ComfyUI Node
⭐ Star Tiled PiD Upscaler
Upscales an image with a PiD / PixelDiT model by processing it in overlapping tiles to keep VRAM usage low. Each tile is re-rendered in pixel space (4 LCM steps) and blended back seamlessly, with per-tile color matching.
⭐ Star Tiled PiD Upscaler
- image
- IMAGE
◄model_name▾►
◄clip_name▾►
◄vae_name▾►
◄latent_formatqwenimage►
◄scale4.00►
◄rows2►
◄cols2►
◄tile_overlap0.25►
Category⭐StarNodes/Image And Latent
Inputs (9)
| Name | Type | Default | Description |
|---|---|---|---|
| image | IMAGE | The image to upscale. | |
| model_name | COMBO | The PiD / PixelDiT diffusion model, e.g. pid_qwenimage_1024_to_4096_4step_bf16.safetensors. | |
| clip_name | COMBO | Gemma 2 2B text encoder for PixelDiT (gemma_2_2b_it_elm). PiD uses an empty prompt, but the model still needs the text encoder loaded. | |
| vae_name | COMBO | VAE matching the PiD backbone, used to encode the input image (e.g. qwen_image_vae for qwenimage, ae.safetensors for flux). | |
| latent_format | COMBO | qwenimage | Latent format of the PiD backbone. Flux1 (16-ch) and Flux2 (128-ch) are auto-detected under 'flux'. |
| scale | FLOAT | 4.001–8 | Upscale factor for the output image. PiD models are trained for 4x. |
| rows | INT | 21–16 | Number of tile rows. More rows = smaller tiles = less VRAM. |
| cols | INT | 21–16 | Number of tile columns. More columns = smaller tiles = less VRAM. |
| tile_overlap | FLOAT | 0.250.05–0.5 | Overlap ratio between tiles. Higher values reduce seam artifacts but increase VRAM/time. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| IMAGE | IMAGE | — |