<h1 id="zit-fp8-aio-and-gguf-one-click-+-upscaler">ZIT - FP8 AIO &amp; GGUF One-Click + Upscaler</h1><p>Fast image generation using the Z-Image-Turbo model in FP8 quantized or GGUF formats. Includes integrated LoRA loading and high-quality upscaling.</p><h2 id="how-does-it-work">How does it work?</h2><p>This workflow is designed for high performance on limited VRAM. It allows you to load models directly and generate images adding LoRAs on the fly.</p><p>If any nodes appear in red, use the ComfyUI Manager to install missing dependencies automatically.</p><h2 id="required-models">Required Models</h2><p>Depending on your hardware, download the version that best fits your VRAM and place it in the corresponding folder:</p><ul><li><p>FP8 Version: Place in \ComfyUI\models\checkpoints Download: <a target="_blank" rel="ugc" href="https://huggingface.co/SeeSee21/Z-Image-Turbo-AIO/resolve/main/z-image-turbo-fp8-aio.safetensors?download=true">https://huggingface.co/SeeSee21/Z-Image-Turbo-AIO/resolve/main/z-image-turbo-fp8-aio.safetensors?download=true</a></p></li><li><p>GGUF Version: Place in \ComfyUI\models\unet Download: <a target="_blank" rel="ugc" href="https://huggingface.co/vantagewithai/Z-Image-Turbo-GGUF/tree/main">https://huggingface.co/vantagewithai/Z-Image-Turbo-GGUF/tree/main</a></p></li></ul><p>Note on Upscaling: If you don't want to upscale your image, simply bypass the <em>ImageScaleToTotalPixels </em>node before running the workflow.</p><h2 id="credits">Credits</h2><p>Original workflow made by <a rel="ugc" href="https://www.youtube.com/@vantagewithai">VantageWithAI</a> and modified by <a rel="ugc" href="https://civarchive.com/user/Rio__">RIO</a> </p>

Z-Image Turbo GGUF: LoRA One-Click + Upscaler

<p>This is an edit of the original workflow, adapted to FP8</p>

Files with SHA256: 38e29a0b62593c25ace07fc7007468f28e7a19977e568320f63adb2fde2cf2be