
Replicate - Run AI with an API
All the latest models are on Replicate. They’re not just demos — they all actually work and have production-ready APIs. AI shouldn’t be locked up inside academic papers and demos. Make it …
AI Image & Photo Restoration - Image Restoration Models
AI models to restore images by fixing blur, noise, and low resolution. Remove noise and compression artifacts with advanced AI image restoration.
Explore - Replicate
Discover and share open-source machine learning models from the community that you can run in the cloud using Replicate.
Changelog - Replicate
2 days ago · Topics: detailed explanations of how Replicate works; Reference: complete documentation for Replicate’s client libraries and API; We’ve added dozens of new code …
About & Careers – Replicate
This goo was created with a model on Replicate: andreasjansson/plasma We’re bringing AI to every software developer. AI can do extraordinary things, but it’s still too hard to use.
LLaVA-13b: Large Language and Vision Model - Replicate
LLaVA-13b on Replicate: A powerful multimodal AI model for language and vision tasks. Run visual question answering, image captioning, and more with ease Visual instruction tuning …
Set up a CI/CD pipeline for your model - Replicate docs
In this guide, you’ll set up a CI/CD pipeline for your Cog model using GitHub Actions and github.com/replicate/cog-safe-push, an open-source project we use internally at Replicate to …
lightricks/ltx-video | Run with an API on Replicate
This model costs approximately $0.012 to run on Replicate, or 83 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with …
Blog – Replicate
May 22, 2025 · Train and deploy a DreamBooth model on Replicate . With just a handful of images and a single API call, you can train a model, publish it to Replicate, and run predictions …
Working with LoRAs - Replicate docs
LoRAs were first popularized for fine-tuning Stable Diffusion and SDXL, and Replicate was one of the first places to support them. By training a LoRA on a specific style or dataset, users could …