Update README.md (#3)

- Update README.md (0b35d0d856782a9811e11400854e847b1b29b6c1)

README.md

@@ -159,7 +159,7 @@ Here is the output. Compared with the output from our text-to-image controlnet e
 ## Model Architecture
 
 ### Overview
-Kandinsky 2.1 is a text-conditional diffusion model based on unCLIP and latent diffusion, composed of a transformer-based image prior model, a unet diffusion model, and a decoder.   
+Kandinsky 2.2 is a text-conditional diffusion model based on unCLIP and latent diffusion, composed of a transformer-based image prior model, a unet diffusion model, and a decoder.   
 
 The model architectures are illustrated in the figure below - the chart on the left describes the process to train the image prior model, the figure in the center is the text-to-image generation process, and the figure on the right is image interpolation. 
 
@@ -167,13 +167,17 @@ The model architectures are illustrated in the figure below - the chart on the l
   <img src="https://raw.githubusercontent.com/ai-forever/Kandinsky-2/main/content/kandinsky21.png"/>
 </p>
 
-Specifically, the image prior model was trained on CLIP text and image embeddings generated with a pre-trained [mCLIP model](https://huggingface.co/M-CLIP/XLM-Roberta-Large-Vit-L-14). The trained image prior model is then used to generate mCLIP image embeddings for input text prompts. Both the input text prompts and its mCLIP image embeddings are used in the diffusion process. A [MoVQGAN](https://openreview.net/forum?id=Qb-AoSw4Jnm) model acts as the final block of the model, which decodes the latent representation into an actual image.
+Specifically, the image prior model was trained on CLIP text and image embeddings generated with a pre-trained [CLIP-ViT-G model](https://huggingface.co/laion/CLIP-ViT-g-14-laion2B-s12B-b42K). The trained image prior model is then used to generate CLIP image embeddings for input text prompts. Both the input text prompts and its CLIP image embeddings are used in the diffusion process. A [MoVQGAN](https://openreview.net/forum?id=Qb-AoSw4Jnm) model acts as the final block of the model, which decodes the latent representation into an actual image.
 
 
 ### Details
 The image prior training of the model was performed on the [LAION Improved Aesthetics dataset](https://huggingface.co/datasets/bhargavsdesai/laion_improved_aesthetics_6.5plus_with_images), and then fine-tuning was performed on the [LAION HighRes data](https://huggingface.co/datasets/laion/laion-high-resolution).
 
-The main Text2Image diffusion model was trained on the basis of 170M text-image pairs from the [LAION HighRes dataset](https://huggingface.co/datasets/laion/laion-high-resolution) (an important condition was the presence of images with a resolution of at least 768x768). The use of 170M pairs is due to the fact that we kept the UNet diffusion block from Kandinsky 2.0, which allowed us not to train it from scratch. Further, at the stage of fine-tuning, a dataset of 2M very high-quality high-resolution images with descriptions (COYO, anime, landmarks_russia, and a number of others) was used separately collected from open sources.
+The main Text2Image diffusion model was trained on [LAION HighRes dataset](https://huggingface.co/datasets/laion/laion-high-resolution) and then fine-tuned with a dataset of 2M very high-quality high-resolution images with descriptions (COYO, anime, landmarks_russia, and a number of others) was used separately collected from open sources.
+
+The main change in Kandinsky 2.2 is the replacement of CLIP-ViT-G. Its image encoder significantly increases the model's capability to generate more aesthetic pictures and better understand text, thus enhancing its overall performance. 
+
+Due to the switch CLIP model, the image prior model was retrained, and the Text2Image diffusion model was fine-tuned for 2000 iterations. Kandinsky 2.2 was trained on data of various resolutions, from 512 x 512 to 1536 x 1536, and also as different aspect ratios. As a result, Kandinsky 2.2 can generate 1024 x 1024 outputs with any aspect ratio.
 
 
 ### Evaluation