🔥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

For those about to deploy, we salute you. Check out our new guide to building a continuous deployment pipeline for your Cog models using @anthropicai for fuzz testing and GitHub Actions for deployment. Link in thread 👇

Step-Video-T2V by StepFun is on Replicate. It's an optimized version by Cheng Zeyi's WaveSpeedAI that is 4x faster than the original implementation. Try it out 👇

Deepseek-v3 is now on Replicate❤️‍🔥 replicate.com/deepseek-ai/de…

The fastest Wan video models on Replicate now support loras. - 480p takes 30s - 720p takes 90s Try them here: replicate.com/wavespeedai (Sound on)

Llama 4's on Replicate! Try it out... 🧵

We're happy to announce that PixVerse v4.5 is now on Replicate. PixVerse is one of the fastest video generation models capable of generation 1080p outputs. v4.5 has better motion, prompt handling and coherency. replicate.com/pixverse/pixve…

We've made it easier for AI code editors and LLMs to use any model on Replicate. Just in time for Codex. You can now: - copy the page as markdown - load directly in Claude or ChatGPT - see an llms.txt page for any model Here's the llms.txt for Google Veo-2:

> A man is running through a beautiful summer park at dawn, he is out of breath, he slows and stops, looks at the camera and says, while panting, "Run AI with an API. Use Replicate", then he carries on running. Then "Replicate" text fades into view at the end Seems like the

🚀 Flux Dev is now 40% faster on Replicate — generating images in just 1.8 seconds. Check it out here: replicate.com/black-forest-l….

Hello FLUX.1 Kontext! Kontext is a new state-of-the-art image editing model from Black Forest Labs. It's live now on Replicate. You can edit images with words: Change clothes, restyle scenes, rewrite text, all from a prompt. It just works 🔥 Pro and Max:

this site so good: replicate.com/flux-kontext-a…

Click to change hair 💇‍♀️ Having too much fun with the Flux Kontext app on Replicate First pic is the reference image!

Introducing Kontext Chat. Edit images by just chatting with them. Kontext was crying out for a chat interface, so we made one. Check it out: kontext-chat.replicate.dev

We've put together a blog post about how to use and prompt Veo 3. Plenty of useful tips in here from @fofrai and Shridhar about prompting audio, handling dialogue, avoiding subtitles, styling outputs and making selfie vlogs. replicate.com/blog/using-and…

We've got some new Imagen 4 models for y'all: Imagen 4 Ultra: $0.06/img, the highest quality outputs replicate.com/google/imagen-… Imagen 4 Fast: $0.02/img, for speed replicate.com/google/imagen-… And we’ve reduced the price of regular Imagen 4 to $0.04/img

This is going to be a good one. Come by if you're in SF and meet the Replicate and BFL teams.

🚨 Hackathon in SF this Saturday! We're teaming up with Black Forest Labs to celebrate the launch of FLUX.1 Kontext. Come by and hack on FLUX and meet the Replicate and BFL teams. Prizes include tons of credit, Airbnb gift cards, and cool tech 👀 lu.ma/air6b63y?x

We are hosting a Black Forest Labs x Replicate hackathon in SF tomorrow! Come hack on Kontext, meet cool people and hangout with Robin Rombach, Andreas Blattmann, @two_dukes and the rest of the BFL team!

People are making millions building "AI Wrappers". This video is a deep dive in: 1. Building Vibe Coded Creative AI Tools 2. Testing the best Image and Video Models 3. Using the Replicate Playground 4. Wrapper Examples created on v0 00:00 - Introduction 00:31 - Vibe Coded

Agent coding in Emacs: github.com/andreasjansson… I was torn between using my beloved Emacs or using coding agents in Claude Code and Cursor. So I decided to have my cake and eat it. Greger uses Claude with a set of built-in tools for editing code, running shell commands,