Have a ComfyUI workflow? Get a readable Workflow Doc in your browser.Make a workflow readable.Try it now ↗
Runtime profile
Source description
jhj Hunyuan Video workflows
Only txt2vid workflow for now.
It loads GGUF from:
https://huggingface.co/city96/HunyuanVideo-gguf/tree/main
It first generates video with smaller resolution -> then upscales for the limits of VRAM.
Probably you better find a better upscaling model for your own purpose.
The version is controlled in :
AI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
jhj Hunyuan Video Workflows is for text-to-video generation: it takes text as input, produces video, and upscales the result.
It generates video at a smaller resolution first, then upscales it for VRAM limits.
The documented input is text for text-to-video, and the documented output is video.
It uses the Hunyuan Video base model and is published by Jhj0517.
Listed model files are: hunyuan-video-t2v-720p-Q4_K_S.gguf, hunyuan_video_vae_bf16.safetensors, clip_l.safetensors, llava_llama3_fp8_scaled.safetensors, and 4x_foolhardy_Remacri.pth.
Listed nodes include: CLIPTextEncode, CR Apply LoRA Stack, DualCLIPLoader, easy loraStack, EmptyHunyuanLatentVideo, ImageScale, ImageUpscaleWithModel, KSamplerAdvanced, UnetLoaderGGUF, UpscaleModelLoader, VAEDecodeTiled, VAELoader, and VHS_VideoCombine.
Before use, verify that your setup includes the listed files and nodes.
Suggestion · not verified
It loads GGUF from the city96/HunyuanVideo-gguf repository on Hugging Face.
Version information is controlled in the jhj0517/ComfyUI-workflows repository.
Consider a different upscaling model for your use case.
Suggestion · not verified
Only text-to-video is documented; image-to-video is not described.
Does this need to be edited?
Sign in to send an edit request.
Sources
1 sourceSource excerpts
1 excerptSource context: 429 downloads · Type Workflows · Base model Hunyuan Video
Estimated VRAM requirement
Estimate unavailable
299 MB across 2 of 10 model files. Model file total + 25% loading overhead + 2 GB execution buffer, rounded up.
Requirements
18 requirementsUpscaler · 63.9 MB · PTH · Unknown
Text encoder · 235 MB · SAFETENSORS · Unknown
DualCLIPLoader
Not resolvedText encoder · Unknown
hunyuan_video_vae_bf16.safetensors
PossibleVAE · Unknown
hunyuan-video-t2v-720p-Q4_K_S.gguf
Not resolvedCheckpoint · Unknown
ImageUpscaleWithModel
Not resolvedUpscaler · Unknown
llava_llama3_fp8_scaled.safetensors
ConflictText encoder · Unknown
UpscaleModelLoader
Not resolvedUpscaler · Unknown
VAEDecodeTiled
Not resolvedVAE · Unknown
VAELoader
Not resolvedVAE · Unknown
CLIPTextEncode
Not resolvedNode pack · Unknown
CR Apply LoRA Stack
Not resolvedNode pack · Unknown
easy loraStack
Not resolvedNode pack · Unknown
Node pack · Unknown
ImageScale
Not resolvedNode pack · Unknown
KSamplerAdvanced
Not resolvedNode pack · Unknown
UnetLoaderGGUF
Not resolvedNode pack · Unknown
VHS_VideoCombine
Not resolvedNode pack · Unknown
