Seedance 2.5
Text or image to cinematic 4K video in 30 seconds
What it does
Generate cinematic 30-second 4K videos from text or images with Seedance 2.5. Native 4K renders (no upscaling), up to 50 multimodal references, text-to-video and image-to-video. What makes it different: reference images keep characters and style consistent across shots, and the 4K pipeline is native rather than an upscale pass — built for creators who need footage that looks intentional.
Generate cinematic 30-second 4K videos from text or images with Seedance 2.5. Native 4K, up to 50 multimodal references, text-to-video and image-to-video.
ByteDance's Seedance 2.5 generates cinematic video from text or images — native 4K with 10-bit color, single-shot 30-second clips, synced native audio, and up to 50 multimodal references. No stitching, no upscaling fakery. A glimpse of what cinematic, controllable AI video looks like. Seedance 2.5 pushes past the limits that held back earlier AI video — longer, sharper, and more controllable, with roughly 20% better prompt adherence than the previous generation. From idea to video in three steps No timeline, no rendering farm — just describe what you want. Write a prompt, or drop in reference images to guide style, character, and motion. Choose duration, resolution, and aspect ratio. Up to…from seedance2-5.me
Does the same job
all alternatives →
Seedance 3.010d ago · seedances3.com · ▲1Multi-modal reference-to-video: cinematic AI clips from imag
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com