Update README.md

README.md

@@ -52,30 +52,35 @@ image.show()
 
 ### 🔄 Flexible Prompt Composition
 
-The prompts used in UniEM-Gen are highly modular — keywords describing morphology, structure, color, and texture can be freely combined to generate diverse electron micrographs. This compositional flexibility allows users to craft custom prompts by mixing and matching descriptive terms.
+You can generate structured scientific descriptions by randomly sampling one term from each of the nine attribute categories defined in the **[UniEM-3M](https://huggingface.co/datasets/NNNan/UniEM-3M)**. This repository includes attribute_values.json, which contains all observed values for these attributes, enabling reproducible and diverse prompt generation.
 
-You can randomly sample one term from each of the nine attribute categories defined in the **[UniEM-3M](https://huggingface.co/datasets/NNNan/UniEM-3M)**, then assemble them into a coherent prompt using the following structured template:
+Use the following template to assemble the sampled terms into a coherent description:
 
 ```text
 <microscopy_type> of <subject>: <morphology>. <surface_texture>. <particle_density>. <distribution>. <layering>. <pixel_size_profile>. <color_profile>.
-💬 Replace each <...> placeholder with a real value from the corresponding category.
+"💬 Replace each <...> placeholder with a real value from the corresponding category."
 ```
 
 ```python
 # Sampled attributes from UniEM-3M
-from collections import defaultdict
-from datasets import load_dataset
-
-attribute_values = defaultdict(set)
-dataset = load_dataset('NNNan/UniEM-3M')
-
-for attr_dict in dataset['synthesized_data_structured_descriptions']['attribute_description']:
-  for key, value in attr_dict.items():
-    attribute_values[key].add(value)
-
-
-# Construct the prompt
-prompt = f"{microscopy_type} of {subject}: {morphology}. {surface_texture}. {particle_density}. {distribution}. {layering}. {pixel_size_profile}. {color_profile}."
+from huggingface_hub import hf_hub_download
+import json
+import random
+
+# Download the attribute_values.json file from the repo
+json_path = hf_hub_download(
+    repo_id="NNNan/UniEM-Gen",
+    filename="attribute_values.json"
+)
+
+# Load the attribute values
+with open(json_path, "r", encoding="utf-8") as f:
+    attribute_values = json.load(f)
+
+# Generate a random description
+template = "{microscopy_type} of {subject}: {morphology}. {surface_texture}. {particle_density}. {distribution}. {layering}. {pixel_size_profile}. {color_profile}."
+sampled = {k: random.choice(list(v)) for k, v in attribute_values.items()}
+prompt = template.format(**sampled)
 print(prompt)
 ```