Z-Image Turbo is a fast AI text-to-image model from Alibaba's Tongyi Lab. It has about 6 billion parameters and generates high-quality images quickly (often in 8-12 steps). This workflow by default uses Fp8 version of the Z-Image Turbo ALL-in-One Model which has Clip & VAE backed in, this will work well on base level Apple Silicon Mac M processors (like M3, M4, M5 etc.) with only 16GB unified memory or on a PC with low end Nvidia and AMD GPUs/eGPUs.. even on 8GB VRAM. But if you want to use bigger bf16 version of the Z-Image Turbo ALL-in-One Model on a more powerful system I also provided links in the readme file. Make sure that you have latest enough versions of both ComfyUI and ComfyUI manager to manage and install any missing dependencies (missing nodes, patches etc.) to use this workflow properly. This workflow works great for illustration-style images, like stickers and cartoons. This workflow uses a LORA that I trained extensively on Z-Image Turbo with 240 high resolution, crisp & clear, meticulously selected digital artworks of multiple varieties so that the end results can be as fine as possible (See the Required Models section for the link to get it). Normally Z-Image Turbo has a very strong bias for AI Digital Photgraphy style outputs or near photorealistic outputs, but my LORA takes advantage of Z-Image Turbo's robust output generation speed but guides it forward to focus more on digital arts and simple vector illustrations.

How This Workflow Works -

#1. Type your positive prompt (what you want) and negative prompt (what to avoid).

#2. The model generates a colorful PNG image (raster format).

#3. The PNG is previewed and saved automatically with a timestamp in the filename.

#4. The PNG image then goes through quantization (reduces colors for cleaner results) and then it is converted to SVG using VTracer tools (vector tracing).

#5. After this, the SVG string is saved as an .svg file.

#6. During the entire process the Memory cleanup nodes help keep VRAM and RAM usage low for systems with Low VRAMs (8 GB or lower).

The result: You get both a normal PNG and a clean, scalable SVG file.

## Required Models

===================

### Download Links for Z-Image Turbo All-in-One Checkpoints (with baked in Clip & VAE)

https://huggingface.co/SeeSee21/Z-Image-Turbo-AIO/resolve/main/z-image-turbo-fp8-aio.safetensors

https://huggingface.co/SeeSee21/Z-Image-Turbo-AIO/resolve/main/z-image-turbo-bf16-aio.safetensors

### Link to my ZIT Illustration LORA

https://civarchive.com/models/2270383/zit-illustration-by-sarcastic-tofu

About PNG and SVG Formats

-------------------------

PNG (Portable Network Graphics) - is a raster image made of pixels. It looks great at original size but gets blurry when enlarged. Good for photos and detailed web images.

SVG (Scalable Vector Graphics) is a vector image made of paths and shapes. It stays sharp at any size and is perfect for logos, icons, stickers, and ideal for commercial print on demand or laser cutters. No pixelation when zoomed or resized.

This workflow is perfect for creating scalable digital stickers, illustrations and laser cutouts (many laser cutter devices use .svg file format).

Enjoy generating!