Higgsfield Launches Seedance 2.5: Enables 30-Second Single-Pass Video Generation
socialwithaayan · x · 2026-08-08
Higgsfield has officially launched the video generation model Seedance 2.5. Aimed at advanced video production, its core highlights include:
- Long Takes: Supports video scenes up to 30 seconds long in a single pass.
- Multiple References: Accommodates up to 50 reference images.
- Production-Ready Editing: Offers editing capabilities geared toward professional filmmaking.
To promote the new model, the platform is running a limited-time offer of 33 days of zero credit cost (unlimited usage). This aims to give creators enough runway to build a full film using AI, encouraging submissions to the $1M Global Film Festival.
More from Multimodal
- ForcingBooster halves computation of autoregressive video diffusion with patch-wise denoising — VAST-AI · 2026-10-16
- Tokyo's Gemini AI Photo Booth turns visitors into plush toys and dioramas — bradneuberg · 2026-10-16
- Orchestrating a 100-image portrait of humanity for aliens with ChatGPT, Argon and p5.brush — dx8xb · 2026-10-16
- Indie Creator Builds an AI-Native Animated Show Solo — ComprehensiveLime654 · 2026-10-16
- Ideogram teases 4.5 arrival and open weights: 'Not yet, but soon' — East_Shoe8814 · 2026-10-16
- Opus 5.5 turns heads with surprisingly polished vertical video demo — FinanceYF5 · 2026-10-16