CapCut brings Seedance 2.5 to desktop with 30-second generations and GPT Image 2 workflow
anthara_ai · x · 2026-09-11
CapCut's desktop app now integrates Dreamina Seedance 2.5 and GPT Image 2 into one AI video/image workflow:
- Up to 30 seconds per generation, enough room to test pacing, blocking and camera progression in one complete shot
- Multimodal reference control, localized editing, timestamp motion direction, and white-model shot planning
- GPT Image 2 covers character design with consistent views, scene extension, multi-image blending, and hyper-realistic UI recreation
- PC multi-timeline bulk editing lets marketers iterate multi-version TVC assets fast
The sharer highlights a workflow reversal: instead of generating video first and fixing details later, they now use GPT-6 Astra to draft custom color LUTs and subtitle .srt files up front, then refine in CapCut — more control before the final edit even starts.
More from Multimodal
- Training a 210M text-to-image DiT on one GPU in 3.5 days: three measured findings — IvanMikhnenkov · 2026-09-11
- Same Prompt, Same Seed: Anima vs SDXL Image Quality Compared — nano_chad99 · 2026-09-11
- Synthesia Adds Custom Avatars Built From a Text Prompt — synthesiaIO · 2026-09-11
- Storyboard: an open-source AI video workflow — chodtoo · 2026-09-11
- Marigold V2 Hits New SOTA in Monocular Depth Estimation with Single-Step Diffusion Transformers — AntonObukhov1 · 2026-09-11
- A Dancer Balancing on a Ladder in Purple Light: A Striking AI Video Demo — misovalko · 2026-09-11