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

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, suitable for expressive speech
Low values (1.0 1.5): More subtle lip movements, suitable for calm speaking
This parameter balances between natural movements and lip-sync accuracy by affecting the model's guidance scale

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 possibly lower quality
The default value of 20 usually provides a good balance between quality and speed

You can also join the Ashuo member group, yumengashuo Backup Liang_Sanity
Community provides:
1. Exclusive advanced workflow for comfyui
2. Solutions to various problems with guaranteed responses
3. Ashuo integration package to resolve environment conflicts, 100 original workflows

Workflow online usage:
Fan benefits: Register through this link to receive a 1000RH coin reward (approximately 20+ videos or hundreds of images can be processed)
The platform allows you to play with RTX4090 48G, much more powerful than local deployment
Daily login gives 100 points, first come first served
Invitation code 【rh v1312】
https://www.runninghub.cn/?inviteCode=rh v1312

Xianggong Cloud is also updated synchronously, for those with insufficient configurations
If you don't want to download models and want to run directly, you can go to the cloud server:
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