this is excellent. i just can't understand why companies (e.g., openai in this case) cannot add small notational hints to make their method more understandable. your diagram at around 2:50 is better than the 2 page gibberish actual paper presents. great work!
@Erik_Fenety
Ай бұрын
Hyperparameter tuning: Finding optimal hyperparameters (e.g., learning rate, network architecture) often involves training multiple models with different configurations, multiplying the computational cost. Complex architectures: Advanced architectures like convolutional neural networks or recurrent neural networks involve specialized operations that add to the computational complexity.
@rezarawassizadeh4601
2 жыл бұрын
Thank you for this easy to understand, to my understanding CLIP is not separate from Prior. Prior includes the frozen CLIP model that constructs image embedding.
@B_knows_A_R_D-xh5lo
2 ай бұрын
😊😊😊😊
@liji9354
2 жыл бұрын
Thank you so much! this is super helpful!
@salomeshunamon
Жыл бұрын
How would you say DALLE2 compares to Stable Diffusion architecturally? Would you consider Stable Diffusion a latent diffusion model, denoising diffusion model or something else?
@salomeshunamon
Жыл бұрын
Another question :) I see in the table that humans evaluated the output and rated the photos by photorealism and prompt accuracy, but what is diversity?
@AIBites
Жыл бұрын
so diversity is how different the output images look. For example, if you want images of winter, then the generated images should not always show hibernating trees without leaves but also show snow
Пікірлер: 10