Omni 1.2 flash

What is Omni 1.2 Flash

Omni 1.2 Flash is an AI-powered video generation model that converts text prompts and images into cinematic videos with natural audio, consistent characters, realistic motion, and up to 4K output. It is the successor to Omni 1.1 Flash and is ranked #1 on the Text-to-Video Arena as of November 6, 2026.

How to use Omni 1.2 Flash

1. Choose Text to Video or Image to Video: Start from a written scene or upload an image to anchor the subject and composition. Add reference images when a product or character must look the same in every shot.
2. Direct the Scene: Describe the subject, action, environment, camera movement, lighting, dialogue, and timing. Clips up to 15 seconds leave room for a full beat: setup, action, and payoff in one take.
3. Edit in Place, Then Upscale: Review the draft, then change the product, lighting, or camera angle with follow-up instructions instead of regenerating. When the take works, upscale it to 1080p or 4K for delivery.

Features of Omni 1.2 Flash

• 15-Second Clips, Extendable to 30 Seconds: A single generation or edit runs up to 15 seconds, up from 10. Scene extension adds 3 to 10 seconds per round, so one continuous story can reach 30 seconds in total.
• Draft Fast, Deliver in 4K: Generate native 360p or 720p drafts first, compare takes quickly, then upscale only the winning result to 1080p or 4K.
• About 30% Lower Price per Second: 720p output costs about $0.07 per second, down from roughly $0.10 on the previous model.
• Stronger Reference Consistency: Use up to 6 reference images, or 3 per character when directing two characters, plus up to 3 reference videos. Products, faces, and brand details stay consistent across shots.
• Stateful Conversational Editing: Keep refining the same clip instead of regenerating it. Swap a product, adjust the lighting, or change the camera angle in a follow-up instruction, and the rest of the scene stays put.
• Cleaner Speech and Lip Sync: Dialogue sounds more natural, lip movement matches the words more closely, and scenes with several speakers keep each voice distinct.

Use Cases of Omni 1.2 Flash

• Talking-head clips: Create videos with natural dialogue and accurate lip sync.
• Ads with spoken lines: Produce commercials with multiple speakers and clear voice separation.
• Interview-style scenes: Generate realistic interview footage with consistent characters.
• Product showcases: Maintain brand and product consistency across shots using reference images.
• Short cinematic stories: Build continuous scenes up to 30 seconds with scene extension.

Pricing

Omni 1.2 Flash offers a 720p output at approximately $0.07 per second, which is about 30% lower than the previous model's rate of roughly $0.10 per second. A full 15-second clip at 720p costs close to what 10 seconds used to. An annual plan is available with credits: only 40 credits, save 50%.

FAQ

What is Omni 1.2 Flash? Omni 1.2 Flash is an AI video generation model that creates videos from text or images with natural audio, consistent characters, and up to 4K resolution.

Is Omni 1.2 the same as Omni 1.2 Flash? Yes, Omni 1.2 and Omni 1.2 Flash refer to the same model.

How long can an Omni 1.2 Flash video be? A single generation can be up to 15 seconds, and with scene extension, it can reach 30 seconds total.

Does Omni 1.2 Flash generate native 4K video? It generates drafts at 360p or 720p and can upscale to 1080p or 4K for delivery.

How much does Omni 1.2 Flash cost? 720p output costs about $0.07 per second, approximately 30% lower than the previous model.

How many references does Omni 1.2 Flash support? It supports up to 6 reference images (3 per character for two characters) and up to 3 reference videos.

Can Omni 1.2 Flash edit a clip without regenerating it? Yes, it supports stateful conversational editing, allowing changes like product swaps or lighting adjustments without regenerating the entire clip.

Does Omni 1.2 Flash generate audio? Yes, it generates natural audio with improved speech and lip sync.

What is the difference between Omni 1.2 Flash and Omni 1.1 Flash? Omni 1.2 Flash offers longer clips (15s vs 10s), extendable to 30s, lower pricing, more reference images (6 vs 3), stateful editing, and improved speech and lip sync.