WorkflowListedExternal

Simple Lora Loader for Hunyuan Video — gguf & lora loaders

A basic workflow for loading a lora to use with Hunyuan video. Modified from the comfyUI example here.

TaskText to videoFamilyHunyuanEstimated VRAMNot yet characterizedBgrade

Runtime profile

Source description

A basic workflow for loading a lora to use with Hunyuan video. Modified from the comfyUI example here.

Loras can be stacked as needed by adding more LoraLoaderModelOnly nodes.

With version to use with GGUF quantized Hunyuan Video models - as requested

Remaining hardware or download-size estimates are not available yet.

AI-generated commentary

AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.

This workflow loads LoRAs for Hunyuan Video, uses Hunyuan Video and LoRA model files, and includes `SaveAnimatedWEBP` for animated WEBP output.

Listed model files include `clip_l.safetensors`, `hathaway style_epoch22.safetensors`, `hunyuan_video_vae_bf16.safetensors`, `Hunyuan/hunyuan-video-t2v-720p-Q3_K_S.gguf`, and `llava-llama-3-8b-v1_1-int4.gguf`.
The workflow includes `SaveAnimatedWEBP` for saving animated WEBP output.

Listed workflow node names include `BasicGuider`, `BasicScheduler`, `CLIPTextEncode`, `DualCLIPLoaderGGUF`, and `EmptyHunyuanLatentVideo`.
Other listed node names are `FluxGuidance`, `KSamplerSelect`, `LoraLoaderModelOnly`, `ModelSamplingSD3`, and `RandomNoise`.
The remaining listed node names are `SamplerCustomAdvanced`, `SaveAnimatedWEBP`, `UnetLoaderGGUF`, `VAEDecodeTiled`, and `VAELoader`.

Stack LoRAs by adding more `LoraLoaderModelOnly` nodes as needed.
For a GGUF-quantized Hunyuan Video model, use the version intended for GGUF models.
Suggestion

Before running, check that the listed model files are available in your setup.
Suggestion

Does this need to be edited?

Sources

1 source

CivitaiPrimary

Verified Jul 20

Source excerpts

1 excerpt

Source context: 2161 downloads · Type Workflows · Base model Hunyuan Video