Replicate’s blog
- Easel AI is now on Replicate
- Stylized video with Wan2.1
- Creative roundup: avatars, lightsabers, and LoRA tricks
- Run Wan2.1 to generate videos with an API
- Wan2.1 parameter sweep
- Wan2.1: generate videos with an API
- You can now fine-tune open-source video models
- Generate short videos with the Replicate playground
- AI video is having its Stable Diffusion moment
- FLUX fine-tunes are now fast
- FLUX.1 Tools – Control and steerability for FLUX
- NVIDIA L40S GPUs are here
- We messed up: data URLs in our sync API
- Ideogram v2 is an outstanding new inpainting model
- Stable Diffusion 3.5 is here
- FLUX is fast and it's open source
- FLUX1.1 [pro] is here
- Using synthetic training data to improve Flux finetunes
- Fine-tune FLUX.1 with an API
- Fine-tune FLUX.1 with your own images
- Fine-tune FLUX.1 to create images of yourself
- Explore Replicate’s official models
- Replicate Intelligence #12
- Replicate Intelligence #11
- Replicate Intelligence #10
- FLUX.1: First Impressions
- Replicate Intelligence #9
- FLUX.1: A new state of the art image generation model from Black Forest Labs
- Replicate Intelligence #8
- Run Meta Llama 3.1 405B with an API
- Replicate Intelligence #7
- Replicate Intelligence #6
- Replicate Intelligence #5
- How to get the best results from Stable Diffusion 3
- Run Stable Diffusion 3 on your Apple Silicon Mac
- Push a custom version of Stable Diffusion 3
- Run Stable Diffusion 3 on your own machine with ComfyUI
- Run Stable Diffusion 3 on ComfyUI locally
- Replicate Intelligence #4
- Run Stable Diffusion 3 with an API
- H100s are coming to Replicate
- Replicate Intelligence #3
- Simplified AI Inference APIs on Replicate with NVIDIA NIM
- Replicate Intelligence #2
- Hello, world!
- Constraining CLIPDraw
- A new template for model READMEs
- Exploring text to image models
- Illustrating the news with AI
- Automating image collection
- Join us at Uncanny Spaces
- Build a robot artist for your Discord server with Stable Diffusion, Replicate, and Fly.io
- Run Stable Diffusion with an API
- Run Stable Diffusion on your M1 Mac’s GPU
- Train and deploy a DreamBooth model on Replicate
- Introducing LoRA: A faster way to fine-tune Stable Diffusion
- Machine learning needs better tools
- Train and run Stanford Alpaca on your own machine
- Fine-tune LLaMA to speak like Homer Simpson
- Week 3 of LLaMA 🦙
- How to use Alpaca-LoRA to fine-tune a model like ChatGPT
- Language models are on Replicate
- AutoCog — Generate Cog configuration with GPT-4
- Language model roundup, April 2023
- Status page
- Make any large language model a better poet
- What happened with Llama 2 in the last 24 hours? 🦙
- Fine-tune Llama 2 on Replicate
- A comprehensive guide to running Llama 2 locally
- Run SDXL with an API
- Run Llama 2 with an API
- What’s the difference between Llama 2 7B, 13B, and 70B?
- Fine-tune SDXL with your own images
- Streaming output for language models
- A guide to prompting Llama 2
- We're cutting our prices in half
- Painting with words: a history of text-to-image AI
- Fine-tuned models now boot in less than one second
- Make smooth AI generated videos with AnimateDiff and an interpolator
- How to run Mistral 7B with an API
- Jet-setting with Llama 2 + Grammars
- Fine-tune MusicGen to generate music in any style
- How to use retrieval augmented generation with ChromaDB and Mistral
- Generate images in one second on your Mac using a latent consistency model
- Generate music from chord progressions and text prompts with MusicGen-Chord
- Using open-source models for faster and cheaper text embeddings
- Scaffold Replicate apps with one command
- How to run Yi chat models with an API
- Businesses are building on open-source AI
- Clone your voice using open-source models
- How to create an AI narrator for your life
- Fine-tune Llama 2 for English to Hinglish translation with axolotl
- Run Code Llama 70B with an API
- Run Meta Llama 3 with an API
- Run Snowflake Arctic with an API
- Shared network vulnerability disclosure
- Replicate Intelligence #1