Gemini Omni 1.1 Flash: Video Extend
Extend an existing video by up to 10 seconds per step, building stories up to 40 seconds total with Gemini Omni 1.1 Flash. The model analyzes the last 10 seconds of context, keeping characters, motion, and audio coherent as the scene continues from where it left off. Optionally attach reference images to introduce new characters mid-story. Works on uploaded clips and previously generated videos; describe how the scene should continue in plain language. Ideal for longer narratives, scene branching, and iterative storytelling.
À propos
This ComfyUI tutorial workflow shows how to extend an existing video in coherent, story-aware chunks using the GeminiVideoOmniV2 node (Gemini Omni 1.1 Flash). It loads your clip with LoadVideo, extracts the final moments as context via Video Slice, and asks Gemini to continue the scene for up to 10 seconds per run. The model reads the last 10 seconds of visual context so characters, motion, camera framing, and scene layout carry forward naturally instead of restarting from scratch. SaveVideo then exports the extended result as a new clip.
Ce que vous fournissez
- Lecture du workflow
S’exécute dans ComfyUI. Ce workflow ne peut pas s’exécuter sur cette page. Ouvrez-le dans Comfy Cloud, avec tout déjà chargé, ou téléchargez-le pour votre propre ComfyUI.
Essayer dans CloudQuestions-réponses
The workflow is tuned for up to 10 seconds per step and about 40 seconds total across iterations. You can run more steps, but visual quality and continuity may degrade as context drifts.
Keep prompts consistent, describe key subjects and camera behavior clearly, and reuse the last 10 seconds as context via the Video Slice node. For stronger identity anchoring, attach one or more reference images to the GeminiVideoOmniV2 node.
This template focuses on visual continuation. LoadVideo/SaveVideo in many ComfyUI setups export silent MP4s. If you need audio, keep your original track and re-sync or design new audio in post after export.
Yes. Duplicate the GeminiVideoOmniV2 + SaveVideo segment, keep the same Video Slice tail input, and vary the prompt (and optional image refs). You’ll get multiple alternate continuations from the same context.
Workflows associés
- Seedance 2.5
Change a video’s background
- LTX-2.3
Remove an object from a video
- LTX-2.3
Expand a video’s frame
- SCAIL-2
Replace a character in a video
- SeedVR2
Upscale a video
- LTX-2.3
Restore archival footage
- Topaz
Agrandir vidéo : Topaz Starlight Precise 2.5
- Nœud partenaire
AI on the Lot 2026_LTX-2.3_IC LoRA (Union Control)
- Wan2.2, Z-Image-Turbo
AIrt MAchIne
- Real-ESRGAN
Améliorateur vidéo GAN rapide
- Nœud partenaire
Beeble SwitchX : Édition Vidéo
- BRIA
Bria : Suppression de fond vidéo