Upload README.md with huggingface_hub

README.md

@@ -1,59 +1,10 @@
----
-license: mit
-base_model: runwayml/stable-diffusion-v1-5
-tags:
-  - text-to-image
-  - diffusers
-  - vector-graphics
-  - svg
-  - sketch
-  - stable-diffusion
-pipeline_tag: text-to-image
-inference: true
----
 
-# DiffSketcher
+# Diffsketcher
 
-This is a Hugging Face implementation of [DiffSketcher](https://github.com/ximinng/DiffSketcher), a method for generating SVG sketches from text prompts.
-
-## Model Description
-
-DiffSketcher is a novel approach to generate SVG sketches from text prompts. It uses a differentiable rasterizer to optimize SVG parameters based on text-to-image diffusion models.
+This is a simplified implementation of Diffsketcher for the Hugging Face Inference API.
 
 ## Usage
 
-You can use this model directly with the Hugging Face Diffusers library:
-
-```python
-from diffusers import DiffusionPipeline
-
-pipeline = DiffusionPipeline.from_pretrained("jree423/diffsketcher")
-output = pipeline(
-    prompt="A beautiful sunset over the mountains",
-    negative_prompt="ugly, blurry",
-    num_paths=96,
-    token_ind=4,
-    num_iter=800,
-    guidance_scale=7.5,
-    width=1.5,
-    seed=42
-)
-
-# Access the generated SVG
-svg = output.svg
-
-# Access the rendered image
-image = output.images[0]
-
-# Save the SVG
-with open("output.svg", "w") as f:
-    f.write(svg)
-```
-
-## Inference API Usage
-
-You can use this model directly with the Hugging Face Inference API:
-
 ```python
 import requests
 
@@ -64,40 +15,5 @@ def query(payload):
     response = requests.post(API_URL, headers=headers, json=payload)
     return response.json()
 
-output = query({
-    "prompt": "A beautiful sunset over the mountains",
-    "negative_prompt": "ugly, blurry",
-    "num_paths": 96,
-    "token_ind": 4,
-    "num_iter": 800,
-    "guidance_scale": 7.5,
-    "width": 1.5,
-    "seed": 42
-})
+output = query({"prompt": "a cat"})
 ```
-
-## Parameters
-
-- `prompt` (str): The text prompt to guide the sketch generation
-- `negative_prompt` (str, optional): The prompt not to guide the sketch generation
-- `num_paths` (int, default=96): Number of SVG paths to generate
-- `token_ind` (int, default=4): Token index for attention control
-- `num_iter` (int, default=800): Number of optimization iterations
-- `guidance_scale` (float, default=7.5): Scale for classifier-free guidance
-- `width` (float, default=1.5): Width of the SVG paths
-- `seed` (int, optional): Random seed for reproducibility
-
-## Limitations
-
-This is a simplified implementation of DiffSketcher for demonstration purposes. For the full implementation, please refer to the [original repository](https://github.com/ximinng/DiffSketcher).
-
-## Citation
-
-```bibtex
-@article{xing2023diffsketcher,
-  title={DiffSketcher: Text Guided Vector Sketch Synthesis through Latent Diffusion Models},
-  author={Xing, Ximing and Xie, Chuang and Yang, Yinghao and Li, Shiyin and Jia, Xu and Qiao, Yu},
-  journal={arXiv preprint arXiv:2306.14685},
-  year={2023}
-}
-```