VideoCrafter is an open source video generation and editing toolbox for crafting video content.
It currently includes the following 3 types of models 1. Base T2V: Generic Text-to-video Generation It is based on the latent video diffusion models (LVDM). It can synthesize realistic videos based on the input text descriptions. 2. VideoLoRA: Personalized Text-to-Video Generation with LoRA By providing a sentence describing the video content along with a LoRA trigger word (specified during LoRA training), it can generate videos with the desired style(or subject/concept). 3. VideoControl: Video Generation with More Condition Controls By pluging a lightweight adapter module to the T2V model, you can get obtained generation results with more detailed control signals such as depth.
0 Comments
Thank you !