This is a cinematic-grade video outpainting application based on LTX 2.3 Dev-Dare / Distilled Video Model + IC-LoRA Video Guidance + Gemma API Prompt Encoding + Video Outpainting & Stitching + Color Correction + Chunked Decoding Output. After a user uploads an original video, the system reads the video frames, frame rate, and audio information, generates and completes the area outside the frame based on prompts, and finally stitches the original video and the newly generated extended area into a larger-format video.
The core advantage of this workflow is: The original video subject and motion are preserved, while the outer space of the frame is generated and completed by LTX 2.3. This is not ordinary image outpainting; it performs outpainting for continuous video frames, making it suitable for converting vertical videos to horizontal, expanding narrow aspect ratios into cinematic widescreen, and supplementing left/right environments, upper/lower spaces, background architecture, sky, ground, stage, and scene atmosphere for videos. The workflow also retains color correction, video information reading, audio transmission, and final mp4 synthesis structures, making it better suited to become an official RunningHub video application. When using, it is recommended to focus on controlling three items: Input video determines the subject and motion, global prompts (used to write overall frame rules) determine the outpainted frame style, and segment prompts (writing action changes for each time period) determine the completion changes in different stages of the video.
🎁Claim RH Coins first, then experience the workflow! Top-right avatar → Invitation Code → Enter [rh-v1111] to instantly claim 1000 RH Coins, and log in daily to claim another 100 coins ~ For more ComfyUI workflows, tutorials, and gameplay, please follow our Official WeChat Account (AIKSK), with synchronized updates on TikTok / Bilibili / Xiaohongshu / YouTube (AI-KSK) ✨


No creations yet

No creations available.