refactor: centralize model factories and defaults (#2198)

examples/server/api.md

@@ -447,10 +447,6 @@ image establishes the generation dimensions if `size` is omitted. Input
 geometry follows `image_preprocess`: references preserve their dimensions by
 default, while init and mask use the generation canvas preset.
 
-When the request starts without preconfigured reference images, the first uploaded image becomes the img2img init image if the loaded model does not support reference-image conditioning, the final reference list is empty, a mask is present, or an explicit numeric `strength` override is provided. Otherwise, only the final reference list is used for image conditioning, without initializing the img2img latent. Requests with preconfigured references retain their existing init-image selection.
-
-Routing uses the reference list and mask after applying `sd_cpp_extra_args`. Both `ref_images: []` and `ref_images: null` clear the reference list; `mask_image: null` clears an uploaded mask. An explicit `init_image` in `sd_cpp_extra_args`, including `null`, takes precedence over the implicit init-image selection.
-
 Reference encoding then follows model presets and `ref_image_args`. To skip
 input geometry for references and disable resizing before VAE encoding, include
 this in `prompt`:

examples/server/openai_edit_policy.h

@@ -1,44 +0,0 @@
-#ifndef __SD_EXAMPLES_SERVER_OPENAI_EDIT_POLICY_H__
-#define __SD_EXAMPLES_SERVER_OPENAI_EDIT_POLICY_H__
-
-#include "common/resource_owners.hpp"
-
-enum class OpenAIEditInitImageAction {
-    KeepExisting,
-    UseUploaded,
-    Clear,
-};
-
-inline bool openai_edit_uses_uploaded_image_as_init(bool supports_ref_image_conditioning,
-                                                    bool has_ref_images,
-                                                    bool has_mask,
-                                                    bool has_explicit_strength_override) {
-    return !supports_ref_image_conditioning || !has_ref_images || has_mask || has_explicit_strength_override;
-}
-
-inline OpenAIEditInitImageAction apply_openai_edit_init_image_policy(
-    SDImageOwner& init_image,
-    SDImageOwner& uploaded_image,
-    bool uploaded_image_was_first_reference,
-    bool supports_ref_image_conditioning,
-    bool has_ref_images,
-    bool has_mask,
-    bool has_extra_init_image_override,
-    bool has_explicit_strength_override) {
-    if (!uploaded_image_was_first_reference || has_extra_init_image_override) {
-        return OpenAIEditInitImageAction::KeepExisting;
-    }
-
-    if (openai_edit_uses_uploaded_image_as_init(supports_ref_image_conditioning,
-                                                has_ref_images,
-                                                has_mask,
-                                                has_explicit_strength_override)) {
-        init_image = std::move(uploaded_image);
-        return OpenAIEditInitImageAction::UseUploaded;
-    }
-
-    init_image.reset();
-    return OpenAIEditInitImageAction::Clear;
-}
-
-#endif  // __SD_EXAMPLES_SERVER_OPENAI_EDIT_POLICY_H__

examples/server/routes_openai.cpp

@@ -7,7 +7,6 @@
 #include "common/common.h"
 #include "common/media_io.h"
 #include "common/resource_owners.hpp"
-#include "openai_edit_policy.h"
 
 static std::string extract_and_remove_sd_cpp_extra_args(std::string& text) {
     std::regex re("<sd_cpp_extra_args>(.*?)</sd_cpp_extra_args>");
@@ -158,24 +157,7 @@ static bool build_openai_edit_request(const httplib::Request& req,
     request.gen_params.height      = height;
     request.gen_params.batch_count = n;
 
-    std::string sd_cpp_extra_args_str        = extract_and_remove_sd_cpp_extra_args(request.gen_params.prompt);
-    const json extra_args                    = sd_cpp_extra_args_str.empty()
-                                                   ? json::object()
-                                                   : json::parse(sd_cpp_extra_args_str, nullptr, false);
-    const bool has_extra_init_image_override = extra_args.is_object() && extra_args.contains("init_image");
-    const bool has_extra_ref_images_override = extra_args.is_object() && extra_args.contains("ref_images");
-    const bool has_extra_strength_override   = extra_args.is_object() &&
-                                             extra_args.contains("strength") &&
-                                             extra_args["strength"].is_number();
-    const bool has_extra_mask_image = extra_args.is_object() &&
-                                      extra_args.contains("mask_image") &&
-                                      !extra_args["mask_image"].is_null();
-    const bool supports_ref_image_conditioning = sd_ctx_supports_ref_image_conditioning(runtime.sd_ctx);
-    const bool may_need_uploaded_init_image    = !has_extra_init_image_override &&
-                                              (!supports_ref_image_conditioning || !mask_bytes.empty() ||
-                                               has_extra_mask_image || has_extra_strength_override || has_extra_ref_images_override);
-    SDImageOwner uploaded_image_for_init;
-    bool uploaded_image_was_first_reference = false;
+    std::string sd_cpp_extra_args_str = extract_and_remove_sd_cpp_extra_args(request.gen_params.prompt);
     for (auto& bytes : images_bytes) {
         int img_w            = 0;
         int img_h            = 0;
@@ -190,17 +172,9 @@ static bool build_openai_edit_request(const httplib::Request& req,
             continue;
         }
 
-        const bool is_first_ref_image = request.gen_params.ref_images.empty();
         SDImageOwner image_owner({(uint32_t)img_w, (uint32_t)img_h, (uint32_t)resolved_channel, raw_pixels});
         request.gen_params.set_width_and_height_if_unset(image_owner.get().width, image_owner.get().height);
 
-        if (is_first_ref_image) {
-            uploaded_image_was_first_reference = true;
-            if (may_need_uploaded_init_image) {
-                uploaded_image_for_init = image_owner;
-            }
-        }
-
         request.gen_params.ref_images.push_back(std::move(image_owner));
     }
 
@@ -231,21 +205,6 @@ static bool build_openai_edit_request(const httplib::Request& req,
         return false;
     }
 
-    const auto init_image_action = apply_openai_edit_init_image_policy(
-        request.gen_params.init_image,
-        uploaded_image_for_init,
-        uploaded_image_was_first_reference,
-        supports_ref_image_conditioning,
-        !request.gen_params.ref_images.empty(),
-        request.gen_params.mask_image.get().data != nullptr,
-        has_extra_init_image_override,
-        has_extra_strength_override);
-    if (init_image_action == OpenAIEditInitImageAction::UseUploaded &&
-        request.gen_params.init_image.get().data == nullptr) {
-        error_message = "could not allocate init image";
-        return false;
-    }
-
     // Intentionally disable prompt-embedded LoRA tag parsing for server APIs.
     if (!request.gen_params.resolve_and_validate(IMG_GEN, "", runtime.ctx_params->hires_upscalers_dir, true)) {
         error_message = "invalid params";