Z-Anime / README.md
Nekochu's picture
fix Examples (needs fn+outputs), full README with API/CLI/MCP docs
eaaf713
---
title: Z-Anime Image Generation (CPU)
emoji: 🎨
colorFrom: blue
colorTo: pink
sdk: docker
pinned: false
license: apache-2.0
tags:
- image-generation
- z-anime
- gguf
- cpu
- anime
- mcp-server
short_description: Z-Anime 6B - CPU anime image generation via sd.cpp
models:
- SeeSee21/Z-Anime
startup_duration_timeout: 1h
---
# Z-Anime Image Generation (CPU)
**CPU Inference** - Generate anime images with Z-Anime 6B via stable-diffusion.cpp GGUF. ~30 min at 512x512 on free CPU.
## Features
- **Image Generation** - text to image via GGUF quantized Z-Anime 6B (S3-DiT)
- **Distill 4-Step** - fast inference with distilled model (4 steps, CFG 1.0)
- **CLI Support** - command-line interface for local generation
- **MCP Server** - AI assistant integration (Claude, Cursor, VS Code)
## Image Generation
1. Enter a prompt describing the anime image
2. Adjust resolution (512x512 recommended on CPU)
3. Adjust CFG (1.0 best, max 1.5)
4. Click **Generate**
**Timing:** ~30 min at 512x512 on free CPU. GPU is much faster (~2 min).
## Models
| Component | File | Size |
|-----------|------|------|
| Diffusion (DiT) | [Z-Anime distill-4step Q5_0 GGUF](https://huggingface.co/WeReCooking/Z-Anime-4step-GGUF) | 4.23 GB |
| Text Encoder | [Qwen3-4B IQ4_XS GGUF](https://huggingface.co/worstplayer/Z-Image_Qwen_3_4b_text_encoder_GGUF) | 2.29 GB |
| VAE | [ae.safetensors](https://huggingface.co/SeeSee21/Z-Anime/blob/main/vae/ae.safetensors) | 168 MB |
## Settings
- **Steps:** 4 (distilled)
- **CFG:** 1.0 (max 1.5, do not exceed)
- **Sampler:** euler_ancestral
- **Resolution:** 512x512 (recommended on CPU)
---
## API
### Python Client
```python
from gradio_client import Client
client = Client("WeReCooking/Z-Anime-CPU")
result = client.predict(
prompt="anime girl with silver hair, fantasy armor, dramatic lighting",
negative_prompt="worst quality, low quality, blurry, bad anatomy",
resolution="512x512",
cfg=1.0,
seed=-1,
api_name="/generate"
)
print(result) # (image, status_message)
```
### MCP (Model Context Protocol)
This Space supports MCP for AI assistants (Claude Desktop, Cursor, VS Code).
**MCP Config:**
```json
{
"mcpServers": {
"z-anime": {"url": "https://werecooking-z-anime-cpu.hf.space/gradio_api/mcp/"}
}
}
```
---
## CLI Usage
```bash
# Basic generation
python app.py "anime girl with silver hair, fantasy armor" -o output.png
# With seed and CFG
python app.py "1girl, maid outfit, cafe background" --seed 42 --cfg 1.0 -o maid.png
# Custom resolution and negative prompt
python app.py "landscape, cherry blossoms, shrine" -r 768x512 -n "blurry, low quality" -o landscape.png
# Start Gradio UI instead
python app.py --gradio
```
---
## Credits
- [Z-Anime](https://huggingface.co/SeeSee21/Z-Anime) by SeeSee21
- [Z-Image](https://github.com/Tongyi-MAI/Z-Image) by Alibaba Tongyi Lab
- [stable-diffusion.cpp](https://github.com/leejet/stable-diffusion.cpp) by leejet
- [Qwen3-4B Text Encoder GGUF](https://huggingface.co/worstplayer/Z-Image_Qwen_3_4b_text_encoder_GGUF) by worstplayer