Click on the avatar in the upper right corner Invite code Fill in the invite code: rh v1408, get 1000 RH coins, log in daily to get 100 coins. If interested, you can join the discussion QQ group: 149735439

Breaking News!! LTX2.3 has been released https://www.runninghub.cn/ai detail/2029954327451803650/?inviteCode=rh v1408

LTX2.3 Workflow: https://www.runninghub.cn/post/2029897152301899777/?inviteCode=rh v1408

Image-to-video LTX2.0 【Acceleration】, the generation time for 720P may range between 2 to 4 minutes, while the generation speed for 1080P is estimated to be around 15s in 7 minutes. 3K resolution can take 5s, 10s is untested.
Auto prompt words: Currently, simple input of actions and camera movements is required, but it is more controllable than before and supports speech. If creating characters, Sigama must be switched
LTX2.0 new gameplay, below are applications of other LTX2. series:

LTX2.0 First and Last Frame Lip-sync: https://www.runninghub.cn/post/2016871878190702594/?inviteCode=rh v1408
LTX2.0 QwenTTS Character Speech: https://www.runninghub.cn/post/2017601157362884610/?inviteCode=rh v1408
LTX2.0 First and Last Frame: https://www.runninghub.cn/post/2009910509788733441/?inviteCode=rh v1408
LTX2.0 Audio Lip-sync 【Digital Human/Singing/Film】https://www.runninghub.cn/post/2011770027745222658/?inviteCode=rh v1408
LTX2.0 Image-to-video: https://www.runninghub.cn/post/2008764920220880897/?inviteCode=rh v1408

Friends, if interested, please follow me
Youtube: https://www.youtube.com/@MoteGlow %E5%B0%98%E5%85%89AI
Bilibili: https://space.bilibili.com/1285669374?spm_id_from=333.1387.0.0
Due to Qwen reverse calculation still being somewhat slow, Qwen reverse calculation has been improved, and the speed seems better. Writing prompt words is still faster with API integration.

Lens lora selection has been updated, now supporting all directional lenses. Normal left and right movement is more natural, but in close-ups or related situations, the corresponding lens needs to be selected; otherwise, left and right movement will forcibly pull the frame away.

Although prompt words are built-in, if someone writes well, they can write their own, roughly including: 1. Chinese scene descriptions (including main actions, microenvironment dynamics, dialogue content and lip movements, specific camera movement trajectories) English Quality Tags. 2. Ambient sound effects Action sound effects (describe the sounds corresponding to the scene). 3. Tone: emotional words (omit this field if there is no dialogue). 4. Style/Instrument.