User praises Gemini Omni Flash 1.1 video generation after testing on Halai
aziz4ai · x · 2026-08-31
An Arabic-speaking user shared a hands-on test of Google's Gemini Omni Flash 1.1 video generation model on the Halai platform. Despite previous disappointments with Google's models, the user was shocked by the results. They provided three reference images (location, character, and car) and generated a video, describing the output as 'insane' and suggesting Google is returning to form with its model capabilities.
Related event: Arabic User Impressed by Hala AI Video Generation, Rethinking Google Models(2 posts)→
More from Multimodal
- Breeze-TTS-2 demo now available on Hugging Face — BreezeBlue · 2026-09-01
- 求助：Anima 模型训练正常但推理生成模糊 — a_throwawayorsmthn · 2026-09-01
- 求测：Ideogram 4 INT8 量化版在 3060 12G 上的表现 — WhyDoiHearBosssMusic · 2026-09-01
- Help: Swapping a Mustache Using a Reference Image in Flux Workflows — sadboi2021 · 2026-09-01
- Fal's new model heralds next chapter for Hollywood VFX — briannekimmel · 2026-09-01
- Sea Angels Generated in p5.js Using Claude Opus 5 — anselm · 2026-09-01