惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

博客园 - Franky
N
Netflix TechBlog - Medium
宝玉的分享
宝玉的分享
Google DeepMind News
Google DeepMind News
腾讯CDC
G
Google Developers Blog
Martin Fowler
Martin Fowler
Microsoft Security Blog
Microsoft Security Blog
Recent Announcements
Recent Announcements
爱范儿
爱范儿
Engineering at Meta
Engineering at Meta
Microsoft Azure Blog
Microsoft Azure Blog
A
About on SuperTechFans
aimingoo的专栏
aimingoo的专栏
有赞技术团队
有赞技术团队
Jina AI
Jina AI
人人都是产品经理
人人都是产品经理
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
M
MIT News - Artificial intelligence
罗磊的独立博客
博客园 - 三生石上(FineUI控件)
美团技术团队
WordPress大学
WordPress大学
阮一峰的网络日志
阮一峰的网络日志

Replicate's blog

How to make remarkable videos with Seedance 2.0 – Replicate blog How to prompt Seedream 5.0 – Replicate blog Recraft V4: image generation with design taste – Replicate blog Run Isaac 0.1 on Replicate – Replicate blog Run FLUX.2 on Replicate – Replicate blog How to prompt Nano Banana Pro – Replicate blog Retro Diffusion's pixel art models are now on Replicate – Replicate blog Replicate is joining Cloudflare – Replicate blog Extract text from documents and images with Datalab Marker and OCR – Replicate blog How to prompt Veo 3.1 – Replicate blog IBM's Granite 4.0 is now on Replicate – Replicate blog Which image editing model should I use? – Replicate blog Introducing our new search API – Replicate blog Torch compile caching for inference speed – Replicate blog Announcing Replicate's remote MCP server – Replicate blog How to prompt Veo 3 with images – Replicate blog Open source video is back – Replicate blog Generate consistent characters – Replicate blog Bria is now on Replicate – Replicate blog How we optimized FLUX.1 Kontext [dev] – Replicate blog Compare AI video models – Replicate blog How to prompt Veo 3 for the best results – Replicate blog Get the most from Google Veo 3 – Replicate blog FLUX.1 Kontext from the community – Replicate blog Use FLUX.1 Kontext to edit images with words – Replicate blog Generate incredible images with Google's Imagen 4 – Replicate blog Run OpenAI’s latest models on Replicate – Replicate blog NVIDIA H100 GPUs are here – Replicate blog Run 30,000+ LoRAs on Hugging Face with Replicate – Replicate blog Ideogram 3.0 on Replicate – Replicate blog
The FLUX.1 Kontext hackathon – Replicate blog
2025-07-01 · via Replicate's blog
FLUX.1 Kontext hackathon participants working on their projects

AI fashion assistants. UI variants of your favorite websites. Voice-assisted photo editors. 3D dinner tables. Text-to-movie apps.

Our FLUX.1 Kontext hackathon might’ve been our best one yet. We teamed up with Black Forest Labs to give over 120 participants the chance to build with FLUX.1 Kontext, the image editing model that has taken the AI community by storm. Resemble AI also joined us to get hackers to build with Chatterbox, their latest text-to-speech model.

We had some insanely creative projects and we were thoroughly impressed by what people built in a couple hours. Choosing from 30 submissions wasn’t easy, but a few stood out to us.

Here were the winners.

Replicate’s picks:

  • Tartan Photographers: AI-automated Shopify listings

    Rafael Cabrera and Christian Cherry created a site which automates uploading listings on Shopify and even edits your product photos with FLUX.1 Kontext to make them click-enticing. We last saw this power team at our Carnegie Mellon University hackathon, and we’re super glad they were able to build with Replicate again!

  • The Table: Conjure food on a 3D dinner table

    This was a fun little project by David Tian. Users enter a food item and a 3D render of it from firtoz/trellis will be placed on a virtual dinner table. We thought this was a neat application of chaining models, super clean UI, fun application of graphics principles: just an overall good hack.

Black Forest Labs’ picks:

  • sellmyshit: Upload products to digital marketplaces

    Another great marketplace-integration app from Vibhu Sapra. sellmyshit allows users to create listings on Ebay, Craigslist, and Facebook Marketplace with generated text descriptions and FLUX.1 Kontext image editing. Such a useful tool that takes the drudgery out of making good product listings!

  • Infinity: AI Dungeons and Dragons

    Pretty much infinite Dungeons and Dragons, all generated images tossed back and forth to FLUX.1 Kontext. Created by Nihar Asare, this was the selling point: “Play for 5 minutes. 5 hours. 5 days. 5 years.”

Resemble AI’s pick:

  • Intel i5-8250U: AI journey generator

    A creative storytelling app made by Fouzan Abdullah and Saad Ahmed that generates personalized adventure narratives using AI. Users input their preferences and the app creates unique journey experiences with custom imagery and descriptions, all powered by FLUX.1 Kontext for visual storytelling and Chatterbox for engaging audio.

Most ‘Vibiest’ Project

We had an extra surprise up our sleeve — Most “Vibeist” Project. These prizes went out to the hacks we thought were just cool, interesting, or flat out “vibey.”

  • VoiceCam: Edit photos with your voice

    Before the hackathon, our fellow Replicant Zeke demonstrated to hackers how you can use FLUX.1 Kontext to make a realtime image editing assistant powered by your voice. Hacker Matt Wong took it and ran to create a snappy mobile version that even works with your phone camera. Sick!

  • NatureBrawl: AI-powered nature battle simulator

    Bryant Wolf built an imaginative game where users can pit different animals against each other in epic battles. The app uses FLUX.1 Kontext to generate dynamic battle scenes and visual effects, creating unique showdowns between creatures. It also had a crazy good UI.

  • FLUX Vibes: Style image transformation app

    A creative app made by Arjun Kaul that transforms photos straight from your camera roll with different styles. We were particularly impressed by the search functionality Arjun developed where users are offered a pruned list of styles to select from based on his or her query.

We were incredibly inspired by the cracked energy. Congrats to all the hackers!

(Check out all the projects here.)


Speaking of hacking, now you can go one layer deeper with FLUX.1 Kontext.

That’s right, Black Forest Labs has released FLUX.1 Kontext dev — open code, open weights. There’s so much you can explore with dev: multi-image or multi-LoRA support, fast inference tricks, playful prompt embeddings in CLIP space, or you could recreate our FLUX.1 Kontext apps closer to the bare metal. There’s endless opportunity to flex your AI engineering muscles. It’s not everyday that we get something open source from Black Forest Labs!

We want to see what you can build. Can you conquer any of those challenges I listed, or solve one of your own?

As always, reach out on our Discord for hacking help and share what you create on X.