LTX2.3 Text-to-Video 3.1 is a text-and-image-to-short-video workflow that automatically generates high-definition short videos based on an uploaded reference image + global prompt + segmented prompts.
Key features include:

Reference Image Subject Locking: After uploading a reference image, the system maintains consistent character identity, clothing, hairstyle, and key features.
Global Prompt Controls Overall Visuals: Defines the video scene, lighting, action boundaries, art style, and camera rules to ensure a consistent visual style.
Segmented Prompts Control Actions: Action changes can be set for each time segment of the video, ensuring coherent character expressions and movements.
Three-Stage Sampling HD Refinement: The generated video goes through three-stage sampling to output clear, high-precision visuals with reduced noise and clutter.
10S Similarity Preservation: Through similarity guidance and anchor constraints, the character in the video remains highly consistent with the reference image, with natural movements.
Supports Audio-Visual Separation: Audio input can be selected to achieve lip-syncing or animated action matching.
Easy to Operate: Simply upload images and input text to generate videos without manual segmented rendering.

🎁Claim RH Coins first, then experience the workflow! Top-right avatar → Invitation Code → Enter [rh-v1111] to instantly get 1000 RH Coins, and log in daily to get another 100 coins~ For more ComfyUI workflows, tutorials, and gameplay, follow our official WeChat account (AIKSK), with simultaneous updates on Douyin / Bilibili / Xiaohongshu / YouTube (AI-KSK) ✨

LTX2.3 Text-to-Video 3.1｜Third-Level HD Fine-Tuning