FLUX 3 Max by @bfl_ai is live on each::labs 🦆 Generate a 10-second video in just 12 seconds. → Make 5 to 20 second videos in up to 1080p, with optional audio → Start from text, an image or timed keyframes → Great at voices, sound effects and physical realism Try it now ⤵

Paying full price for every bad take? Seedance 2.5 Draft Completion is live on each::labs 🎬 → Try your ideas as quick, low-cost 480p drafts. → Pick the take you love and finish it in 1080p. → Same motion and timing, in final-cut quality. Try it now ⤵

FIBO 2.0 by @bria_ai_ is live on each::labs on day 0 🌈 Bria’s new open-weights model for image generation and editing. → Generate images from text and pick your aspect ratio and output format. → Edit photos with text instructions or precise masks. Try it now ⤵

Flying cars are finally here. Now someone has to decide when they take off 💨 Decision models, a road full of traffic and less than a second to make every call. Overtake or fly over? each::labs Decisions is live. → Yes/no probabilities, choices and scores. No paragraphs to parse. → Answers in under a second, fast enough for real-time apps. We put 6 of them behind the wheel. Watch what they choose. Try it now on each::labs ⤵

Got a photo and an audio clip? That's all you need. BytePlus OmniHuman 2.0 is live on each::labs 🎙️ → Works with any character, real photos, paintings, illustrations and more → 4 seconds to 5 minutes of audio → Same photo, new prompt, different mood Try it now ⤵

This will change how you create 🔌 each::labs is now a plugin for Claude and Codex, with 600+ image, video and audio models in your chat and terminal. → No more model shopping. Tell it what you need and the AI picks the right one. → No more switching between tabs. Create, edit and trim in one conversation. → Nothing new to learn. Just keep working the way you already do. Closing the imagination gap, right inside your chat. Try it now ⤵

Krea 3 by @krea_ai is live on each::labs 🎨 A new image model built for fast, precise edits with your own references. → Edit at 2K and see results in under 8 seconds. → Draw a box to change only the area you want. → Keep refining the same image step by step. Try it now ⤵

P-Video-2-Pro Reference by @PrunaAI is live on each::labs. Lock a product, character or voice from your references and build a scene around it. → Use up to 9 images, 3 videos and 3 audio clips. → Get 5-15s clips with sound. → Keep your audio as the soundtrack. Try it now ⤵

each::labs × @Sonilo_music 🎧 Five new Sonilo models are now live on each::labs. Create professionally licensed music and realistic sound effects that fit your story, from a text prompt or straight from your video, in seconds. Let’s take a look at what each model can do ⤵