feat: add PiD 1.5 support

docs/pid.md

@@ -1,7 +1,7 @@
 # How to Use
 
 PiD is NVIDIA's Pixel Diffusion Decoder. It replaces the usual VAE decode or decode-then-upscale path with a pixel-space diffusion decoder conditioned on a
-source latent and text prompt.
+source latent and text prompt. Both the original PiD checkpoints and PiD 1.5 are supported.
 
 In stable-diffusion.cpp, PiD currently runs as an image edit pipeline: provide a reference image with `-r`/`--ref-image`, encode that image with a matching VAE, then let the PiD diffusion model decode/upscale directly to RGB.
 
@@ -16,6 +16,7 @@ In stable-diffusion.cpp, PiD currently runs as an image edit pipeline: provide a
     - Flux / Z-Image PiD: use the Flux VAE and pass `--vae-format flux`
     - SD3 PiD: use the SD3 VAE and pass `--vae-format sd3`
     - Flux.2 PiD: use the Flux.2 VAE and pass `--vae-format flux2`
+    - Qwen-Image PiD: use the Qwen-Image 2D VAE and pass `--vae-format wan`
 
 The official PiD model card should be checked before use. At the time of the initial PiD release, the official weights are under the NSCLv1 non-commercial license.
 

examples/common/common.cpp

@@ -50,6 +50,9 @@ static sd_vae_format_t str_to_vae_format(const std::string& value) {
     if (value == "flux2") {
         return SD_VAE_FORMAT_FLUX2;
     }
+    if (value == "wan") {
+        return SD_VAE_FORMAT_WAN;
+    }
     return SD_VAE_FORMAT_COUNT;
 }
 
@@ -401,7 +404,7 @@ ArgOptions SDContextParams::get_options() {
          &vae_path},
         {"",
          "--vae-format",
-         "VAE latent format override: auto, flux, sd3, or flux2 (default: auto)",
+         "VAE latent format override: auto, flux, sd3, flux2, or wan (default: auto)",
          0,
          &vae_format},
         {"",
@@ -743,7 +746,7 @@ bool SDContextParams::validate(SDMode mode) {
     }
 
     if (str_to_vae_format(vae_format) == SD_VAE_FORMAT_COUNT) {
-        LOG_ERROR("error: vae_format must be 'auto', 'flux', 'sd3', or 'flux2'");
+        LOG_ERROR("error: vae_format must be 'auto', 'flux', 'sd3', 'flux2', or 'wan'");
         return false;
     }
 

include/stable-diffusion.h

@@ -180,6 +180,7 @@ enum sd_vae_format_t {
     SD_VAE_FORMAT_FLUX,
     SD_VAE_FORMAT_SD3,
     SD_VAE_FORMAT_FLUX2,
+    SD_VAE_FORMAT_WAN,
     SD_VAE_FORMAT_COUNT,
 };