update inst

app.py

@@ -306,10 +306,40 @@ def generate(
 
 # --- Gradio UI Definition ---
 with gr.Blocks(title="HDM Demo", theme=gr.themes.Soft()) as demo:
-    gr.Markdown("# HDM Demo")
+    gr.Markdown("# HDM Early Demo")
     gr.Markdown(
         "### Enter a natural language prompt and/or specific tags to generate an image."
     )
+    with gr.Accordion("Introduction", open=False):
+        gr.Markdown("""
+# HDM: HomeDiffusion Model Project
+HDM is a project to implement a series of generative model that can be pretrained at home.
+
+## About this Demo
+This DEMO used a checkpoint during training to demostrate the functionality of HDM.
+Not final model yet.
+
+## Usage
+This early model used a model trained on anime image set only, 
+so you should expect to see anime style images only in this demo.
+
+For prompting, enter danbooru tag prompt to the box "Tag Prompt" with comma seperated and remove the underscore.
+enter natural language prompt to the box "Natural Language Prompt" and enter negative prompt to the box "Negative Prompt".
+
+If you don't want to spent so much effort on prompting, try to keep "Enable TIPO" selected.
+
+If you don't want to apply any pre-defined format, unselect "Enable TIPO" and "Enable Format".
+
+## Model Spec
+- Backbone: 342M custom DiT(UViT modified) arch
+- Text Encoder: Qwen3 0.6B (596M)
+- VAE: EQ-SDXL-VAE, an EQ-VAE finetuned sdxl vae.
+
+## Pretraining Dataset
+- Danbooru 2023 (latest id around 8M)
+- Pixiv famous artist set
+- some pvc figure photos
+""")
 
     with gr.Row():
         with gr.Column(scale=2):