BytePlus launches Dreamina Seedance 2.5 on OpenRouter

// 46d agoMODEL RELEASE

BytePlus launches Dreamina Seedance 2.5 on OpenRouter

BytePlus has released Dreamina Seedance 2.5 on OpenRouter, bringing a specialized joint audio-video generation model to developers via API. The model generates up to 30 seconds of synchronized audio-video using up to 50 reference assets and supports precise multimodal editing.

// ANALYSIS

Bringing native long-duration audio-video generation alongside deep multi-reference editing to OpenRouter makes high-end AI video production significantly more accessible to developers.

–Supports single-pass generation up to 30 seconds with multi-round extension capabilities up to 50 total references.
–Extremely high reference capacity allowing 30 images, 10 video clips, and 10 audio clips per request.
–Precise video and audio editing features enable adding, deleting, or modifying specific subjects within existing media.

// TAGS

dreaminaseedance-2.5byteplusopenroutervideo-genmultimodalai-editingaudio-video

DISCOVERED

46d ago

2026-08-09

PUBLISHED

46d ago

2026-08-09

RELEVANCE

8/ 10

AUTHOR

OpenRouter

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

LAUNCH35m ago

Siren demos autonomous marketing agent with MCP

Siren is an autonomous marketing platform that generates code-rendered launch videos, ad creatives, and social copy from a single prompt and automatically distributes them across social channels. Operating via a web dashboard and an MCP server, it allows developers to orchestrate marketing asset creation and publishing directly inside coding environments like Cursor and Claude Code.

OPEN SOURCE49m ago

stable-diffusion.cpp brings dependency-free diffusion inference to C++

stable-diffusion.cpp is an open-source implementation enabling lightweight and efficient inference of major generative diffusion architectures, including Stable Diffusion, Flux, Wan, and Qwen Image, using pure C and C++. Modeled after the ggml ecosystem, the project removes heavyweight Python dependencies and framework overhead, enabling cross-platform local generation across standard consumer CPUs and accelerators with minimal resource footprints.

OPEN SOURCE53m ago

Lap is an open-source, local-first desktop photo manager built with Tauri and Rust that delivers on-device AI search and duplicate detection across large personal media libraries.

Lap is an open-source, cross-platform photo manager designed to organize massive local media collections without relying on cloud services or proprietary database lock-in. Powered by a high-performance Rust and Tauri backend with a Vue frontend, Lap works directly on existing filesystem folders to index libraries containing over 100,000 photos and videos. It features completely local AI capabilities—including semantic search, face clustering, and subject tagging—alongside essential organization tools such as duplicate and similar-photo detection, multi-pane image comparison, smart rule-based albums, interactive map views, and broad format compatibility covering RAW files, Apple Live Photos, and Android Motion Photos across macOS, Windows, and Linux.

BytePlus launches Dreamina Seedance 2.5 on OpenRouter