SeeDance 2.5 Tested: 720p Video Generation and Stricter Moderation
TomLikesRobots · x · 2026-07-31
A user shared hands-on impressions of the video generation model SeeDance 2.5. Currently, it supports up to 720p resolution, with a 15-second limit for audio and video references. Testing revealed that its safety moderation is stricter than SD 2.0, blocking violent generations, and it suffers from instruction-following flaws (e.g., failing to obey prompts requesting no music).
More from Multimodal
- Flux 3 Generates 'First Ever Video Footage from 1702', Showcasing Stunning Retro Realism — fofrAI · 2026-07-31
- 3DGS-to-Mesh Software Update: Now Supports Large-Scale Scene Conversion — janusch_patas · 2026-07-31
- AI-Generated Music Video Criticized as 'Cheap' and Lacking Artistic Direction — gnukeith · 2026-07-31
- Fish Audio Raises $52M Seed, Launches S2.1 Pro Voice Model — alexcovo_eth · 2026-07-31
- Daily Midjourney SREF: Graphic Novel Interiors with Hand-Drawn Shadows — tisch_eins · 2026-07-31
- AI Visual Art: Blooming 'Blossoms of Flames' with striking VFX — TheChuckTone · 2026-07-31