diffusion-models-class VS stable-diffusion

When you use stable diffusion, you can adjust the classifier free guidance scale to control how much it follows the input prompt. From what I understand(check https://github.com/huggingface/diffusion-models-class/tree/main/unit3), what cfg does is that it generates an unconditional image and an image conditional on the text prompt, and then scale up the difference.

https://huggingface.co/learn/nlp-course/ https://huggingface.co/docs/transformers (go through the task guide) https://github.com/huggingface/diffusion-models-class http://d2l.ai/ https://www.youtube.com/watch?v=VMj-3S1tku0&list=PLAqhIrjkxbuWI23v9cThsA9GvCAUhRvKZ

I couldn't understand the original paper(havent done meth in a long time). This blog post and short course help me to understand.

The Diffusion Models Course is another good resource to learn more technical details.

Next, you need to become familiar with the diffusion model. I recommend this huggingface's course(https://github.com/huggingface/diffusion-models-class) because it is very high quality and you will learn while using diffusers. At first glance, it may not seem directly related to this game, but in my case, knowing what is happening in diffusers helped me in many ways: trial and error, inspiration for ideas, etc. I had no knowledge of pytorch (the deep learning library used for diffusers), so I also took this course (https://www.udacity.com/course/deep-learning-pytorch--ud188) which was in the prerequisites for that huggingface's course. It was also very good.

Hugging Face Dreambooth Hackaton details

Details: https://github.com/huggingface/diffusion-models-class/blob/main/hackathon/README.md

What are the differences between the stable diffusion projects by Stability-AI and RunwayML? In addition, a similar project Diffusers by HuggingFace also exists, is that different as well?

Ok. I refreshed my memory (here). RunwayML did the training. Stability AI donated the compute. At least. 1 member of the german research team has gone to work for RML and basically continued his work there. I'm not clear at all on the relationship between SAI and RML.

Pretty sure. There's an in painting model that is available! I heard it's pretty good! https://github.com/runwayml/stable-diffusion

so use it with the fork it was designed to work on: https://github.com/runwayml/stable-diffusion

source: https://github.com/runwayml/stable-diffusion/blob/main/Stable_Diffusion_v1_Model_Card.md

If this gets taken down because of the cucks at Stability, you can also download the model weights at https://github.com/runwayml/stable-diffusion