<h2 id="smittie's-pid-upscaler-workflow">Smittie's PiD Upscaler Workflow</h2><p></p><h3 id="description">Description</h3><p>With this workflow you can upscale low-resolution images (512, 1K) to much higher resolutions (2K, 4K) using <a rel="ugc" href="https://research.nvidia.com/labs/sil/projects/pid/">Nvidia's PiD (Pixel Diffusion)</a>. It is a simple image to image (I2I) workflow.</p><p></p><h3 id="install-instructions">Install Instructions</h3><p>1. Update ComfyUI to latest build with PiD support</p><p>2. Install all missing custom nodes via the ComfyUI Manager</p><p>3. Download all needed models</p><p></p><p><strong>Diffusion model</strong></p><ul><li><p><a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/PixelDiT/tree/main/diffusion_models">All available</a></p></li><li><p>For Z-Image or Flux.1 like images in 1K resolution use <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/PixelDiT/blob/main/diffusion_models/pid_flux1_1024_to_4096_4step_bf16.safetensors">pid_flux1_1024_to_4096_4step_bf16.safetensors</a></p></li></ul><p><strong>Text encoder</strong></p><ul><li><p><a rel="ugc" href="https://huggingface.co/Comfy-Org/PixelDiT/tree/main/text_encoders">gemma_2_2b_it_elm_bf16.safetensors</a></p></li></ul><p><strong>VAE</strong></p><ul><li><p><a rel="ugc" href="https://huggingface.co/Comfy-Org/z_image_turbo/tree/main/split_files/vae">ae.safetensors</a></p></li></ul><p></p><h3 id="video-instructions">Video Instructions</h3><p>If you don't know what to do, you can watch the <a rel="ugc" href="https://www.youtube.com/watch?v=DlvhlQOBHBw">Nvidia PiD Tutorial by AI Search</a>. He works with a different workflow, which I have built upon.</p><p></p><h3 id="acknowledgement">Acknowledgement</h3><p>Most credits goes to the Nvidia, ComfyUI and CivitAI team, as well as kijai and AI Search. Thank you guys!</p>

Files with SHA256: 60500fc3ca5c596d8d7e735eec0216fcfd5532c76376fd91b7978ed1e0e0302e