Qwopus3.8-27B-Flash
A fine-tuned Qwen3.8-27B optimized for fast, efficient agentic reasoning and tool-use.
Live drop
Google DeepMindDropped Aug 27, 202625 builds24 makers8 prompts
Scene extension to 40s with first/last frame keyframing and 360p-to-4K draft-upscale workflow for controllable video edits.



About this release
Gemini Omni 1.1 Flash is Google DeepMind's production multimodal video generation and editing model. It accepts text, images, and video inputs to output synchronized video with audio. Key updates include analyzing up to 10 seconds of prior context for scene extensions (cumulative 40s), first-and-last-frame interpolation for camera control, video references for consistency, and resolution options from 360p drafts to 4K upscales via the Gemini API.
Read the official Google DeepMind launch pageWorth opening first
Same brief, other models
All challenges →Challenge
Same brief across models — older takes on the left, newer on the right.
Challenge
Same brief across models — older takes on the left, newer on the right.
Paste the URL and Dropday.ai will credit you, track the build as it evolves, and put it on this drop.
Submit a build