You can now edit text-to-video models in under 1 second! ⚡️🚀🎥

Unified Concept Editing now supports video models, thanks to Mamiglia!

It's amazing how UCE extends to large video models: instant erase/edit (1 sec) compared to standard fine-tuning (>30 mins) ⏱️

Try the code👇

We discovered how to fix diffusion model's diversity issues using interpretability!

It's all in the first time-step!⏱️

Turns out the concepts to be diverse are present in the model - it simply doesn't use them!

Checkout our @wacv_official work - we added theoretical evidence👇
x.com/rohitgandik...

We tested several unlearning methods and found none of them really erase knowledge from the model - they simply hide it! 🧐

What does this mean? We must tread carefully with unlearning research within diffusion models🚨

Here is what we learned 🧵👇(led by @kevinlu4588)
x.com/kevinlu4588...

Erasing Concepts from FLUX.1 models 🔥

ESD now supports FLUX models, and we've recently added SDXL support as well.

Check out the code and share your experiments with us:
github.com/rohitgandik...

(This is a long-awaited request from our users - thank you for your patience!)

x.com/RohitGandik...

New Preprint 🚀

Can diffusion models draw artistic inspiration from nature? 🤔

@huiren and @materzynska trained a diffusion model solely on natural images, excluding artwork from pre-training data ❌🎨

Surprisingly, it can mimic art styles!

Curious how it works?👇🧵w/ @davidbau and Antonio Torralba

Stuck on what Thanksgiving dish to cook? 🦃 Here are some AI generated ideas - by composing concepts like "cooked" and "fancy" dinner. 🍗🥧 You can also blend and explore “vegetarian”, “healthier diet”, and many more!

Stay tuned for technical details! 🧵

Happy Holidays!🎄✨

@davidbau.bsky.social