How to use from
Unsloth Studio
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for PinkPixel/ASCII-Machine to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for PinkPixel/ASCII-Machine to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for PinkPixel/ASCII-Machine to start chatting
Load model with FastModel
pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="PinkPixel/ASCII-Machine",
    max_seq_length=2048,
)
Quick Links
ASCII Machine Logo

✨ ASCII Machine ✨

ASCII Art Generation Model


🚀 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
  • Specialization: ASCII Art Generation & Vision-to-ASCII tasks

🎨 Dataset

This model was trained on the 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:

  ^__^
 (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:

from transformers import AutoProcessor, AutoModelForVision2Seq

model_id = "PinkPixel/ASCII-Machine"
processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForVision2Seq.from_pretrained(model_id)

Made with ❤️ by Pink Pixel
"Dream it, Pixel it"
Downloads last month
22
Safetensors
Model size
2B params
Tensor type
F32
·
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for PinkPixel/ASCII-Machine

Finetuned
Qwen/Qwen3.5-2B
Finetuned
(91)
this model
Quantizations
1 model

Dataset used to train PinkPixel/ASCII-Machine