Replicate
@replicate
Run AI with an API
We've partnered with Runway @runwayml to bring their video + upscale models to Replicate. Create cinematic shots. Upscale up to 40 seconds of video to 4K. Try them today: replicate.com/runwayml/gen4-… replicate.com/runwayml/upsca…
Kudos to @replicate - For helping us spread the word about open-source, enterprise-ready visual generative AI. go.bria.ai/4lGSEz0
Wan 2.1 might be the best open-source text-to-image model, and everyone is sleeping on it. The one drawback is Wan's slow inference speed, so we applied a series of optimizations to bring it down to just 3s for 2 MP images. You can try it on @replicate: replicate.com/prunaai/wan-im…
We've added nearly $30,000 in credits to Vercel's Open Source Program. Thanks to generous partner companies, the new OSS Starter Pack adds access to tools that help you build, maintain, and grow your project. Let's create a more sustainable web, together.
Trivia && Game Night Wed July 30? Yes please! @CloudflareDev 🤝@replicate 🤝@getmetronome 🤝 👾🎮🧩🎲 Feat. 🔥 prizes like - Game consoles - Replicate credits - Mystery gifts... 👀 lu.ma/vp2nnqni
You can now run Kontext LoRAs via Huggingface 🤗 huggingface.co/fofr/kontext-m…
Run all the Flux.1 Kontext [dev] LoRAs Run any Kontext LoRA from Replicate, Hugging Face, CivitAI, etc replicate.com/black-forest-l…
![replicate's tweet card. FLUX.1 Kontext[dev] image editing model for running lora finetunes](https://pbs.twimg.com/card_img/1947728819181244426/xpE3h4hV?format=jpg&name=orig)
When legends take flight. Image + Video: Midjourney Audio: Smart ThinkSound on @replicate Inspired by @Alin_Reaper05
We've put together a guide on what we think are the best models for creating consistent characters from a single reference image (no lora training required). replicate.com/blog/generate-…
"Rube Goldberg machine" No one quite got the physics right, but Hailou-02 and Kling 2.1 Master are the most interesting to watch.
We've got some more models for you! Bria AI @bria_ai_ has a suite of commercial-safe image generation + editing tools to try: - Image 3.2 (image gen) - Genfill (inpainting) - Expand image - Generate background - Remove background - Eraser (remove objects) - Increase resolution
🚨 NEW i2v model: Runway Gen-4 Turbo! Generate studio quality shots with consistent characters, scenes, and cinematic styles. In under 30s. replicate.com/runwayml/gen4-…
I'm happy to ship this now, you can use the lora here: replicate.com/fofr/kontext-m… Download: huggingface.co/fofr/kontext-m… I find it works best at ~1.2 strength. Lower values are more subtle. You can change the prompt to make skin more/less spotty/freckled too.
I'm working on a new kontext lora for making AI people look more like real people. These are the results of the second pass. Still a few tweaks and retraining needed, but it's getting there.
Design like Karpathy is watching - @zeke @replicate A great example of turning criticism into product improvements! Recommended watch. 👍 buff.ly/oF3RgW8
Experimenting with @replicate model @GoogleAI Imagen-4 capability with impossible latte art.
Weekly experiment with @cavalry__app and @replicate .
Yesterday we launched wan-image on @replicate and it can generate amazing animal cinematic pictures