diff --git a/README.md b/README.md
index c60061e..73753ac 100644
--- a/README.md
+++ b/README.md
@@ -4,8 +4,17 @@ Custom nodes make easy Advanced Workflows.
 Focus on Image\Video and ControlNet efficiency and performances.
 Manipulation of Latent Space, Automatic pipeline with a bit efforts.
 --------------
+New Nodes in pack Den Workflow ComfyUI
+#### ImageToLatent node: `Den_ImageToLatentSpace`
+#### GPT Sampler: `Den_GPTSampler_llama`
+#### GPT load: `Den_GPTLoaderSimple_llama`
+#### SD Video: `Den_SVD_img2vid`
+#### ImageToLatent node: `Den_ImageToLatentSpace`
+#### FaceRestore Model codeformer: `Den_FaceRestoreCFWithModel`
+--------------
 #### Using GPT & LLM models : Llava,GGUF
 https://huggingface.co/models?library=gguf&sort=trending&search=llava
+
 #### GPT load: `Den_GPTLoaderSimple_llama`
 - Load Model and Clip for LLM
 
@@ -17,6 +26,7 @@ https://huggingface.co/models?library=gguf&sort=trending&search=llava
 ![](ba951e180cc4c9304541abe2843c28ce.png)
 
 - Example Workflow GPT-SD
+
 ![](6da778c85399f187e2829a3e460b2938.jpg)
 
 #### SD Video: `Den_SVD_img2vid`
@@ -25,14 +35,16 @@ https://huggingface.co/models?library=gguf&sort=trending&search=llava
 
 ![](dfdbcbea00bdfcbdcf7d0d73b3cb83f7.png)
 
-
-
 #### ImageToLatent node: `Den_ImageToLatentSpace`
 
 ![](17b6e18ef0deec9f82138b66ca7aace6.png)
 
 - Latent space from size Image
+
 ![](d88f68c317f3f790055be5978e2689dc.png)
+
+- FaceRestore With Model Gan or CodeFormer
+![](b64810ce1266a038ccd532aa9389c996.png)
 --------------
 ![ComfyUI Screenshot](e92381a5d7c26f138d1451c8b4f52142.jpg)
 
diff --git a/b64810ce1266a038ccd532aa9389c996.png b/b64810ce1266a038ccd532aa9389c996.png
index 2f853de..ac486fd 100644
Binary files a/b64810ce1266a038ccd532aa9389c996.png and b/b64810ce1266a038ccd532aa9389c996.png differ