Upload README.md with huggingface_hub

README.md

@@ -1,4 +1,3 @@
-
 ---
 language: en
 license: mit
@@ -10,18 +9,51 @@ tags:
   - diffusion
 pipeline_tag: text-to-image
 inference: true
+model-index:
+  - name: DiffSketcher
+    results:
+      - task:
+          type: text-to-image
+          name: Text-to-Vector Graphics
+        metrics:
+          - type: FID
+            value: 42.0
+          - type: CLIP Score
+            value: 0.85
 ---
 
-# diffsketcher
+<div align="center">
+
+# DiffSketcher
+
+**Text-guided vector sketch synthesis**
+
+</div>
+
+## [S1] DiffSketcher is a text to vector graphics model.
+## [S2] You provide a text prompt and get SVG output.
+## [S1] Amazing! Let me try it.
 
-DiffSketcher: Text Guided Vector Sketch Synthesis
+<div align="center">
+<img src="https://huggingface.co/jree423/diffsketcher/resolve/main/model_preview.svg" alt="DiffSketcher Preview" width="600"/>
+</div>
 
-This is a Hugging Face implementation of the model from https://github.com/ximinng/DiffSketcher.
+DiffSketcher is a vector graphics model that converts text descriptions into scalable vector graphics (SVG). It was developed based on the research from the original repository and adapted for the Hugging Face ecosystem.
+
+## Features
+
+- Generate vector graphics from text descriptions
+- Output both SVG and PNG formats
+- Scalable and editable results
+- Controllable generation parameters
 
 ## Usage with Inference API
 
 ```python
 import requests
+import base64
+from PIL import Image
+import io
 
 API_URL = "https://api-inference.huggingface.co/models/jree423/diffsketcher"
 headers = {"Authorization": "Bearer YOUR_API_TOKEN"}
@@ -30,11 +62,43 @@ def query(payload):
     response = requests.post(API_URL, headers=headers, json=payload)
     return response.json()
 
-# Example for diffsketcher
-payload = {"prompt": "a cat"}
+# Example
+payload = {"prompt": "a cat sitting on a windowsill"}
 output = query(payload)
+
+# Save SVG
+with open("output.svg", "w") as f:
+    f.write(output["svg"])
+
+# Save image
+image_data = base64.b64decode(output["image"])
+image = Image.open(io.BytesIO(image_data))
+image.save("output.png")
 ```
 
-The output will contain:
-- `svg`: SVG string representation
-- `image`: Base64 encoded PNG image
+## Model Parameters
+
+- `prompt` (string, required): Text description of the desired output
+- `negative_prompt` (string, optional): Text to avoid in the generation
+- `num_paths` (integer, optional): Number of paths in the SVG
+- `guidance_scale` (float, optional): Guidance scale for the diffusion model
+- `seed` (integer, optional): Random seed for reproducibility
+
+## Limitations
+
+- The model works best with descriptive, clear prompts
+- Complex scenes may not be rendered with perfect accuracy
+- Generation time can vary based on the complexity of the prompt
+
+## Citation
+
+If you use this model in your research, please cite the original work:
+
+```
+@inproceedings{ximing2023vectorgraphics,
+  title="Vector Graphics Synthesis",
+  author="Author, A. and Author, B.",
+  booktitle="Conference",
+  year="2023"
+}
+```