Mera 2.0 Fast is our latest flagship video generation model, combining Mera’s precision with advances from major video generation models to deliver fast inference, rapid draft previews, robust lipsync, built-in audio generation, and highly controllable text-to-video, image-to-video, and audio-to-video creation with up to 1080p at 48 FPS, multi-aspect ratio support, and prompt upsampling for more realistic, physically accurate results.
Model availability and access depend on your workspace and plan.
Mera 2.0 FastAbout the model
Mera 2.0 Fast is our latest flagship video generation model, combining Mera’s precision with advances from major video generation models to deliver fast inference, rapid draft previews, robust lipsync, built-in audio generation, and highly controllable text-to-video, image-to-video, and audio-to-video creation with up to 1080p at 48 FPS, multi-aspect ratio support, and prompt upsampling for more realistic, physically accurate results.
What you get back. Your generated video appears directly in your Relam chat.
Working with Mera 2.0 Fast
Random seed for reproducible generation.
Text prompt for video generation.
Video duration in seconds.
Last-frame reference image.
First-frame reference image.
Output & configuration
These options come from Mera 2.0 Fast’s model specification. Your workspace shows the options included with your plan.
Questions & answers
Generation mode: quality, speed, or cost.
Model default: speed
Video resolution.
Model default: 768p
Aspect ratio; reference images determine the canvas when provided.
Model default: 16:9
Expand your prompt before video generation.
Model default: turbo