Hot starts, batch inference, and what's next for Runpod Serverless. Webinar June 25.

Blog

Get Better DreamBooth Results Using Offset Noise

DreamBooth tends to overfit and produce weird artifacts, like extra heads or multiple faces, especially with only a few training images. One trick to.

Get Better DreamBooth Results Using Offset Noise

TheLastBen recently updated our fast stable diffusion template with the offset noise functionality in dreambooth!

To turn it on, start up the template and connect to the jupyter link. Then just flip the Offset_Noise variable to "True" and increase your total steps by 10-20% - that's it!

Jupyter notebook DreamBooth training settings with the Offset_Noise option circled in red

Apparently this can get you some really awesome outputs in the realm that SD usually can't touch ( very dark and very light images). For more on the research behind this, you can check out this research blog post

and this YouTube video:

The results look pretty stunning, so go check it out yourself!

‍

Author profile: Zhen Lu

Blog Posts

Related articles

View All
Deploy When Available is now GA

Deploy When Available is now GA

Queue for any GPU spec, even one that's fully rented out, and we'll deploy it the moment capacity opens up. No more refreshing the console or running a sniping tool.

All
Deploy When Available is now GA
The Chips Got Faster. The Stack Didn't.

The Chips Got Faster. The Stack Didn't.

Explore why faster chips have shifted the bottleneck to AI infrastructure, and what that means for teams running production workloads.

All
The Chips Got Faster. The Stack Didn't.

Build what’s next.

Build, train, and scale AI workloads on Runpod with cloud GPUs, Serverless, and Clusters.