惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

T
Tailwind CSS Blog
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
雷峰网
雷峰网
量子位
有赞技术团队
有赞技术团队
阮一峰的网络日志
阮一峰的网络日志
The Cloudflare Blog
博客园 - Franky
罗磊的独立博客
宝玉的分享
宝玉的分享
博客园_首页
腾讯CDC
The GitHub Blog
The GitHub Blog
D
DataBreaches.Net
IT之家
IT之家
D
Docker
Microsoft Security Blog
Microsoft Security Blog
博客园 - 司徒正美
V
V2EX
月光博客
月光博客
N
Netflix TechBlog - Medium
爱范儿
爱范儿
I
InfoQ
P
Proofpoint News Feed

TestingCatalog

SpaceXAI gearing up for upcoming Grok 4.5 release Meta prepares Scheduled tasks for Meta AI users on web Google tests new Gemini Inbox section for Workspace triage OpenAI might be preparing GPT-5.6 for next week's release Mistral releases Leanstral 1.5 model for proof engineering xAI debuts Grok Voice Agent Builder for Enterprises Condense launches proxy to cut AI coding agent bills by 66% Vellum adds agent-to-agent AI collaboration for Slack Early look at Anthropic's Claude Science app for researchers Google launches Nano Banana 2 Lite and Gemini Omni Flash Google might be testing Gemini Flash upgrade on LM Arena Anthropic may impose KYC restrictions for Fable 5 access Anthropic launches Claude Sonnet 5 model on Claude and APIs NoimosAI launches Creative Agent for brand assets Apify lets AI Agents pay via Coinbase x402 for web tools Bloome launches chat platform for AI agent teams Meituan launches LongCat-2.0 1.6T parameter model Cursor releases its iOS app for vibe coding on the go OpenAI prepares upgraded Office controls for Codex OpenAI tests gifting Codex credits as new growth strategy Microsoft launches MAI-Code-1-Flash on GitHub Copilot Google adds Computer Use to Gemini 3.5 Flash Google tests notebook collections for NotebookLM OpenAI launches GPT-5.6 Sol preview for select partners Microsoft adds Copilot finance tools to Excel for M365 users DeepReinforce releases Ornith-1.0 open-source coding models Gemini to get voice dictation and Magic Pointer on desktop Meta launches AI glasses with three new styles from $299 Anthropic launches Claude Tag on Team and Enterprise plans Mistral launches OCR 4 for multilingual document extraction
ByteDance set to launch Seedance 2.5 with 3-minute output
https://www.facebook.com/testingcatalog · 2026-07-05 · via TestingCatalog

ByteDance appears close to releasing Dreamina Seedance 2.5, with current rumors pointing to a possible July 9 launch. Public Dreamina and CapCut pages already reference the model, while third-party reports suggest an early-July rollout window rather than a confirmed date. Availability is expected across Dreamina, CapCut, and partner platforms that already work with ByteDance’s video stack.

Coming soon: Dreamina Seedance 2.5 is arriving on CapCut.

Seamless generation and editing. Up to 50 multimodal references. 30-second scenes in one shot. Finer creative control. More reliable results. It's built to make creating faster, smoother, and more intuitive.

Whether… pic.twitter.com/hkJnP3zg6Y

— CapCut (@capcutapp) July 4, 2026

The main new feature will be a move from short clips to 30-second standard video generation. Dreamina pages describe a long video workflow that can generate 30-second scenes, 90-second drafts, and 180-second outputs, making three-minute AI video the biggest claimed shift for this release. The open question is not only about duration but also about whether the model can keep character identity, motion, camera logic, and prompt intent stable across extensions.

You can create cinematic videos up to 30 seconds in standard mode or extend them to 180 seconds with the beta long-video mode. 
Dreamina website
Dreamina website

For creators, advertisers, anime editors, social video accounts, and AI filmmakers, this would turn Seedance from a short-shot generator into a tool for longer sequences. The likely location is within Dreamina’s Seedance workflow, CapCut’s creator tools, and partner apps that use ByteDance’s model access. The evidence appears to come from public-facing product pages and platform copy, while the July 9 timing remains rumor-level until ByteDance posts a dated release notice.

The company behind the model is ByteDance, which has been tying AI video to its creator ecosystem through Dreamina, CapCut, TikTok-adjacent production flows, and API distribution. Seedance 2.0 is still positioned around motion stability, multimodal references, and audio-video generation, with listed durations of 4 to 15 seconds on BytePlus. Seedance 2.5 would push that strategy toward longer commercial storytelling and creator workflows, while Google’s Veo and Gemini Omni remain the clearest competitive pressure after OpenAI discontinued Sora’s web and app product on April 26, 2026.

Source