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:
@replicate
-
Replicate Changelog Updates Past Two Weeks
By
–
It's been a busy couple of weeks at Replicate. Catch up on the latest with our changelog.
-
Imagen-4 Now Available on Replicate Platform
By
–
Did you try Imagen-4 on Replicate yet?https://t.co/KYxLPymqHw pic.twitter.com/Ez8HS8y1xH
— Replicate (@replicate) 24 mai 2025Did you try Imagen-4 on Replicate yet? https://
replicate.com/google/imagen-4 -
OpenAI’s Latest Models Now Available on Replicate Platform
By
–
You can now run OpenAI's latest models on Replicate, including GPT-4.1, GPT-4o, and the o-series. http://
replicate.com/openai -
Google’s Imagen-4 Now Available on Replicate Platform
By
–
We've worked with Google to get you Imagen-4 on Replicate: https://
replicate.com/google/imagen-4 This is a preview, and the model is still being perfected by Google, and things might change, but images are already exceptional. Let's go -
Flux Dev 40% Faster on Replicate with 1.8 Second Generation
By
–
Flux Dev is now 40% faster on Replicate — generating images in just 1.8 seconds. Check it out here: https://
replicate.com/black-forest-l
abs/flux-dev
…. -
Kling AI Lip-Sync Model Now Available on Replicate
By
–
Kling AI's lip-sync model is now available on Replicatehttps://t.co/wW6enrYrgP
— Replicate (@replicate) 18 mai 2025
Here's a Kling v2.0 generation with lip-synced audio added pic.twitter.com/aDhsDofipJKling AI's lip-sync model is now available on Replicate https://replicate.com/kwaivgi/kling-lip-sync
… Here's a Kling v2.0 generation with lip-synced audio added -
Kling v1.6 Now Supports Scene Elements in Video Generation
By
–
Kling v1.6 models on Replicate now support scene elements (reference_images).
— Replicate (@replicate) 18 mai 2025
Add up to 4 elements, like brands, characters, products or styles, to a video.https://t.co/2PL2Njue3d
Here's a generation that used two elements: a character and a Replicate hat. pic.twitter.com/Q8bUYk8KQqKling v1.6 models on Replicate now support scene elements (reference_images). Add up to 4 elements, like brands, characters, products or styles, to a video. https://
replicate.com/kwaivgi Here's a generation that used two elements: a character and a Replicate hat. -
Replicate Makes AI Models Easier for Code Editors and LLMs
By
–
We've made it easier for AI code editors and LLMs to use any model on Replicate. Just in time for Codex.
— Replicate (@replicate) 17 mai 2025
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:… pic.twitter.com/ZKKYr1D0JXWe'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: -
PixVerse v4.5 Now Available on Replicate for Fast Video Generation
By
–
We're happy to announce that PixVerse v4.5 is now on Replicate.
— Replicate (@replicate) 16 mai 2025
PixVerse is one of the fastest video generation models capable of generation 1080p outputs. v4.5 has better motion, prompt handling and coherency.https://t.co/uCCpwK7LCp pic.twitter.com/kJQZuRVPCtWe'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. https://
replicate.com/pixverse/pixve
rse-v4.5
…