【双语】Stable Diffusion from Scratch in PyTorch - Conditional LDM
TIP! Right-click and select "Save link as..." to download.
| VIDEOS | |||
| MP4 | N/A | 480P | Download |
| MP4 | N/A | 360P | Download |
| AUDIO | |||
| MP4 | N/A | mp4a.40.2 | Download |
| MP4 | N/A | mp4a.40.5 | Download |
| MP4 | N/A | mp4a.40.2 | Download |
| THUMBNAILS | |||
|
JPEG | Origin Image | Download |
转载自 https://www.youtube.com/watch/hEJjg7VUA8g
In this video, we'll cover all the different types of conditioning in latent diffusion and finish stable diffusion implementation in PyTorch and after this you would be able to build and train Stable Diffusion from scratch.
This is Part II of the tutorial where I get into conditioning in latent diffusion models. We dive deep into class conditioning in latent diffusion models, implementing class conditional latent diffusion model and see results of training latent diffusion model to conditionally generate mnist digits.
Then we get into semantic synthesis in latent diffusion models, and implement that.
We also understand super resolution in latent diffusion and see how inpainting with latent diffusion model can be done without training it for that. We then see latent diffusion model is fine tuned for inpainting.
Finally we get into cross attention and see how stable diffusion uses cross attention to do text conditioning. We will also implement cross attention for latent diffusion models and see results of text to image latent diffusion models
We then see how to move from latent diffusion to stable diffusion model and also talk about clip a bit. By the end of this video, you will be able to code conditional stable diffusion in PyTorch by yourself.
Paper - http://tinyurl.com/exai-latent-diffus...
Implementation - http://tinyurl.com/exai-stable-diffus...
🔔 Subscribe
https://tinyurl.com/exai-channel-link
In this video, we'll cover all the different types of conditioning in latent diffusion and finish stable diffusion implementation in PyTorch and after this you would be able to build and train Stable Diffusion from scratch.
This is Part II of the tutorial where I get into conditioning in latent diffusion models. We dive deep into class conditioning in latent diffusion models, implementing class conditional latent diffusion model and see results of training latent diffusion model to conditionally generate mnist digits.
Then we get into semantic synthesis in latent diffusion models, and implement that.
We also understand super resolution in latent diffusion and see how inpainting with latent diffusion model can be done without training it for that. We then see latent diffusion model is fine tuned for inpainting.
Finally we get into cross attention and see how stable diffusion uses cross attention to do text conditioning. We will also implement cross attention for latent diffusion models and see results of text to image latent diffusion models
We then see how to move from latent diffusion to stable diffusion model and also talk about clip a bit. By the end of this video, you will be able to code conditional stable diffusion in PyTorch by yourself.
Paper - http://tinyurl.com/exai-latent-diffus...
Implementation - http://tinyurl.com/exai-stable-diffus...
🔔 Subscribe
https://tinyurl.com/exai-channel-link
Supported Sites
