-
### Motivation.
I am one of the authors of the paper Stay On Topic with Classifier-Free Guidance ( https://openreview.net/forum?id=RiM3cl9MdK¬eId=s1BXLL1YZD ) who has been nominated as ICML'24 Spo…
-
### 🚀 The feature, motivation and pitch
Implementation in transformers: https://github.com/huggingface/transformers/blob/6b22a8f2d8ded6b2a681e1c078b0e1abf27d045c/src/transformers/generation/logits_…
-
Hi, Mr Gu,
I am trying your code. I notice that you did not do any mask on the text in your trainging code, but you did classifier free guidance in your eval code. I want to know if you did thi…
-
Hello, thanks for your paper.
I have a small question. Is your paper applicable for text2image networks? Concrete for Classifier Free Guidance. Can FDM precondition be used for conditional input and …
-
### Model/Pipeline/Scheduler description
The paper's authors performs an analysis and proposes 1 line change in order to make Classifier-Free Guidance looks better
![cfg](https://github.com/huggin…
-
Classifier-free guidance was implemented in llama.cpp in https://github.com/ggerganov/llama.cpp/pull/2135, but it doesn't look like there's a way to use it with these bindings. It seems like a useful …
-
https://arxiv.org/pdf/2306.17806.pdf
notes:
- basically gives a "guidance prompt," the idea being that it wont decay in context the same way the normal prompt does (normal prompt is just treated l…
-
Hi, thank you for your excellent work. I checked your code carefully and I am curious about why you did not use classifier-free guidance.
-
In the classifier-free guidance paper, the formulation is as follow
However, it is imple…
-
I might have missed it in the code, but I can't see whether we randomly drop the captions for classifier-free guidance (which is already used at inference).