-
Hello @orpatashnik - Great work!
I wanted to perform a test and create a new StyleGan2 model with CLIP. So simply adding "captions" like male, and female to the images, and learn how it works.
…
-
### Is there an existing issue for this?
- [X] I have searched the existing issues and checked the recent builds/commits
### What happened?
I have my prompts saved to re-use and get similar results…
-
## タイトル: SDXL Turbo：スパースオートエンコーダを用いたテキスト画像生成モデルの解釈
## リンク: https://arxiv.org/abs/2410.22366
## 概要:
スパースオートエンコーダ（SAE）は大規模言語モデル（LLM）のリバースエンジニアリングにおいて中心的な要素となっています。LLMでは、SAEは、直接解釈することが難しい中間表現を、解釈可能な特…
-
My machine is a MacBook Air M1 with 16GB ram
When using Stable Diffusion 2.1 from stabilityai, I get the following error spammed to console, seemingly with each step (but not confirmed):
```
2022…
-
Trying to develop diffusion BIDS apps is made significantly more difficult by using the FSL bval/bvec format. A format that is dependent on the image axis (and even then only *sometimes*) means that a…
-
**First of all, thank You for the great and inspiring work You did!**
The quality of the results I am getting seems to be much lower than the results that are shown on the website.
I used the defa…
-
### Describe the bug
`pipeline_stable_diffusion.py` trys to encode the prompt when there is no prompt and `prompt_embeds` and `negative_prompt_embeds` are given.
### Reproduction
Use `--pre_comput…
-
Hi, in the example notebook text2im.ipynb, I'm not clear on how to use a larger batch size that 1, or the recommended way to generate many images?
I'd like to play around with the model and generat…
-
Is there a method for enabling / using the SD XL refiner. Ideally using passing over the latent rather than using img2img.
-
Can you please make a yt video on how to get ort models and install them on Android sdai app I'm looking everywhere for custom ort models but can't find any.