Essential for lip-syncing in videos: The strongest video lip synchronization latentsync1.5

Load videos longer than 10 seconds Recording Generate lip-sync videos
For more detailed parameters, please adjust in the workflow

Seed: Random seed for reproducible results (default: 1247)

Lip expression: Controls the vividness of lip movements (default: 1.5)
High values (2.0 3.0): More pronounced lip movements, better suited for expressive speech
Low values (1.0 1.5): Subtler lip movements, better suited for calm speech
This parameter affects the model's guidance scale, balancing between natural movements and lip-sync accuracy

Inference steps: Number of denoising steps during the inference process (default: 20)
High values (30 50): Better quality results but slower processing speed
Low values (10 15): Faster processing speed but potentially lower quality
The default value of 20 usually provides a good balance between quality and speed

Invitation code 【rh v1312】
https://www.runninghub.cn/?inviteCode=rh v1312
Use this code to get a reward of 1000 RH coins (equivalent to running more than 20 videos and hundreds of images)

You can also join Ashuo's member group, public account: Ashuo talks AI, WeChat yumengashuo
Community provides:
1. Exclusive advanced workflows for ComfyUI
2. Solutions to various difficult problems, answers to all questions
3. Local integration package to resolve environment conflicts, 100 original workflows
4. Cloud image synchronization (even low computer configurations can play)

Xiangong Cloud also updates synchronously, suitable for insufficient configurations
If you don't want to download models and want to run directly, you can go to the cloud server:
The following link gives you 5~8 yuan upon registration, equivalent to 5 hours of running RTX4090 24G
Address: https://www.xiangongyun.com/image/detail/76e9371c 086f 435e 97a4 0067664fb89b?r=A39VYP

No environment conflict integration package ComfyUI continuously updated
Address: https://pan.baidu.com/s/1x0hAlsZPcJKVYQAmNZRa_A?pwd=8848