Easel AI is now on Replicate
Advanced face swap and AI avatars from Easel AI are now on Replicate.
AI NEWS JOURNAL
Search AI news
Search headlines, summaries and articles to connect the dots.
Stylized video with Wan2.1
One of the most fun ways to use Wan2.1 is video style transfer. Learn how here.
Creative roundup: avatars, lightsabers, and LoRA tricks
We take a quick look at the latest creative models, experiments, and community projects.
Wan2.1: generate videos with an API
Wan2.1 is the most capable open-source video generation model, producing coherent and high-quality outputs. Learn how to run it in the cloud with a single line of code.
Wan2.1 parameter sweep
We've been playing with Alibaba's WAN2.1 text-to-video model lately. What happens when you tweak those mysterious parameters? Let's find out.
You can now fine-tune open-source video models
Train your own versions of Tencent's HunyuanVideo for style, motion, and characters on Replicate.
Generate short videos with the Replicate playground
Create AI videos with a convenient workflow.
AI video is having its Stable Diffusion moment
There are lots of models that are as good as OpenAI's Sora now.
FLUX fine-tunes are now fast
We've made running fine-tunes on Replicate much faster, and the optimizations are open-source.
FLUX.1 Tools – Control and steerability for FLUX
A new set of image generation capabilities for FLUX models, including inpainting, outpainting, canny edge detection, and depth maps.
FLUX is fast and it's open source
FLUX is now much faster on Replicate, and we’ve made our optimizations open-source so you can see exactly how they work and build upon them.
Code with CodeQwen1.5
GITHUB HUGGING FACE MODELSCOPE DEMO DISCORD Introduction The advent of advanced programming tools, which harnesses the power of large language models (LLMs), has significantly enhanced programmer productivity and accuracy. Notwithstanding these advancements, dominant coding assistants like Github Copilot, built upon proprietary LLMs, pose notable challenges in terms of cost, privacy, security, and potential copyright infringement. Recognizing the imperative for a more transparent and accessible alternative, the open-source community has embarked on a concerted endeavor to develop open codeLLMs.
Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters
GITHUB HUGGING FACE MODELSCOPE DEMO DISCORD Introduction Since the surge in interest sparked by Mixtral, research on mixture-of-expert (MoE) models has gained significant momentum. Both researchers and practitioners are keenly interested in understanding how to effectively train such models and assessing their efficiency and effectiveness. Today, we introduce Qwen1.5-MoE-A2.7B, a small MoE model with only 2.7 billion activated parameters yet matching the performance of state-of-the-art 7B models like Mistral 7B and Qwen1.