This is a multi-image first-and-last-frame narrative video generation application based on LTX 2.3 + VBVR LoRA.
Users can upload the first frame, intermediate keyframes, and the last frame, combined with action prompts, allowing the model to generate coherent, highly-controlled, and loopable narrative videos across multiple images. This workflow does not just animate a single ordinary image; instead, it uses multiple keyframes to guide the video structure, enabling the model to more stably complete action designs such as "start-process-end-loop".
Features of this workflow:
Recommended usage:
Recommended prompt writing style:
Keep the character and scene consistent first, then have the subject enter obvious action changes, move into climax actions, and finally return to a posture close to the initial one but slightly advanced, forming a natural loop.
The current positive prompt in your file is already a standard VBVR storyboard-style writing, including "Storyboard 1, Storyboard 2, Storyboard 3, Storyboard 4", and is an action design progressing in a clear sequence, which indicates its best usage is "writing narrative actions in segments".
🎁Claim RH Coins first, then experience the workflow! Click your avatar in the top right corner → Invitation Code → Enter [rh-v1111] to instantly receive 1000 RH Coins. Log in daily to get another 100 RH Coins~ For more ComfyUI workflows, tutorials, and gameplay, please follow our Official Account (AIKSK), with simultaneous updates on Douyin / Bilibili / Xiaohongshu / YouTube (AI-KSK) ✨
No creations yet

No creations available.