feat: change image dimensions requirement for DiT models (#742)

Dockerfile.musa

@@ -1,6 +1,7 @@
-ARG MUSA_VERSION=rc3.1.1
+ARG MUSA_VERSION=rc4.2.0
+ARG UBUNTU_VERSION=22.04
 
-FROM mthreads/musa:${MUSA_VERSION}-devel-ubuntu22.04 as build
+FROM mthreads/musa:${MUSA_VERSION}-devel-ubuntu${UBUNTU_VERSION}-amd64 as build
 
 RUN apt-get update && apt-get install -y ccache cmake git
 
@@ -15,7 +16,7 @@ RUN mkdir build && cd build && \
         -DSD_MUSA=ON -DCMAKE_BUILD_TYPE=Release && \
     cmake --build . --config Release
 
-FROM mthreads/musa:${MUSA_VERSION}-runtime-ubuntu22.04 as runtime
+FROM mthreads/musa:${MUSA_VERSION}-runtime-ubuntu${UBUNTU_VERSION}-amd64 as runtime
 
 COPY --from=build /sd.cpp/build/bin/sd /sd
 

examples/cli/main.cpp

@@ -596,13 +596,13 @@ void parse_args(int argc, const char** argv, SDParams& params) {
         exit(1);
     }
 
-    if (params.width <= 0 || params.width % 64 != 0) {
-        fprintf(stderr, "error: the width must be a multiple of 64\n");
+    if (params.width <= 0) {
+        fprintf(stderr, "error: the width must be greater than 0\n");
         exit(1);
     }
 
-    if (params.height <= 0 || params.height % 64 != 0) {
-        fprintf(stderr, "error: the height must be a multiple of 64\n");
+    if (params.height <= 0) {
+        fprintf(stderr, "error: the height must be greater than 0\n");
         exit(1);
     }
 

stable-diffusion.cpp

@@ -1875,6 +1875,15 @@ ggml_tensor* generate_init_latent(sd_ctx_t* sd_ctx,
 sd_image_t* generate_image(sd_ctx_t* sd_ctx, const sd_img_gen_params_t* sd_img_gen_params) {
     int width  = sd_img_gen_params->width;
     int height = sd_img_gen_params->height;
+    if (sd_version_is_dit(sd_ctx->sd->version)) {
+        if (width % 16 || height % 16) {
+            LOG_ERROR("Image dimensions must be must be a multiple of 16 on each axis for %s models. (Got %dx%d)", model_version_to_str[sd_ctx->sd->version], width, height);
+            return NULL;
+        }
+    } else if (width % 64 || height % 64) {
+        LOG_ERROR("Image dimensions must be must be a multiple of 64 on each axis for %s models. (Got %dx%d)", model_version_to_str[sd_ctx->sd->version], width, height);
+        return NULL;
+    }
     LOG_DEBUG("generate_image %dx%d", width, height);
     if (sd_ctx == NULL || sd_img_gen_params == NULL) {
         return NULL;