_KJ.safetensors	16.40 GB	diffusion_models
Wan21-WanMove_fp16.safetensors	32.79 GB	diffusion_models

lightx2v I2V 14B 480p >7 files

Name	Size	Target Dir
lightx2v_I2V_14B_480p_cfg_step_distill_rank4_bf16.safetensors	54.41 MB	loras
lightx2v_I2V_14B_480p_cfg_step_distill_rank8_bf16.safetensors	99.98 MB	loras
lightx2v_I2V_14B_480p_cfg_step_distill_rank16_bf16.safetensors	191.13 MB	loras
lightx2v_I2V_14B_480p_cfg_step_distill_rank32_bf16.safetensors	373.42 MB	loras
lightx2v_I2V_14B_480p_cfg_step_distill_rank64_bf16.safetensors	738.01 MB	loras
lightx2v_I2V_14B_480p_cfg_step_distill_rank128_bf16.safetensors	1.47 GB	loras
lightx2v_I2V_14B_480p_cfg_step_distill_rank256_bf16.safetensors	2.92 GB	loras

umt5_xxl >2 files

Name	Size	Target Dir
umt5_xxl_fp8_e4m3fn_scaled.safetensors	6.74 GB	text_encoders
umt5_xxl_fp16.safetensors	11.4 GB	text_encoders

Wan2 VAE >4 files

Name	Size	Target Dir
wan_2.1_vae.safetensors	254 MB	vae
wan2.2_vae.safetensors	1.41 GB	vae
Wan2_1_VAE_bf16.safetensors	254 MB	vae
Wan2_1_VAE_fp32.safetensors	508 MB	vae

clip_vision_h >1 files

Name	Size	Target Dir
clip_vision_h.safetensors	1.26 GB	clip_vision