SD1.5 NPU High Resolution

WARNING

Quantized high-resolution (>768×768) SD1.5 models often produce images with poor overall layout — extra limbs, distorted proportions, repeated subjects. This is a known limitation of W8A16 static quantization at large resolutions, not a bug in your setup.

Recommended Workflow (Highres.fix)

The reliable way to get high-resolution images on the NPU is a two-stage process, equivalent to AUTOMATIC1111's Highres.fix:

1. Generate at 512×512 with the base SD1.5 NPU model. The composition will be coherent.
2. (Optional) Upscale the result with one of the built-in upscalers if you need a sharper input.
3. Run img2img at the target resolution using the high-resolution patched model. Use a denoise strength around 0.8 so the output keeps the original layout but adds high-resolution detail.

Step 1: txt2img @ 512×512   →  good layout, low detail
Step 2: img2img @ 1024×1024+  →  good layout + high detail
        denoise_strength ≈ 0.8

Why Not Just Generate at 1024x1024 Directly?

Direct high-resolution generation goes through the same quantized weights but without the structural prior of a small initial latent. The model has to infer the entire composition at high resolution, which is exactly the case where quantization noise hurts the most.

The two-stage workflow lets the low-resolution pass do the structural work and uses the high-resolution pass only for refinement, where quantization is much more forgiving.

Tips

• A denoise strength below 0.7 often loses high-frequency detail; above 0.85 can shift the composition.
• For SDXL NPU models, this workflow is unnecessary — SDXL is fixed at 1024×1024 and generates well directly.
• The upscaler step before img2img is optional but helps when going from 512 to 1024+.