Creator shares full prompt-level workflow for realistic AI videos using GPT Image 2.5 and Seedance 2.5
socialwithaayan · x · 2026-09-10
Creator @abxxai breaks down the actual workflow behind hyper-realistic AI videos: generating stills with GPT Image 2.5 and animating them with Seedance 2.5. The thread shares every prompt used step by step, making it a replicable recipe for AI video creation.
More from Multimodal
- Full pipeline: niji + GPT Image + local MiniMax H3 + Codex for pixel-perfect animation — Hailuo_AI · 2026-09-10
- Marigold V2 arrives as Qwen-Video-Edit repurposes an image editing DiT for video — AntonObukhov1 · 2026-09-10
- MiniMax H3 video generation demoed with character dance and multi-background references — Hailuo_AI · 2026-09-10
- Dev open-sources a Visual RefMod Picker for ComfyUI to manage 1500+ character reference mods — Francky_B · 2026-09-10
- Puffin-World: unified world model with native 3D states, open-sourced with 16M dataset — ccloy · 2026-09-10
- Dimillian shows off high-quality Blender spaceship made with Astra — Dimillian · 2026-09-10