Robin Guignard-Perret

P-Image-Try-On is already available on Tellers! 🎬 Direct your AI films with a professional costume designer at your fingertips.

What is AI changing for content creators?

In light of what happened, I'm doubling down on skills like /improve. A frontier model got pulled. If it happened once, it's gonna happen again. Fable today. 4.9 tomorrow or maybe gpt 6 one day. So, treat intelligence as borrowed. Drain intelligence when it's available. Build a catalog of plans today. Then implement later with a cheaper, open source, or a model you control. Build the backlog now. github.com/shadcn/improve

@eachlabs @WiroAI @inference_sh @Scenario_gg @replicate @runware @wavespeed_ai @togethercompute P-Video Replace is now on @tellersai | tellers.ai

We're already making the editing of TV Shows 30% faster for our clients and we're only getting started! tellers.ai/use-cases/tv-p…

@aaliya_va @PrunaAI Feel free to book a quick onboarding with me on the website : tellers.ai

@rguignar @PrunaAI Excited to try it

Prompt with your body 🕺 p-video-animate by @PrunaAI is already live on Tellers!!

P-Video-Animate is now the fastest model for top-quality image-to-video motion transfer. - $0.03/s at 720p and $0.06/s at 1080p — a fraction of typical motion-transfer pricing (~$0.07–$0.35/s at 720p in our benchmarks) - 5.24 s generation time per second of output video at 720p — roughly 7× faster than typical motion-transfer alternatives in the same benchmarks - Upload one still plus a driver video to preserve motion, timing, camera movement, and scene structure, with optional source audio and clips up to ~2 minutes at 720p Ideal for UGC ads, gaming cinematics, film casting, and product demos when you already have a winning take and want a new hero still to follow it. Try it in the playground: …-playground-production.up.railway.app/p-video-animate We’re launching with 70% discounted usage for the coming two days with our launch partners. @eachlabs, eachlabs.ai/pruna/p-video/… @replicate, replicate.com/prunaai/p-vide… @runware, runware.ai/models/prunaai… @scenario_gg, scenario.com/models/p-video… @wavespeed_ai, wavespeed.ai/models/pruna-a… @wiroai, wiro.ai/models/pruna-p… @TellersAI, buff.ly/RBmFEco Soon also on @togethercompute We’d love your feedback as you try it. 📚 Model docs & API examples: docs.pruna.ai/en/stable/docs… 📚 API quickstart: docs.api.pruna.ai/guides/quickst… ⭐️ OSS: github.com/PrunaAI/pruna 🌐 pruna.ai

Just published a free, no account, no upload, fully private, browser based subtitle generator. Just drop your video: tellers.ai/free-standalon…

Partnership announcement "AI should be fast so creators stay in the creative loop" | @TellersAI x Pruna Our full model family is now live in @TellersAI. The agentic video editor. P-Image · P-Video · P-Image-Upscale · P-Video-Avatar Same Station F roots. Same belief: AI should be fast enough that creators stay in the creative loop. Sub-second images. Video in seconds. Iterate without burning credits. Read the full blog here: tellers.ai/blog/pruna_ai_…

Video generation is finally fast. @PrunaAI 🤝 @TellersAI

@flwenz Audio in-painting and audio-extension are so cool! Well done!!

We have been cooking... Today is a big day for Mirelo AI. We are launching a bunch of great stuff: A new model, new tools, new website and more. See below.

Vibe sound design is here!! We got early access to @MireloAI SFX 1.6, the model is amazing. It instantly becomes a must-have in any AI creator’s tool belt. We integrated it inside Tellers, and, as a bonus, it unlocks something huge, video extension with audio continuity!

We just released free video utilities tellers.ai/free-standalon…

SOMEONE TURNED THE VIRAL "TEACH CLAUDE TO TALK LIKE A CAVEMAN TO SAVE TOKENS" STRATEGY INTO AN ACTUAL CLAUDE CODE SKILL one-line install and it cuts ~75% of tokens while keeping full technical accuracy they even benchmarked it with real token counts from the API: > explain React re-render bug: 1180 tokens → 159 tokens (87% saved) > fix auth middleware: 704 → 121 (83% saved) > set up PostgreSQL connection pool: 2347 → 380 (84% saved) > implement React error boundary: 3454 → 456 (87% saved) > debug PostgreSQL race condition: 1200 → 232 (81% saved) average across 10 tasks: 65% savings. range is 22-87% depending on the task. three intensity levels: > lite: drops filler, keeps grammar. professional but no fluff > full: drops articles, fragments, full grunt mode > ultra: maximum compression. telegraphic. abbreviates everything works as a skill for Claude Code and a plugin for Codex. this is PEAK

My Tellers x OpenClaw demo is featured in the @AITinkerers newsletter! Read more about giving video editing skills to your Claw: post-training.aitinkerers.org/p/ai-tinkerers…

When code can evolve this fast, vision and stories win over features

Give the most seamless and performant video editing skills to your #openclaw clawhub.ai/yxdunc/tellers