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).
Related event: Seedance 2.5 Launches with 30s Native Generation and Local Editing(51 posts)→
More from Multimodal
- MiniMax H3 motion graphics demo impresses, $50K challenge with Picsart opens — egeberkina · 2026-09-16
- After Suno dropped his chords, this user built a MIDI-to-.abc converter so YuE2 preserves them — Saren-WTAKO · 2026-09-16
- Hugging Face team ships 'Building VLMs' book: hands-on guide to vision-language models — andimarafioti · 2026-09-16
- Hugging Face publishes illustrated guide to the 3D generation ecosystem — unofficialmerve · 2026-09-16
- Creator shares 4 imaginary tokens for Midjourney v8.2 to generate metaphorical imagery — LudovicCreator · 2026-09-16
- Zero-cost video generation with a copy-paste Grok prompt that just works — songguoxiansen · 2026-09-16