Friendly Hunyuan Video 1.5

Important: if you have any error you should update your ComfyUI to nightly version!

Welcome to my 💫🎦 Friendly Hunyuan Video 1.5 (All-in-One T2V, I2V, Audio & Interpolation)

✨ Less mess, more magic

Hunyuan Video 1.5 is a new video generation model with 8.3b parameters under the hood. This makes it a competitor to local Wan models. Thanks to the new 480p step-distilled model (4-12 steps), it generates even slightly faster than Wan 2.2.

🎵 Soundtrack version is here! Create videos with high-quality stereo sound using a friendly workflow! Adjust the volume to your liking (unique feature).

v1.2 based on MultiGPU optimization.

💻 System requirements:

• Minimum system requirements for 480P fp8 models (less VRAM consumption):

RTX 3000-s, 6GB VRAM, 45GB+ RAM, 8-core processor, SSD, latest ComfyUI

• Minimum system requirements for 720p fp16 (better quality):

RTX 3000-s, 12GB VRAM, 45GB+ RAM, 8-core processor, SSD, latest ComfyUI

📌 Detailed tips and links to models in the workflow

✨ Workflow features:

• Friendly all-in-one interface with step by step logics: image or text generation, audio, and interpolation

• Convenient one-click mode switching

• Workflow based on new Hunyuan Video 1.5 step distilled model, allowing generation in 8-12 steps. Hunyuan Video Foley is responsible for generating high-quality sound

• Unique volume control function

• Performance optimization without sacrificing quality for systems with 6GB of video memory or more. 45GB+ RAM recommended

• VAE optimization for low VRAM consumption

• Additional color match settings

• Additional image sharpness settings

• Detailed tooltips and links to models

🤗🙏🏼 Thanks to Tencent Team

Original repo — GitHub