♻️ Tools
Replicate Blog
2 min read
Open source video is back
Wan 2.2 is our fastest, cheapest video model.
Latest AI News & Research
636 articles
♻️ Tools
Replicate Blog
6 min read
Generate consistent characters
We compare the best image models for generating consistent characters from a single reference image.
🌍 Safety
Future of Life Institute
5 min read
Google DeepMind Falls Behind OpenAI in Latest Safety Review; All AI Companies Still Falling Short, Say Experts
The Future of Life Institute’s 2025 summer update to its AI Safety Index shows some companies making incremental progress, but dangerous gaps remain in key categories such as risk assessment…
♻️ Tools
Replicate Blog
2 min read
Bria is now on Replicate
We've partnered with Bria to bring a suite of commercial-grade image generation and editing models to Replicate. Built entirely on licensed data, Bria’s tools are designed for enterprises and developers…
🐍 Newsletters
AI Snake Oil
31 min read
Could AI slow science?
Confronting the production-progress paradox
![How we optimized FLUX.1 Kontext [dev]](https://replicate.com/blog/flux-kontext-optimization.png)
♻️ Tools
Replicate Blog
6 min read
How we optimized FLUX.1 Kontext [dev]
A deep-dive into the Taylor Seer optimization technique
♻️ Tools
Replicate Blog
2 min read
Compare AI video models
It's hard keeping up with every new video model. In this post we'll help you pick the best one for your needs.
🐻 Research
Berkeley AI Research
7 min read
Whole-Body Conditioned Egocentric Video Prediction
× Predicting Ego-centric Video from human Actions (PEVA) . Given past video frames and an action specifying a desired change in 3D pose, PEVA predicts the next video frame. Our…
♻️ Tools
Replicate Blog
4 min read
The FLUX.1 Kontext hackathon
We hosted a hackathon with BFL for FLUX.1 Kontext. Here were the winners.
🔄 News
Synced Review
7 min read
ByteDance Introduces Astra: A Dual-Model Architecture for Autonomous Robot Navigation
ByteDance introduces Astra, an innovative dual-model architecture revolutionizing robot navigation in complex indoor environments. The post ByteDance Introduces Astra: A Dual-Model Architecture for Autonomous Robot Navigation first appeared on Synced…
🔄 News
Synced Review
5 min read
MIT Researchers Unveil “SEAL”: A New Step Towards Self-Improving AI
MIT introduces SEAL, a framework enabling large language models to self-edit and update their weights via reinforcement learning. The post MIT Researchers Unveil “SEAL”: A New Step Towards Self-Improving AI…
🔄 News
Synced Review
5 min read
Researchers from PSU and Duke introduce “Multi-Agent Systems Automated Failure Attribution
"Automated failure attribution" is a crucial component in the development lifecycle of Multi-Agent systems. It has the potential to transform the challenge of identifying "what went wrong and who is…
♻️ Tools
Replicate Blog
12 min read
How to prompt Veo 3 for the best results
Learn expert prompting techniques to create stunning videos with Google's Veo 3.
📊 Business
Benedict Evans
2 min read
AI metrics
With every platform shift, we want to measure the growth but we’re confused about what to measure. That’s partly a problem of data and definitions, but it’s really a question…
♻️ Tools
Replicate Blog
2 min read
Get the most from Google Veo 3
We're sharing our experiments and tips on Google's new Veo 3 model.
📐 Research
The Gradient
20 min read
AGI Is Not Multimodal
"In projecting language back as the model for thought, we lose sight of the tacit embodied understanding that undergirds our intelligence." –Terry Winograd The recent successes of generative AI models…
♻️ Tools
Replicate Blog
3 min read
FLUX.1 Kontext from the community
FLUX.1 Kontext is everywhere - see what folks are cooking.
♻️ Tools
Replicate Blog
6 min read
Use FLUX.1 Kontext to edit images with words
This is how to get the most from Black Forest Labs' new image editing model.
🔄 News
Synced Review
3 min read
Adobe Research Unlocking Long-Term Memory in Video World Models with State-Space Models
By combining State-Space Models (SSMs) for efficient long-range dependency modeling with dense local attention for coherence, and using training strategies like diffusion forcing and frame local attention, researchers from Adobe…
📊 Business
Benedict Evans
3 min read
GenAI’s adoption puzzle
Generative AI chatbots might be a life-changing transformation in the nature of computing, that can replace all software, but so far, most of its users only pick it up every…
♻️ Tools
Replicate Blog
5 min read
Generate incredible images with Google's Imagen 4
Google's flagship image generation model, Imagen 4, is now available for you to try on Replicate. Create images with fine detail, versatile styles, and improved typography.
♻️ Tools
Replicate Blog
1 min read
Run OpenAI’s latest models on Replicate
OpenAI's latest models are now available on Replicate, including GPT-4.1, GPT-4o, and the o-series.
♻️ Tools
Replicate Blog
3 min read
NVIDIA H100 GPUs are here
NVIDIA H100 GPUs are here, with better performance and lower cost.
🔄 News
Synced Review
12 min read
DeepSeek-V3 New Paper is coming! Unveiling the Secrets of Low-Cost Large Model Training through Hardware-Aware Co-design
A newly released 14-page technical paper from the team behind DeepSeek-V3, with DeepSeek CEO Wenfeng Liang as a co-author, sheds light on the “Scaling Challenges and Reflections on Hardware for…