Ultra-fast optimized version, [low resolution sampling once, upscaled sampling twice],

1920*1088 total 161 frames, approximately 5 minutes,

1920*1088 total 251 frames, approximately 6 minutes,

2560*1440 total 161 frames, approximately 6 minutes,

2560*1440 total 251 frames, approximately 10 minutes,

24G video memory is also supported, 48G video memory is recommended,

AI application:

• Supports text-to-video, first frame, last frame, first and last frames, first-middle-last frames video generation, enable the corresponding images as needed.

• Supports automatic/manual prompt switching

Workflow:

• Nodes in fluorescent green are input parameters, adjust as needed
• Use the pink switch for function toggling

Output [a video   prompt text file]

👇LTX2.0 first-last frame video generation V3 audio-driven version_three-sample (upload audio yourself) has been released, audio can be uploaded to achieve lip-sync, influence video, etc.

https://www.runninghub.cn/post/2017697617920135169?inviteCode=ishbfzc1