AI · Official
Picsart Adds Faster, Cheaper Seedance 2.5 Flash AI Video Model
Picsart blog ·

At a glance
Picsart has added Seedance 2.5 Flash, a faster and cheaper version of ByteDance's Seedance 2.5 video model, to its AI Playground. It makes clips from 4 to 30 seconds with sound, at 480p or 720p. The model is meant for quick testing before a final video is made.
Key points
- Flash makes video faster and cheaper than the full Seedance 2.5 model.
- It can create clips up to 30 seconds long with sound included.
- Output is capped at 720p, and the reference limit is lower at 20 files.
- Draft Mode stays only with the full model.
Why it matters
Creators can test many video ideas at lower cost before committing to a final, higher-quality render.
Original source
Seedance 2.5 Flash brings faster, lower-cost AI video to Picsart
Picsart blog · Nov 16, 21:24 KST
Read on Picsart blog ↗AI summarized the original article. Check the original for accuracy. Copyright belongs to Picsart blog.
More from this field
- Designers Say Ssense's Website Shows Their Clothes Inaccurately
Designer Reese Cooper noticed his RCOS puffer coat looked distorted on the luxury retailer Ssense's website, with a chest hook drawn far too large. Ssense said some site images came from a "virtual try-on" program, though it would not say whether that program uses AI.
The New York Times · Nov 21, 06:16 KST - Korean Firms Build Three-Way AI Push: Anthropic Stake, HBM Chips, Claude Rollout
Korean companies are expanding their roles in the global AI market around Anthropic's IPO. SK Telecom earned large paper gains from an early investment, while Samsung Electronics and SK hynix are strengthening chip supply ties. Samsung SDS and LG CNS are bringing Anthropic's Claude model into the business AI market.
뉴스웨이 · Nov 21, 06:10 KST - MIT and IBM Team Probes Gaps in Multimodal AI Understanding
MIT and IBM researchers are studying where today's multimodal AI models fall short, even when they handle text, images, and sound fluently. Their team, co-led by MIT's Jim Glass, builds new benchmarks and training methods that need less labeled data. This Q&A walks through how the project started and how it has evolved.
MIT News · Nov 21, 06:00 KST - Leaky AI Supply Chain Exposes Secret User Data at Alarming Rate
A research test sent nearly two million prompts with fake but working secrets through a network of AI services to see where they ended up. Many of the secrets were stolen, and attackers used them to reach cloud accounts. The results point to weak protection of customer data along the chain.
Ars Technica · Nov 21, 05:59 KST