A repeatable image-to-video prompt trick for Gemini, Grok and GPT Image
charis_ai · x · 2026-09-03
Mehwish shares a reportedly reliable image generation trick: open Gemini, Grok or GPT Image 2.0, pick an image plus a video, enter the prompt, and generate. The reposter calls it a fun prompt with a lot of potential.
More from Multimodal
- VPIPE does fast local image generation too: 1024×1024 in 2.5 min on M4 Pro — TgoAI · 2026-09-03
- 3 Street View Images to a Full 3D Home Reconstruction: World Labs Atlas Stuns Users — CSProfKGD · 2026-09-03
- Temporal Film Grain node brings non-static, frame-aware grain to ComfyUI — Acrobatic-Example315 · 2026-09-03
- FoundYou paper accepted at ECCV 2026: one photo tracks and segments the same object across thousands of images — gabriberton · 2026-09-03
- Google demos Gemini 3.8 Flash with interactive 3D hardware teardown visualizer — gaganghotra_ · 2026-09-03
- SenseNova U1 Pro Vanished After Weeks of Hype — No Weights, No API, No Release — Pure_Bend5514 · 2026-09-03