About the challenge

This hackathon is about experimenting with FLUX.1 Kontext [dev].

Create a LoRA. Combine it with other FLUX models. Build a workflow. Or just try something totally unexpected.

You can run Kontext [dev] however you like - locally on your own setup, or through our partners FAL and Ostris' AI Toolkit on Hugging Face if you don’t have GPUs handy.

The goal is simple: play, explore, and push Kontext [dev] into new directions. Surprise us with what you make.

Get started

Check the resources tab for more info

Requirements

What to Build

Apply FLUX.1 Kontext [dev] in an innovative way, surprise use with new capabilities or workflows. Think in terms of what falls into the following categories - we’ll pick one winner for each:

  • Best Overall - the most impressive and innovative application of FLUX.1 Kontext [dev]

  • Best LoRA - the most creative, useful, or technically impressive LoRA fine-tune (style, concept, character, workflow)

  • Most Creative Vision - the most artistic and visually stunning project built with Kontext [dev]

  • Best Local Use Case - the smartest offline or local workflow using Kontext [dev], combining tools, agents, or hardware in novel ways

What to Submit

  1. Choose the category or categories that best aligns with your project and provide a brief explanation for your choice.

  2. Text description that explains the features and functionality of your Project.

  3. <3-minute Demonstration video of your Project

  4. Provide a URL to your public code repository for judging and testing, with clear indication of FLUX.1 Kontext [dev] model use (e.g., README with testing instructions, sample data, or a link to model weights / training data if you created LoRAs). An OSS/Apache License is encouraged, but not required.

Hackathon Sponsors

Prizes

$5,000+ in prizes
+ other prizes
Best Overall | Sponsored by Black Forest Labs
$3,000 in cash
1 winner

Best Local Use Case | Sponsored by NVIDIA
1 winner

1x NVIDIA RTX 5090 GPU (ARV: $1,999)

Most Creative Vision | Sponsored by Black Forest Labs
$2,000 in cash
1 winner

Best LoRA | Sponsored by FAL
1 winner

$3,000 FAL Credits, sponsored by FAL

Devpost Achievements

Submitting to this hackathon could earn you:

Judges

Saksham Consul

Saksham Consul
Member of Technical Staff / Black Forest Labs

Michael Fukuyama

Michael Fukuyama
Product Manager - Visual PC Generative AI / NVIDIA

Stephen Batifol

Stephen Batifol
Developer Advocate / Black Forest Labs

Kaan Oktay

Kaan Oktay
AI / FAL

Apolinário Passos
Head of Machine Learning for Art and Creativity / Hugging Face

Judging Criteria

  • Usage of FLUX.1 Kontext [dev]
    Does the project apply the model in an effective way, fitting with the categories? Can other models do the same thing, or does the project showcase the strengths of the models uniquely?
  • Potential Impact
    How big of an impact could the project have for its intended audience? How big of an impact could it have beyond the target community and the rest of the world?
  • Novelty of the Idea
    How creative and unique is the project? Does the concept exist already? If so, how much does the project improve on it?

Questions? Email the hackathon manager

Tell your friends

Hackathon sponsors

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.