Wenkang Han

icon indicating a website link https://dqyzhwk.github.io/

icon location Hangzhou,China icon location Multimodal Learning

Results 15 issues of Wenkang Han

Inference Pipline for for video-to-video generation

1 comment

I want to know if this project can provide a pipeline for video-to-video generation similar to video super-resolution tasks.

stale

degradation pipline

1 comment

Could you please open source the degraded code of LQ video？

The connection between Upscale-A-Video and StableSR

Is Upscale-A-Video based on StableSR with the addition of fine-tuning through the incorporation of time dimensions and flow fields?

Code Release ?

Code Release ?

Code Release ?

Code Release ?

Any schedule for subsequent open source plans?

有计划优化 VEnhancer 的训练和微调代码吗

1 comment

Mind2web 评测实现细节

描述: Element Accuracy (Ele. Acc) compares the predicted element with the ground-truth elements. Operation F1 (Op. F1) calculates the token-level F1 score for the predicted operation comprised of action and...