feat(server): add recipe constraints and update generation workspace (#2217)

src/model/diffusion/moss_image.hpp

@@ -185,7 +185,7 @@ namespace MOSSImage {
                     ggml_build_forward_expand(ctx->graph, parts[i]);
                 }
             }
-            x         = ggml_concat(c, x, text, 1);
+            x = ggml_concat(c, x, text, 1);
             for (int64_t i = 0; i < config.depth; ++i) {
                 if (std::find(skip.begin(), skip.end(), i) == skip.end()) {
                     x = std::dynamic_pointer_cast<Block>(blocks["layers." + std::to_string(i)])->forward(ctx, x, pe, parts);

src/pipeline/image.cpp

@@ -314,8 +314,8 @@ namespace sd::pipeline {
         }
 
         bool skip_vae_encoding = (sd->version == VERSION_HIDREAM_O1) || !(
-            ref_image_params.pass_to_dit || ref_image_params.vlm_use_vae_input ||
-            sd_version_is_unet_edit(sd->version) || sd_version_is_pid(sd->version));
+                                                                            ref_image_params.pass_to_dit || ref_image_params.vlm_use_vae_input ||
+                                                                            sd_version_is_unet_edit(sd->version) || sd_version_is_pid(sd->version));
 
         std::vector<sd::Tensor<float>> ref_latents;
         for (size_t i = 0; i < ref_images.size(); i++) {

src/runtime/image_preprocess.cpp

@@ -379,8 +379,13 @@ namespace sd {
         if (target == ImageTarget::Mask && has_init_transform_) {
             auto options = resolve_options(target, index);
             if (image.width != init_transform_.source_width || image.height != init_transform_.source_height) {
-                fail("mask and init source dimensions must match");
-                return {};
+                ImagePreprocessor alignment;
+                tensor = alignment.apply_geometry(tensor, target, index, init_transform_.source_width, init_transform_.source_height,
+                                                  ImageResizeMode::CropResize, ops::InterpolateMode::NearestExact);
+                if (tensor.empty()) {
+                    fail("could not align mask to init source dimensions");
+                    return {};
+                }
             }
             bool geometry_override = options.count("width") || options.count("anchor") ||
                                      (options.count("mode") && options.at("mode") != "auto");