Ray 3.2 from @LumaLabsAI is now live!
Explore HDR and EXR outputs with multi-keyframe control. Designed in collaboration with creatives entertainment, advertising, and gaming.
Almost 10M views on Instagram in less than 24 hours 😱
New Asian theater trend featuring fictional characters. The key? Combining the realism of live theater with the fantasy of the characters' powers 🔥
And as always, here’s the TUTORIAL 🧵📚 (Warning: it’s ridiculously easy)
Introducing Claude Fable 5: a Mythos-class model that we’ve made safe for general use.
Its capabilities exceed those of any model we’ve ever made generally available.
introducing Krea 2 Turbo.
generate high-quality images in just 2s; compatible with style references, moodboards, and LoRAs.
try it for free at krea . ai
P-Video-Replace from @PrunaAI is up on Replicate!
This is the fastest model for character replacement in existing video.
And until Sunday, we're giving our community 70% off, making this model only $0.009/s of output video.
P-Video-Replace is now the fastest model for top-quality character replacement in existing video.
- $0.03/s at 720p and $0.06/s at 1080p — a small fraction of typical character-replacement / video-edit pricing (~$0.07–$0.35/s at 720p in our benchmarks)
- 3.58 s generation time
In honor of partnering with @xai to bring their models to Replicate, we've put together the ultimate prompting guide for their latest video model, Grok Imagine Video 1.5.
replicate.com/blog/grok-imag…
Introducing Ideogram 4.0: the best open image model in the world.
Think it. Make it. Own it.
Download the weights, fine-tune on your own data, and run it on your hardware. Live on every Ideogram plan and the API today.
Introducing Aleph 2.0 from @runwayml on Replicate.
A major upgrade for video editing that delivers localized video edits for clips up to 30s and 1080p.
Change lighting, swap in a product, remove objects, or restyle your entire video. All in just a prompt.
P-Video-Animate from @PrunaAI just dropped!
Given a reference input image and video, create a new video preserving the original motion, style, camera movement, and scene structure of the reference video.
And until Sunday, it's only $0.009/sec of video.
Gemini 3.5 Flash is here and it's our best model yet for getting things done quickly and efficiently.
Whether you need help with everyday tasks or multi-step creative projects, Gemini 3.5 Flash navigates real-world complexity to help you take action. #GoogleIO
Avatar V from @HeyGen is now on Replicate
Create realistic, studio-quality videos with preserved identity. Better motion quality and more coherent expressions, especially on longer scripts.
Plus, multi-angle capabilities with character consistency.
Avatar V API is live at $0.05/sec
The highest-quality AI avatar model for developers
Benchmarked against Veo 3.1, Kling O3 Pro, OmniHuman 1.5, and Seedance 2.0 on cross-scene talking-head generation
Avatar V won every category
Research report + API ↓