Google demo says Gemma 4 can inspect car damage from video in under 6 seconds

soumitrashukla9 · x · 2026-07-22

Google’s Gemma demo shows extremely fast multimodal inference for video damage inspection.

• The quoted post says Gemma 4 on Cerebras runs at 2,300+ tokens/s.
• The demo analyzes rental-car walkaround videos and produces annotated damage reports with box coordinates in under 6 seconds.
• The author says Google is already posting demos they helped build with Cerebras’ DevX team.

Original post →

More from Multimodal

• Storyboard-first workflows are making AI dance videos and influencers more consistent — aftahi_ai · 2026-07-22
• Interactive video should be judged by responsiveness, not just frame quality — Soggy_Limit8864 · 2026-07-22
• Runpod MCP and Claude help spin up image and video generation workflows — 802high · 2026-07-22
• Midjourney prompt turns a bee into a glitching pixel explosion — michaelrabone · 2026-07-22
• A physics reward can improve video generation without creating a real physics engine — Dapper-Drawer4546 · 2026-07-22
• HeyGen adds a media-sourcing skill for coding agents with 75k images and 10k tracks — HeyGen · 2026-07-22

Multimodal channel →