<?xml version="1.0" encoding="utf-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">
    <id>https://replicate.com/blog</id>
    <title>Replicate's blog</title>
    <updated>2025-01-12T00:10:37.064Z</updated>
    <generator>https://github.com/jpmonette/feed</generator>
    <link rel="alternate" href="https://replicate.com/blog"/>
    <link rel="self" href="https://replicate.com/blog/atom"/>
    <subtitle>Machine learnings from Replicate's team</subtitle>
    <entry>
        <title type="html"><![CDATA[AI video is having its Stable Diffusion moment]]></title>
        <id>https://replicate.com/blog/ai-video-is-having-its-stable-diffusion-moment</id>
        <link href="https://replicate.com/blog/ai-video-is-having-its-stable-diffusion-moment"/>
        <updated>2024-12-16T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[There are lots of models that are as good as OpenAI's Sora now.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[What’s the difference between Llama 2 7B, 13B, and 70B?]]></title>
        <id>https://replicate.com/blog/all-the-llamas</id>
        <link href="https://replicate.com/blog/all-the-llamas"/>
        <updated>2023-08-04T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[Let's break down the differences between the Llama 2 models and help you choose the right one for your use case.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Make smooth AI generated videos with AnimateDiff and an interpolator]]></title>
        <id>https://replicate.com/blog/animatediff-interpolator</id>
        <link href="https://replicate.com/blog/animatediff-interpolator"/>
        <updated>2023-10-04T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[Combine AnimateDiff and the ST-MFNet frame interpolator to create smooth and realistic videos from a text prompt]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[AutoCog — Generate Cog configuration with GPT-4]]></title>
        <id>https://replicate.com/blog/autocog</id>
        <link href="https://replicate.com/blog/autocog"/>
        <updated>2023-04-19T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[Give it a machine learning directory and AutoCog will create predict.py and cog.yaml until it successfully runs a prediction]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Build a robot artist for your Discord server with Stable Diffusion, Replicate, and Fly.io]]></title>
        <id>https://replicate.com/blog/build-a-robot-artist-for-your-discord-server-with-stable-diffusion</id>
        <link href="https://replicate.com/blog/build-a-robot-artist-for-your-discord-server-with-stable-diffusion"/>
        <updated>2022-08-25T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[A tutorial for building a chat bot that replies to prompts with the output of a text-to-image model.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Constraining CLIPDraw]]></title>
        <id>https://replicate.com/blog/constraining-clipdraw</id>
        <link href="https://replicate.com/blog/constraining-clipdraw"/>
        <updated>2022-05-27T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[An introduction to differentiable programming and the process of refining generative art models.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[We're cutting our prices in half]]></title>
        <id>https://replicate.com/blog/cutting-prices-in-half</id>
        <link href="https://replicate.com/blog/cutting-prices-in-half"/>
        <updated>2023-08-16T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[The price of public models is being cut in half, and soon we'll start charging new users for setup and idle time on private models.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Illustrating the news with AI]]></title>
        <id>https://replicate.com/blog/daily-news</id>
        <link href="https://replicate.com/blog/daily-news"/>
        <updated>2022-07-28T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[Creating a web app to illustrate news headlines with AI-generated visualizations]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[We messed up: data URLs in our sync API]]></title>
        <id>https://replicate.com/blog/data-urls-in-our-sync-api</id>
        <link href="https://replicate.com/blog/data-urls-in-our-sync-api"/>
        <updated>2024-10-31T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[We've decided to stop returning data URLs in sync API outputs based on feedback from users. We're going to take a few steps back and figure out the best way to get your model output as fast as possible.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Train and deploy a DreamBooth model on Replicate]]></title>
        <id>https://replicate.com/blog/dreambooth-api</id>
        <link href="https://replicate.com/blog/dreambooth-api"/>
        <updated>2022-11-21T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[With just a handful of images and a single API call, you can train a model, publish it to Replicate, and run predictions on it in the cloud.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Exploring text to image models]]></title>
        <id>https://replicate.com/blog/exploring-text-to-image-models</id>
        <link href="https://replicate.com/blog/exploring-text-to-image-models"/>
        <updated>2022-07-18T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[The basics of using the API to create your own images from text.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[FLUX fine-tunes are now fast]]></title>
        <id>https://replicate.com/blog/fast-flux-fine-tunes</id>
        <link href="https://replicate.com/blog/fast-flux-fine-tunes"/>
        <updated>2024-11-26T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[We've made running fine-tunes on Replicate much faster, and the optimizations are open-source.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[How to use Alpaca-LoRA to fine-tune a model like ChatGPT]]></title>
        <id>https://replicate.com/blog/fine-tune-alpaca-with-lora</id>
        <link href="https://replicate.com/blog/fine-tune-alpaca-with-lora"/>
        <updated>2023-03-23T00:00:00.000Z</updated>
    </entry>
    <entry>
        <title type="html"><![CDATA[Fine-tuned models now boot in less than one second]]></title>
        <id>https://replicate.com/blog/fine-tune-cold-boots</id>
        <link href="https://replicate.com/blog/fine-tune-cold-boots"/>
        <updated>2023-09-06T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[We've made some dramatic improvements to cold boots for fine-tuned models.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Fine-tune FLUX.1 with an API]]></title>
        <id>https://replicate.com/blog/fine-tune-flux-with-an-api</id>
        <link href="https://replicate.com/blog/fine-tune-flux-with-an-api"/>
        <updated>2024-09-09T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[Create and run your own fine-tuned Flux models programmatically using Replicate's HTTP API.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Fine-tune FLUX.1 to create images of yourself]]></title>
        <id>https://replicate.com/blog/fine-tune-flux-with-faces</id>
        <link href="https://replicate.com/blog/fine-tune-flux-with-faces"/>
        <updated>2024-08-30T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[Create your own fine-tuned Flux model to generate new images of yourself.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Fine-tune FLUX.1 with your own images]]></title>
        <id>https://replicate.com/blog/fine-tune-flux</id>
        <link href="https://replicate.com/blog/fine-tune-flux"/>
        <updated>2024-08-15T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[We've added fine-tuning (LoRA) support to FLUX.1 image generation models. You can train FLUX.1 on your own images with one line of code using Replicate's API.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Fine-tune Llama 2 on Replicate]]></title>
        <id>https://replicate.com/blog/fine-tune-llama-2</id>
        <link href="https://replicate.com/blog/fine-tune-llama-2"/>
        <updated>2023-07-20T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[So you want to train a llama...]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Fine-tune LLaMA to speak like Homer Simpson]]></title>
        <id>https://replicate.com/blog/fine-tune-llama-to-speak-like-homer-simpson</id>
        <link href="https://replicate.com/blog/fine-tune-llama-to-speak-like-homer-simpson"/>
        <updated>2023-03-17T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[With a small amount of data and an hour of training you can make LLaMA output text in the voice of the dataset.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Fine-tune MusicGen to generate music in any style]]></title>
        <id>https://replicate.com/blog/fine-tune-musicgen</id>
        <link href="https://replicate.com/blog/fine-tune-musicgen"/>
        <updated>2023-10-13T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[We’ve added fine-tuning support to MusicGen. You can train the small, medium and melody models on your own audio files using Replicate.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Fine-tune SDXL with your own images]]></title>
        <id>https://replicate.com/blog/fine-tune-sdxl</id>
        <link href="https://replicate.com/blog/fine-tune-sdxl"/>
        <updated>2023-08-08T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[We’ve added fine-tuning (Dreambooth, Textual Inversion and LoRA) support to SDXL 1.0. You can train SDXL on your own images with one line of code using the Replicate API.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[FLUX1.1 [pro] is here]]></title>
        <id>https://replicate.com/blog/flux-1-1-pro-is-here</id>
        <link href="https://replicate.com/blog/flux-1-1-pro-is-here"/>
        <updated>2024-10-03T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[Black Forest Labs continue to push boundaries with their latest release of FLUX.1 image generation model.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[FLUX.1: First Impressions]]></title>
        <id>https://replicate.com/blog/flux-first-impressions</id>
        <link href="https://replicate.com/blog/flux-first-impressions"/>
        <updated>2024-08-02T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[We explore FLUX.1's unique strengths and aesthetics to see what we can generate.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[FLUX is fast and it's open source]]></title>
        <id>https://replicate.com/blog/flux-is-fast-and-open-source</id>
        <link href="https://replicate.com/blog/flux-is-fast-and-open-source"/>
        <updated>2024-10-10T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[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.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Run FLUX with an API]]></title>
        <id>https://replicate.com/blog/flux-state-of-the-art-image-generation</id>
        <link href="https://replicate.com/blog/flux-state-of-the-art-image-generation"/>
        <updated>2024-08-01T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[FLUX.1 is a new text-to-image model from Black Forest Labs, the creators of Stable Diffusion, that exceeds the capabilities of previous open-source models.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[FLUX.1 Tools – Control and steerability for FLUX]]></title>
        <id>https://replicate.com/blog/flux-tools</id>
        <link href="https://replicate.com/blog/flux-tools"/>
        <updated>2024-11-21T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[A new set of image generation capabilities for FLUX models, including inpainting, outpainting, canny edge detection, and depth maps.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Generate music from chord progressions and text prompts with MusicGen-Chord]]></title>
        <id>https://replicate.com/blog/generate-music-from-chord-progressions-musicgen-chord</id>
        <link href="https://replicate.com/blog/generate-music-from-chord-progressions-musicgen-chord"/>
        <updated>2023-11-08T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[We’ve added chord conditioning to Meta’s MusicGen model, so you can create automatic backing tracks in any style using text prompts and chord progressions.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[How to get the best results from Stable Diffusion 3]]></title>
        <id>https://replicate.com/blog/get-the-best-from-stable-diffusion-3</id>
        <link href="https://replicate.com/blog/get-the-best-from-stable-diffusion-3"/>
        <updated>2024-06-18T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[We show you how to use Stable Diffusion 3 to get the best images, including new techniques for prompting.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Automating image collection]]></title>
        <id>https://replicate.com/blog/grab-hundreds-of-images-with-clip-and-laion</id>
        <link href="https://replicate.com/blog/grab-hundreds-of-images-with-clip-and-laion"/>
        <updated>2022-08-05T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[Using CLIP and LAION5B to collect thousands of captioned images.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[H100s are coming to Replicate]]></title>
        <id>https://replicate.com/blog/h100s-are-coming</id>
        <link href="https://replicate.com/blog/h100s-are-coming"/>
        <updated>2024-06-12T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[We'll soon support NVIDIA's H100 GPUs for predictions and training. Let us know if you want early access.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Hello, world!]]></title>
        <id>https://replicate.com/blog/hello-world</id>
        <link href="https://replicate.com/blog/hello-world"/>
        <updated>2022-05-16T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[We're a small team of engineers and machine learning enthusiasts working to make machine learning more accessible.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[How to create an AI narrator for your life]]></title>
        <id>https://replicate.com/blog/how-to-create-an-ai-narrator</id>
        <link href="https://replicate.com/blog/how-to-create-an-ai-narrator"/>
        <updated>2023-12-06T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[Or, how I met a virtual David Attenborough.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[A guide to prompting Llama 2]]></title>
        <id>https://replicate.com/blog/how-to-prompt-llama</id>
        <link href="https://replicate.com/blog/how-to-prompt-llama"/>
        <updated>2023-08-14T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[Learn the art of the Llama prompt.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Clone your voice using open-source models]]></title>
        <id>https://replicate.com/blog/how-to-tune-a-realistic-voice-clone</id>
        <link href="https://replicate.com/blog/how-to-tune-a-realistic-voice-clone"/>
        <updated>2023-12-06T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[We’ve added fine-tuning for realistic voice cloning (RVC). You can train RVC on your own dataset from a YouTube video with a few lines of code using Replicate's API.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[How to use retrieval augmented generation with ChromaDB and Mistral]]></title>
        <id>https://replicate.com/blog/how-to-use-rag-with-chromadb-and-mistral-7b-instruct</id>
        <link href="https://replicate.com/blog/how-to-use-rag-with-chromadb-and-mistral-7b-instruct"/>
        <updated>2023-10-17T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[In this post we'll explore the basics of retrieval augmented generation by creating an example app that uses bge-large-en for embeddings, ChromaDB for vector store, and mistral-7b-instruct for language model generation.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Ideogram v2 is an outstanding new inpainting model]]></title>
        <id>https://replicate.com/blog/ideogram-v2-inpainting</id>
        <link href="https://replicate.com/blog/ideogram-v2-inpainting"/>
        <updated>2024-10-22T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[We've partnered with Ideogram to bring their inpainting model to Replicate's API.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Language model roundup, April 2023]]></title>
        <id>https://replicate.com/blog/language-model-roundup</id>
        <link href="https://replicate.com/blog/language-model-roundup"/>
        <updated>2023-04-21T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[A roundup of recent developments from the world of open-source language models.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Language models are on Replicate]]></title>
        <id>https://replicate.com/blog/language-models</id>
        <link href="https://replicate.com/blog/language-models"/>
        <updated>2023-04-05T00:00:00.000Z</updated>
    </entry>
    <entry>
        <title type="html"><![CDATA[Jet-setting with Llama 2 + Grammars]]></title>
        <id>https://replicate.com/blog/llama-2-grammars</id>
        <link href="https://replicate.com/blog/llama-2-grammars"/>
        <updated>2023-10-09T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[How to use Llama 2 models with grammars for information extraction tasks.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[What happened with Llama 2 in the last 24 hours? 🦙]]></title>
        <id>https://replicate.com/blog/llama-2-roundup</id>
        <link href="https://replicate.com/blog/llama-2-roundup"/>
        <updated>2023-07-19T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[A roundup of recent developments from the llamaverse following the second major release of Meta's open-source large language model.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Week 3 of LLaMA 🦙]]></title>
        <id>https://replicate.com/blog/llama-roundup</id>
        <link href="https://replicate.com/blog/llama-roundup"/>
        <updated>2023-03-18T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[A roundup of recent developments from the llamaverse.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Introducing LoRA: A faster way to fine-tune Stable Diffusion]]></title>
        <id>https://replicate.com/blog/lora-faster-fine-tuning-of-stable-diffusion</id>
        <link href="https://replicate.com/blog/lora-faster-fine-tuning-of-stable-diffusion"/>
        <updated>2023-02-07T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[It's like DreamBooth, but much faster. And you can run it in the cloud on Replicate.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Machine learning needs better tools]]></title>
        <id>https://replicate.com/blog/machine-learning-needs-better-tools</id>
        <link href="https://replicate.com/blog/machine-learning-needs-better-tools"/>
        <updated>2023-02-21T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[Lots of people want to build things with machine learning, but they don't have the expertise to use it.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[A new template for model READMEs]]></title>
        <id>https://replicate.com/blog/model-docs</id>
        <link href="https://replicate.com/blog/model-docs"/>
        <updated>2022-07-05T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[Inspired by model cards, we've created templates for documenting models on Replicate.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Status page]]></title>
        <id>https://replicate.com/blog/new-status-page</id>
        <link href="https://replicate.com/blog/new-status-page"/>
        <updated>2023-05-18T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[We've added a status page to provide real-time updates on the health of Replicate.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[NVIDIA L40S GPUs are here]]></title>
        <id>https://replicate.com/blog/nvidia-l40s-gpus-are-here</id>
        <link href="https://replicate.com/blog/nvidia-l40s-gpus-are-here"/>
        <updated>2024-11-15T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[NVIDIA L40S GPUs are here, with better performance and lower cost.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Explore Replicate’s official models]]></title>
        <id>https://replicate.com/blog/official-models</id>
        <link href="https://replicate.com/blog/official-models"/>
        <updated>2024-09-02T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[Replicate now has official models. Official models are always on, fast, and high quality. They have predictable pricing and dedicated support. They're a reliable choice to build projects on.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Painting with words: a history of text-to-image AI]]></title>
        <id>https://replicate.com/blog/painting-with-words-a-history-of-text-to-image-ai</id>
        <link href="https://replicate.com/blog/painting-with-words-a-history-of-text-to-image-ai"/>
        <updated>2023-08-22T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[With the recent release of Stable Diffusion XL fine-tuning on Replicate, and today being the 1-year anniversary of Stable Diffusion, now feels like the perfect opportunity to take a step back and reflect on how text-to-image AI has improved over the last few years.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Push a custom version of Stable Diffusion 3]]></title>
        <id>https://replicate.com/blog/push-a-custom-sd3</id>
        <link href="https://replicate.com/blog/push-a-custom-sd3"/>
        <updated>2024-06-14T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[Create your own custom version of Stability's latest image generation model and run it on Replicate via the web or API.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Train and run Stanford Alpaca on your own machine]]></title>
        <id>https://replicate.com/blog/replicate-alpaca</id>
        <link href="https://replicate.com/blog/replicate-alpaca"/>
        <updated>2023-03-16T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[We'll show you how to train Alpaca, a fine-tuned version of LLaMA that can respond to instructions like ChatGPT.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Replicate Intelligence #1]]></title>
        <id>https://replicate.com/blog/replicate-intelligence-2024-05-24</id>
        <link href="https://replicate.com/blog/replicate-intelligence-2024-05-24"/>
        <updated>2024-05-24T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[DIY Llama 3 implementation, open-source smart glasses, steering language models with dictionary learning]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Replicate Intelligence #2]]></title>
        <id>https://replicate.com/blog/replicate-intelligence-2024-05-31</id>
        <link href="https://replicate.com/blog/replicate-intelligence-2024-05-31"/>
        <updated>2024-05-31T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[Faster image generation, AI-powered world simulator, insights on AI dataset complexity]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Replicate Intelligence #3]]></title>
        <id>https://replicate.com/blog/replicate-intelligence-2024-06-07</id>
        <link href="https://replicate.com/blog/replicate-intelligence-2024-06-07"/>
        <updated>2024-06-07T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[Garden State Llama, applied LLMs guide, real-time image generation]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Replicate Intelligence #4]]></title>
        <id>https://replicate.com/blog/replicate-intelligence-2024-06-14</id>
        <link href="https://replicate.com/blog/replicate-intelligence-2024-06-14"/>
        <updated>2024-06-14T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[Find concepts in GPT models, real-time speech to text in the browser, H100s are coming]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Replicate Intelligence #5]]></title>
        <id>https://replicate.com/blog/replicate-intelligence-2024-06-21</id>
        <link href="https://replicate.com/blog/replicate-intelligence-2024-06-21"/>
        <updated>2024-06-21T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[Really good coding model, AI search breakthroughs, Discord support bot]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Replicate Intelligence #6]]></title>
        <id>https://replicate.com/blog/replicate-intelligence-2024-06-28</id>
        <link href="https://replicate.com/blog/replicate-intelligence-2024-06-28"/>
        <updated>2024-06-28T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[Google's Gemma2 models, language model leaderboard, tips for Stable Diffusion 3]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Replicate Intelligence #7]]></title>
        <id>https://replicate.com/blog/replicate-intelligence-2024-07-12</id>
        <link href="https://replicate.com/blog/replicate-intelligence-2024-07-12"/>
        <updated>2024-07-12T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[Data curation, data generation, data data data]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Replicate Intelligence #8]]></title>
        <id>https://replicate.com/blog/replicate-intelligence-2024-07-26</id>
        <link href="https://replicate.com/blog/replicate-intelligence-2024-07-26"/>
        <updated>2024-07-26T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[A top-tier open-ish language model, new safety classifiers, model search API]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Replicate Intelligence #9]]></title>
        <id>https://replicate.com/blog/replicate-intelligence-2024-08-02</id>
        <link href="https://replicate.com/blog/replicate-intelligence-2024-08-02"/>
        <updated>2024-08-02T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[Open source frontier image model, cut objects from videos, new Python web framework from Jeremy Howard]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Replicate Intelligence #10]]></title>
        <id>https://replicate.com/blog/replicate-intelligence-2024-08-09</id>
        <link href="https://replicate.com/blog/replicate-intelligence-2024-08-09"/>
        <updated>2024-08-09T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[Flux developments, Minecraft bot, Streamlit cookbook with Zeke]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Replicate Intelligence #11]]></title>
        <id>https://replicate.com/blog/replicate-intelligence-2024-08-16</id>
        <link href="https://replicate.com/blog/replicate-intelligence-2024-08-16"/>
        <updated>2024-08-16T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[Fine tune FLUX.1, generative video games, a vision for the metaverse]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Replicate Intelligence #12]]></title>
        <id>https://replicate.com/blog/replicate-intelligence-2024-08-23</id>
        <link href="https://replicate.com/blog/replicate-intelligence-2024-08-23"/>
        <updated>2024-08-23T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[Flux LoRAs, Hot Zuck, and Replicate on Lex Fridman]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Scaffold Replicate apps with one command]]></title>
        <id>https://replicate.com/blog/replicate-scaffold</id>
        <link href="https://replicate.com/blog/replicate-scaffold"/>
        <updated>2023-11-22T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[We've added a CLI command that makes it easy to get started with Replicate.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Run Snowflake Arctic with an API]]></title>
        <id>https://replicate.com/blog/run-arctic-with-an-api</id>
        <link href="https://replicate.com/blog/run-arctic-with-an-api"/>
        <updated>2024-04-23T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[Arctic is a new open-source language model from Snowflake. Learn how to run it in the cloud with one line of code.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Using open-source models for faster and cheaper text embeddings]]></title>
        <id>https://replicate.com/blog/run-bge-embedding-models</id>
        <link href="https://replicate.com/blog/run-bge-embedding-models"/>
        <updated>2023-11-10T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[An interactive example showing how to embed text using a state-of-the-art embedding model that beats OpenAI's embeddings API on price and performance.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Run Code Llama 70B with an API]]></title>
        <id>https://replicate.com/blog/run-codellama-with-an-api</id>
        <link href="https://replicate.com/blog/run-codellama-with-an-api"/>
        <updated>2024-01-30T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[Code Llama 70B is one of the powerful open-source code generation models. Learn how to run it in the cloud with one line of code.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Generate images in one second on your Mac using a latent consistency model]]></title>
        <id>https://replicate.com/blog/run-latent-consistency-model-on-mac</id>
        <link href="https://replicate.com/blog/run-latent-consistency-model-on-mac"/>
        <updated>2023-10-25T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[How to run a latent consistency model on your M1 or M2 Mac]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Run Llama 2 with an API]]></title>
        <id>https://replicate.com/blog/run-llama-2-with-an-api</id>
        <link href="https://replicate.com/blog/run-llama-2-with-an-api"/>
        <updated>2023-07-27T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[Llama 2 is the first open source language model of the same caliber as OpenAI’s models. Learn how to run it in the cloud with one line of code.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Run Meta Llama 3.1 405B with an API]]></title>
        <id>https://replicate.com/blog/run-llama-3-1-with-an-api</id>
        <link href="https://replicate.com/blog/run-llama-3-1-with-an-api"/>
        <updated>2024-07-23T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[Llama 3.1 405B: is the most powerful open-source language model from Meta. Learn how to run it in the cloud with one line of code.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Run Meta Llama 3 with an API]]></title>
        <id>https://replicate.com/blog/run-llama-3-with-an-api</id>
        <link href="https://replicate.com/blog/run-llama-3-with-an-api"/>
        <updated>2024-04-18T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[Llama 3 is the latest language model from Meta. Learn how to run it in the cloud with one line of code.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[A comprehensive guide to running Llama 2 locally]]></title>
        <id>https://replicate.com/blog/run-llama-locally</id>
        <link href="https://replicate.com/blog/run-llama-locally"/>
        <updated>2023-07-22T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[How to run Llama 2 on Mac, Linux, Windows, and your phone.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[How to run Mistral 7B with an API]]></title>
        <id>https://replicate.com/blog/run-mistral-7b-with-api</id>
        <link href="https://replicate.com/blog/run-mistral-7b-with-api"/>
        <updated>2023-10-06T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[Mistral 7B is an open-source large language model. Learn what it's good at and how to run it in the cloud with one line of code.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Simplified AI Inference APIs on Replicate with NVIDIA NIM]]></title>
        <id>https://replicate.com/blog/run-nvidia-nim-models-on-replicate</id>
        <link href="https://replicate.com/blog/run-nvidia-nim-models-on-replicate"/>
        <updated>2024-06-02T00:00:00.000Z</updated>
    </entry>
    <entry>
        <title type="html"><![CDATA[Run Stable Diffusion 3 on your own machine with ComfyUI]]></title>
        <id>https://replicate.com/blog/run-sd3-on-comfyui</id>
        <link href="https://replicate.com/blog/run-sd3-on-comfyui"/>
        <updated>2024-06-14T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[Copy and paste a few commands into terminal to play with Stable Diffusion 3 on your own GPU-powered machine.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Run SDXL with an API]]></title>
        <id>https://replicate.com/blog/run-sdxl-with-an-api</id>
        <link href="https://replicate.com/blog/run-sdxl-with-an-api"/>
        <updated>2023-07-26T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[How to run Stable Diffusion XL 1.0 using the Replicate API]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Run Stable Diffusion 3 on your Apple Silicon Mac]]></title>
        <id>https://replicate.com/blog/run-stable-diffusion-3-on-apple-silicon-mac</id>
        <link href="https://replicate.com/blog/run-stable-diffusion-3-on-apple-silicon-mac"/>
        <updated>2024-06-18T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[A step-by-step guide to generating images with Stable Diffusion 3 on your M-series Mac using MPS acceleration.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Run Stable Diffusion 3 with an API]]></title>
        <id>https://replicate.com/blog/run-stable-diffusion-3-with-an-api</id>
        <link href="https://replicate.com/blog/run-stable-diffusion-3-with-an-api"/>
        <updated>2024-06-12T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[Stable Diffusion 3 is the latest text-to-image model from Stability, with improved image quality, typography, prompt understanding, and resource efficiency. Learn how to run it in the cloud with one line of code.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Run Stable Diffusion on your M1 Mac’s GPU]]></title>
        <id>https://replicate.com/blog/run-stable-diffusion-on-m1-mac</id>
        <link href="https://replicate.com/blog/run-stable-diffusion-on-m1-mac"/>
        <updated>2022-08-31T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[How to run Stable Diffusion locally so you can hack on it]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Run Stable Diffusion with an API]]></title>
        <id>https://replicate.com/blog/run-stable-diffusion-with-an-api</id>
        <link href="https://replicate.com/blog/run-stable-diffusion-with-an-api"/>
        <updated>2022-08-29T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[How to use Replicate to integrate Stable Diffusion into hacks, apps, and projects]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[How to run Yi chat models with an API]]></title>
        <id>https://replicate.com/blog/run-yi-chat-with-api</id>
        <link href="https://replicate.com/blog/run-yi-chat-with-api"/>
        <updated>2023-11-23T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[The Yi series models are large language models trained from scratch by developers at 01.AI. Learn how to run them in the cloud with one line of code.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Businesses are building on open-source AI]]></title>
        <id>https://replicate.com/blog/series-b</id>
        <link href="https://replicate.com/blog/series-b"/>
        <updated>2023-12-05T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[We've raised a $40 million Series B led by a16z.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Shared network vulnerability disclosure]]></title>
        <id>https://replicate.com/blog/shared-network-vulnerability-disclosure</id>
        <link href="https://replicate.com/blog/shared-network-vulnerability-disclosure"/>
        <updated>2024-05-23T00:00:00.000Z</updated>
    </entry>
    <entry>
        <title type="html"><![CDATA[Stable Diffusion 3.5 is here]]></title>
        <id>https://replicate.com/blog/stable-diffusion-3-5-is-here</id>
        <link href="https://replicate.com/blog/stable-diffusion-3-5-is-here"/>
        <updated>2024-10-22T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[Stability AI's latest text-to-image model is now available on Replicate and you can run it with an API.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Streaming output for language models]]></title>
        <id>https://replicate.com/blog/streaming</id>
        <link href="https://replicate.com/blog/streaming"/>
        <updated>2023-08-14T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[Our API now supports server-sent event streams for language models. Learn how to use them to make your apps more responsive.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Make any large language model a better poet]]></title>
        <id>https://replicate.com/blog/turn-your-llm-into-a-poet</id>
        <link href="https://replicate.com/blog/turn-your-llm-into-a-poet"/>
        <updated>2023-05-26T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[Prompt engineering and training are often the first solutions we reach for to improve language model behavior, but they're not the only way.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Join us at Uncanny Spaces]]></title>
        <id>https://replicate.com/blog/uncanny-spaces</id>
        <link href="https://replicate.com/blog/uncanny-spaces"/>
        <updated>2022-08-11T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[We're bringing people together to explore what's being created with machine learning.]]></summary>
    </entry>
    <entry>
        <title type="html"><![CDATA[Using synthetic training data to improve Flux finetunes]]></title>
        <id>https://replicate.com/blog/using-synthetic-data-to-improve-flux-finetunes</id>
        <link href="https://replicate.com/blog/using-synthetic-data-to-improve-flux-finetunes"/>
        <updated>2024-09-20T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[It's easy to fine-tune Flux, but sometimes you need to do a little more work to get the best results. This post covers techniques you can use to improve your fine-tuned Flux models.]]></summary>
    </entry>
</feed>