Update README.md

README.md

@@ -15,7 +15,6 @@ license: apache-2.0
 
 In this repository, we provide a family of diffusion models to generate a video or an image (<em>Coming Soon</em>) given a textual prompt and distilled model for faster generation.
 
-https://github.com/user-attachments/assets/b9ff0417-02a4-4f6b-aacc-60c44e7fe6f1
 
 ## Project Updates
 
@@ -265,7 +264,7 @@ images = pipe(
 Video("./test.mp4")
 ```
 
-Please, refer to [inference_example.ipynb](inference_example.ipynb) notebook for more usage details.
+Please, refer to [inference_example.ipynb](https://github.com/ai-forever/Kandinsky-5/blob/main/inference_example.ipynb) notebook for more usage details.
 
 ### Distributed Inference
 
@@ -293,7 +292,7 @@ python test.py --prompt "A dog in red hat" --magcache
 
 ### ComfyUI
 
-See the instruction [here](comfyui)
+See the instruction [here]((https://github.com/ai-forever/Kandinsky-5/tree/main/comfyui))
 
 ### Beta testing
 You can apply to participate in the beta testing of the Kandinsky Video Lite via the [telegram bot](https://t.me/kandinsky_access_bot).