Update README.md

README.md

@@ -59,7 +59,7 @@ license: apache-2.0
 
 ## Description:
 
-Kandinsky 4.0 is a text-to-video generation model based on latent diffusion for 480p and HD resolutions. Here we present distiled version of this model **Kandisnly 4 flash**, that can generate **12 second videos** in 480p resolution in **11 seconds** on a single NVIDIA H100 gpu. The pipeline consist of 3D causal [CogVideoX](https://arxiv.org/pdf/2408.06072) VAE, text embedder [T5-V1.1-XXL](https://huggingface.co/google/t5-v1_1-xxl) and our trained MMDiT-like transformer model.
+Kandinsky 4.0 T2V Flash is a text-to-video generation model based on latent diffusion for 480p resolution, that can generate **12 second videos** in 480p resolution in **11 seconds** on a single NVIDIA H100 gpu. The pipeline consist of 3D causal [CogVideoX](https://arxiv.org/pdf/2408.06072) VAE, text embedder [T5-V1.1-XXL](https://huggingface.co/google/t5-v1_1-xxl) and our trained MMDiT-like transformer model.
 
 <img src="https://github.com/ai-forever/Kandinsky-4/assets/pipeline.png">
 
@@ -70,7 +70,7 @@ A serious problem for all diffusion models, and especially video generation mode
 
 ## Architecture
 
-For training Kandinsky 4 Flash we used the following architecture of diffusion transformer, based on MMDiT proposed in [Stable Diffusion 3](https://arxiv.org/pdf/2403.03206).
+For training Kandinsky 4.0 T2V Flash we used the following architecture of diffusion transformer, based on MMDiT proposed in [Stable Diffusion 3](https://arxiv.org/pdf/2403.03206).
 
 <img src="https://github.com/ai-forever/Kandinsky-4/assets/MMDiT1.png"> <img src="https://github.com/ai-forever/Kandinsky-4/assets/MMDiT_block1.png">