🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

No way this AI tool automatically edits your raw footage 😳

✅ New feature: Automatically remove silences from your audio/video. What do you think?

Yesterday, the Hawk Tuah girl launched an AI app so significant it fundamentally changed the trajectory of AI forever. Inspired by her courage and groundbreaking insights into denoising diffusion probabilistic models for high-dimensional video synthesis, we humbly launched

Excited to see our video editing engine empowering the next wave of video startups! Check out @diffusionstudio/core for more.

Launching Core v2 – The Future of Web-Based Video Rendering Today, we're rolling out a major update to our WebCodecs-powered video rendering engine. We've completely removed PixiJS and Pixi Filters, replacing them with a new, custom-built render system designed for speed,

🚀 Just launched the world’s first open-source video editing agent! Our technology proposal: Our Python-based agent starts a browser session using Playwright and opens operator.diffusion.studio. This web app is a video editing UI optimized for agents, providing access to

After almost 2 years of R&D, we launch Core V3—a video editing engine that runs in your browser. We ditched WASM-compiled FFmpeg for pure TypeScript multiplexers, enabling client-side rendering of any video size with insane performance. Benchmarks show it’s 2x faster than

Finally gave in to the ASCII art trend – Muybridge video + WebGL shader

Next launch will be ready in 2-3 decades, stay tuned 🎉

As it turns out, rendering text is incredibly hard! This is my 5th attempt at getting rich, dynamic text to render at 60fps using the 2D context API. Past attempts: 1️⃣ Draw text every frame on the main context 2️⃣ Create a canvas per word/token & render separately 3️⃣ Use SVGs

Been working on transformation bounding boxes for our playground. Getting to this level of detail requires hundreds of geometric equations.

Introducing Diffusion Studio Pro. The world’s first multimodal AI studio for professionals. Think CapCut + Cursor. Local first, browser based editor (non linear). Free unlimited tier. Fully agentic sidebar with access to 16+ generative models. Comment “DSPRO” to get early

Diffusion Studio Pro got a redesign. + small teaser of what will be launched tomorrow

The world’s most intuitive AI canvas is here. We built an agentic canvas for generating pro-level creative assets. Think Figma meets Sora. Comment “Canvas” and we’ll DM you an invite code.

Agentic Canvas ✌️

one shotted with Diffusion Studio including transitions, sfx and music

This video was entirely generated and edited by AI, with zero human interaction. DSPro generated the visuals, added audio, composed the music, aligned everything on the timeline, and inserted text. Imagine what this could look like in six months…

This is how to write prompts in Diffusion Studio Pro