Update app.py

Changed grid to columns in the outputs.

app.py

@@ -102,7 +102,7 @@ gr.Interface(
         ),
         gr.Image(),
     ],
-    outputs=gr.Gallery(grid=[2], height="auto"),
+    outputs=gr.Gallery(columns=2, height="auto"),
     title="Generate controlled outputs with Categorical Conditioning on Waifu Diffusion 1.5 beta 2.",
     description="This Space uses image examples as style conditioning. Experimental proof of concept made for the [Huggingface JAX/Diffusers community sprint](https://github.com/huggingface/community-events/tree/main/jax-controlnet-sprint)[Demo available here](https://huggingface.co/spaces/Ryukijano/CatCon-One-Shot-Controlnet-SD-1-5-b2)[My teammate's demo is available here] (https://huggingface.co/spaces/Cognomen/CatCon-Controlnet-WD-1-5-b2) This is a controlnet for the Stable Diffusion checkpoint [Waifu Diffusion 1.5 beta 2](https://huggingface.co/waifu-diffusion/wd-1-5-beta2) which aims to guide image generation by conditioning outputs with patches of images from a common category of the training target examples. The current checkpoint has been trained for approx. 100k steps on a filtered subset of [Danbooru 2021](https://gwern.net/danbooru2021) using artists as the conditioned category with the aim of learning robust style transfer from an image example.Major limitations:- The current checkpoint was trained on 768x768 crops without aspect ratio checkpointing. Loss in coherence for non-square aspect ratios can be expected.- The training dataset is extremely noisy and used without filtering stylistic outliers from within each category, so performance may be less than ideal. A more diverse dataset with a larger variety of styles and categories would likely have better performance.- The Waifu Diffusion base model is a hybrid anime/photography model, and can unpredictably jump between those modalities.- As styling is sensitive to divergences in model checkpoints, the capabilities of this controlnet are not expected to predictably apply to other SD 2.X checkpoints.",