FastHunyuanVideo

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

FastHunyuan is an accelerated HunyuanVideo model. It can sample high quality videos with 6 diffusion steps. We provide workflows and models in GGUF format, allowing users with either limited or ample GPU memory to find the model files that best suit their needs.

FastHunyuanVideo >13 files

Name	Size	Target Dir
fast-hunyuan-video-t2v-720p-q3_k_s.gguf	6.09 GB	unet
fast-hunyuan-video-t2v-720p-q3_k_m.gguf	6.24 GB	unet
fast-hunyuan-video-t2v-720p-q4_0.gguf	7.74 GB	unet
fast-hunyuan-video-t2v-720p-q4_k_s.gguf	7.74 GB	unet
fast-hunyuan-video-t2v-720p-q4_k_m.gguf	7.88 GB	unet
fast-hunyuan-video-t2v-720p-q4_1.gguf	8.52 GB	unet
fast-hunyuan-video-t2v-720p-q5_0.gguf	9.30 GB	unet
fast-hunyuan-video-t2v-720p-q5_k_s.gguf	9.30 GB	unet
fast-hunyuan-video-t2v-720p-q5_k_m.gguf	9.45 GB	unet
fast-hunyuan-video-t2v-720p-q5_1.gguf	10.08 GB	unet
fast-hunyuan-video-t2v-720p-q6_k.gguf	10.95 GB	unet
fast-hunyuan-video-t2v-720p-q8_0.gguf	13.97 GB	unet
fast-hunyuan-video-t2v-720p-bf16.gguf	25.65 GB	unet

Hunyuan Video LoRA >2 files

Name	Size	Target Dir
hyvid_lora_adapter.safetensors	323 MB	loras
hyvid-lora-mila3d.safetensors	472 MB	loras

Hunyuan Video VAE >2 files

Name	Size	Target Dir
hunyuan_video_vae_fp8_e4m3fn.safetensors	247 MB	vae
hunyuan_video_vae_bf16.safetensors	493 MB	vae

Flux Text Encoders >4 files

Name	Size	Target Dir
clip_l.safetensors	246 MB	text_encoders
t5xxl_fp8_e4m3fn.safetensors	4.89 GB	text_encoders
t5xxl_fp8_e4m3fn_scaled.safetensors	5.16 GB	text_encoders
t5xxl_fp16.safetensors	9.79 GB	text_encoders

llava llama3 Encoders >2 files

Name	Size	Target Dir
llava_llama3_fp8_scaled.safetensors	9.09 GB	text_encoders
llava_llama3_fp16.safetensors	16.1 GB	text_encoders