| --- |
| license: apache-2.0 |
| base_model: unsloth/Qwen3.5-2B |
| tags: |
| - ascii |
| - vision |
| - art |
| - unsloth |
| - image-to-text |
| datasets: |
| - PinkPixel/ASCII-Art |
| pipeline_tag: image-to-text |
| library_name: transformers |
| --- |
| |
| <div align="center"> |
| <img src="logo.png" alt="ASCII Machine Logo" width="300" height="300"> |
| <h1>✨ ASCII Machine ✨</h1> |
| <p><i>ASCII Art Generation Model</i></p> |
| </div> |
|
|
| --- |
|
|
| **NOTE:** This is the first version of this model and it may not always generate perfect ASCII art. Fine tuning is still in progress and there will be updated versions coming soon. |
|
|
| ## 🚀 Model Overview |
|
|
| **ASCII Machine** is a specialized vision-language model designed for high-quality ASCII art generation and interpretation. Based on the **Qwen3.5-2B** architecture, it has been fine-tuned to excel at transforming visual concepts into intricate text-based masterpieces. |
|
|
| - **Model Name:** PinkPixel/ASCII-Machine |
| - **Base Model:** Qwen3.5-2B |
| - **Training Platform:** [Unsloth Studio](https://unsloth.ai/) |
| - **Specialization:** ASCII Art Generation & Vision-to-ASCII tasks |
|
|
| ## 🎨 Dataset |
|
|
| This model was trained on the [PinkPixel/ASCII-Art](https://huggingface.co/datasets/PinkPixel/ASCII-Art) dataset, a curated collection of thousands of diverse ASCII artworks across various styles and subjects. |
|
|
| ## 💬 Example Usage |
|
|
| ### User: |
| > Can you create a small ASCII art of a cat? |
|
|
| ### ASCII Machine: |
| ```text |
| ^__^ |
| (oo)\_______ |
| (__)\ )\/\ |
| ||----w | |
| || || |
| ``` |
| *(Note: Actual output quality may vary based on prompt complexity and artistic style requested)* |
|
|
| ## 👁️ Vision Capabilities |
|
|
| As a vision-enabled model, **ASCII Machine** can "see" images and describe them or convert them directly into ASCII representations. Please note that this uses a cutting-edge architecture; while the full safetensors version supports vision natively in compatible environments, third-party support in tools like `llama.cpp` or `LM Studio` may still be in development. |
|
|
| ## 🛠️ Installation & Usage |
|
|
| You can use this model directly with the Hugging Face `transformers` library: |
|
|
| ```python |
| from transformers import AutoProcessor, AutoModelForVision2Seq |
| |
| model_id = "PinkPixel/ASCII-Machine" |
| processor = AutoProcessor.from_pretrained(model_id) |
| model = AutoModelForVision2Seq.from_pretrained(model_id) |
| ``` |
|
|
| --- |
| <div align="center"> |
| Made with ❤️ by <a href="https://pinkpixel.dev">Pink Pixel</a> |
| <br> |
| <i>"Dream it, Pixel it"</i> |
| </div> |
|
|
