Comments (1)
I think the "k-diffusion" you are referring to is the k-lms scheduler? It is already used by default in this implementation.
About learning about diffusion models, I guess it would be hard to understand without previous experience with generative models like GANs and VAEs, also knowing about the network architecture that StableDiffusion uses helps too. Mostly if you want to edit the models themselves you would need a fair amount of theoretical knowledge about machine learning. I think the best way to learn would be taking a undergraduate course on machine learning then a few graduate courses about representation learning.
I got started by learning from courses and also a lot of self learning by reading papers. I'm not sure if there is any open courses similar to the one given at MILA (the one given there does not always have video recordings) (https://sites.google.com/view/ift-6135-h2020/lectures) but any course that resembles this one would get you 90% of the way there, and the last 10% catching up by reading the original paper on diffusion models (https://arxiv.org/abs/2006.11239), then the DALL-E 2 paper (https://arxiv.org/abs/2204.06125) and finally the StableDiffusion paper (https://arxiv.org/abs/2112.10752).
from crossattentioncontrol.
Related Issues (20)
- negative weighting HOT 1
- how to prevent promp 1 from being distorted HOT 1
- Question about the code in CrossAttention_Release.ipynb HOT 1
- Did you get a same result? HOT 1
- AttributeError: 'dict' object has no attribute 'sample' HOT 2
- Can't run the notebook in Google Colab, some issues with versions. HOT 2
- Notebook error HOT 3
- Add direct target editing to the notebook HOT 1
- How to make image inversion more precise? HOT 8
- please add InverseCrossAttention to colab
- Better support for prompt_edit_token_weights parsing
- Implementing Dreambooth weights HOT 2
- The differences from the official implementation? HOT 1
- About the finite difference gradient descent method HOT 1
- Question about original google implementation with stable diffusion HOT 3
- About terms["nll"]
- Why LMSDiscreteScheduler? HOT 1
- Relating to the recent paper about 'Self-guidance' method HOT 1
- An observation HOT 3
- Optmised for 6 GB? HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from crossattentioncontrol.