ComfyUI integrates Gemini Omni Flash 1.1 with 4K video support
osanseviero · x · 2026-08-28
ComfyUI has announced day 0 support for Google's Gemini Omni Flash 1.1 model. Via the Gemini Video Omni node, users can perform multiple tasks within a single node:
- Generation & Editing: Text-to-video, image-to-video, reference-to-video, instruction-based editing, and scene extension.
- High Resolution: Supports output up to 4K, with auto-generated audio tracks.
- Multimodal Input: Accepts text, image, and video inputs simultaneously.
The model's native multimodal processing ensures output coherence and supports conversational video editing.
More from Multimodal
- Flova Advances to Agent-Native Video Creation with All-in-One Tools — SimplyAnnisa · 2026-08-28
- SpatialCrafter enables consistent video gen from single images via 3D proxies — kwangmoo_yi · 2026-08-28
- Hy4 Preview generates detailed Sakura Bonsai image via WorkBuddy — vincent_koc · 2026-08-28
- Midjourney prompting tip: using 'imperfection' to narrate the aftermath of luxury — tisch_eins · 2026-08-28
- PotionUI, an Open-Source Image/Video/Audio Generation App, Seeks Alpha Testers — 0roborus_ · 2026-08-28
- Community LoRA gets MiniMax to Seedance-level fight scenes — Beginning-District69 · 2026-08-28