Realtime AI News
ByteDance's Seedance 2.5 draws attention: AI video generated 30 seconds at a time
Reports say ByteDance's AI video model Seedance 2.5 can generate 30 seconds of video in a single pass. The capability, if confirmed, would let creators produce complete coherent clips without stitching, a significant step for short-video and advertising workflows.
ByteDance's AI video model Seedance 2.5 is drawing attention after reports said it can generate 30 seconds of video in a single pass. The item circulated on August 12 via Google News aggregation of ByteDance AI coverage.
That capability means creators can obtain a full, coherent 30-second clip without stitching multiple segments together, a direct benefit for short-video production, advertising, and previsualization work.
The report comes from Pasquale Pillitteri's write-up on Seedance 2.5. Public information so far focuses on the single-pass duration; details on visual quality, resolution, model specs, and availability channels have not been fully disclosed.
Single-pass output length has become a key battleground for video generation models. Longer generation windows help preserve consistency in scenes, characters, and motion while reducing jumps from stitching, making duration an important measure of a video model's maturity.
Seedance is one of ByteDance's core video-generation efforts, and Seedance 2.5 is positioned as the latest step in that direction. If the capability is opened up officially, it could intensify competition with both domestic and international video generation products.
What to watch next is the official release channel, availability, and more detailed performance demos of Seedance 2.5. If the 30-second single-pass capability holds up in real testing, it would push the practical usefulness of video generation to a new level.
Why it matters
If Seedance 2.5's 30-second single-pass generation is confirmed, it would make AI video far more practical for short-video and advertising production and intensify competition in the video generation market.
Nearby Updates
All08/12, 17:52
Lei Jun poaches a key executive from ByteDance, Sina reports
Sina reported that Lei Jun has poached a key executive from ByteDance, without naming the person or the role. The move, surfaced through ByteDance AI-related news aggregation, is the latest sign of intensifying talent competition between major tech companies.
08/12, 18:24
Qwen Releases Qwen3.8-2.4T-A95B MoE Model with FP8 Quantized Version
Qwen has published the Qwen3.8-2.4T-A95B model on Hugging Face, a mixture-of-experts text model whose naming indicates roughly 2.4 trillion total parameters and 95 billion active parameters. The team also uploaded an FP8 quantized variant of the same model in the same release window.
08/12, 19:00
AI code-testing startup Blacksmith's valuation jumps nearly 10x in under a year
Blacksmith, an AI code-testing startup, says its valuation has jumped nearly tenfold in less than a year to $550 million. The company reports revenue growth of more than tenfold over the past year, as AI-driven coding fuels demand for software validation.
08/12, 15:57
China's edge-AI unicorn ModelBest files for A-share IPO counseling as MiniCPM hits 38M downloads
ModelBest, China's largest edge-AI model unicorn, has filed for A-share IPO counseling, with its MiniCPM series reaching 38 million cumulative downloads. The filing marks the company's first formal step toward a listing on China's A-share market and adds momentum to the capitalization of the on-device AI segment.