DarthAffe/stable-diffusion.cpp
1
0 Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-11-11 03:24:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: return generation metadata with core results (#2206)

Browse Source
This commit is contained in:
leejet authored and GitHub committed 2026-10-25 03:18:03 +08:00
1 parent b29cad540a
commit a85db96aa5
37 files changed
+1528 -758
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

src/pipeline/diffusion_engine.cpp
+31 -20
View File
@@ -675,87 +675,93 @@ bool StableDiffusionGGML::init_model_loader(ModelLoader& model_loader, ModelConf
const auto* sd_ctx_params = &configuration.params;
auto& use_tae = configuration.use_tae;
auto& use_audio_vae = configuration.use_audio_vae;
const auto load_model = [&](const char* name, const char* path, const std::string& prefix = "") {
if (!model_loader.init_from_file(path, prefix))
return false;
configuration.record_model(name, path);
return true;
};
if (strlen(SAFE_STR(sd_ctx_params->model_path)) > 0) {
LOG_INFO("loading model from '%s'", sd_ctx_params->model_path);
if (!model_loader.init_from_file(sd_ctx_params->model_path)) {
if (!load_model("model", sd_ctx_params->model_path)) {
LOG_ERROR("init model loader from file failed: '%s'", sd_ctx_params->model_path);
}
}
if (strlen(SAFE_STR(sd_ctx_params->diffusion_model_path)) > 0) {
LOG_INFO("loading diffusion model from '%s'", sd_ctx_params->diffusion_model_path);
if (!model_loader.init_from_file(sd_ctx_params->diffusion_model_path, "model.diffusion_model.")) {
if (!load_model("diffusion_model", sd_ctx_params->diffusion_model_path, "model.diffusion_model.")) {
LOG_WARN("loading diffusion model from '%s' failed", sd_ctx_params->diffusion_model_path);
}
}
if (strlen(SAFE_STR(sd_ctx_params->high_noise_diffusion_model_path)) > 0) {
LOG_INFO("loading high noise diffusion model from '%s'", sd_ctx_params->high_noise_diffusion_model_path);
if (!model_loader.init_from_file(sd_ctx_params->high_noise_diffusion_model_path, "model.high_noise_diffusion_model.")) {
if (!load_model("high_noise_diffusion_model", sd_ctx_params->high_noise_diffusion_model_path, "model.high_noise_diffusion_model.")) {
LOG_WARN("loading diffusion model from '%s' failed", sd_ctx_params->high_noise_diffusion_model_path);
}
}
if (strlen(SAFE_STR(sd_ctx_params->uncond_diffusion_model_path)) > 0) {
LOG_INFO("loading unconditional diffusion model from '%s'", sd_ctx_params->uncond_diffusion_model_path);
if (!model_loader.init_from_file(sd_ctx_params->uncond_diffusion_model_path, "model.diffusion_model.uncond.")) {
if (!load_model("uncond_diffusion_model", sd_ctx_params->uncond_diffusion_model_path, "model.diffusion_model.uncond.")) {
LOG_WARN("loading unconditional diffusion model from '%s' failed", sd_ctx_params->uncond_diffusion_model_path);
}
}
if (strlen(SAFE_STR(sd_ctx_params->clip_l_path)) > 0) {
LOG_INFO("loading clip_l from '%s'", sd_ctx_params->clip_l_path);
if (!model_loader.init_from_file(sd_ctx_params->clip_l_path, "clip_l.")) {
if (!load_model("clip_l", sd_ctx_params->clip_l_path, "clip_l.")) {
LOG_WARN("loading clip_l from '%s' failed", sd_ctx_params->clip_l_path);
}
}
if (strlen(SAFE_STR(sd_ctx_params->clip_g_path)) > 0) {
LOG_INFO("loading clip_g from '%s'", sd_ctx_params->clip_g_path);
if (!model_loader.init_from_file(sd_ctx_params->clip_g_path, "clip_g.")) {
if (!load_model("clip_g", sd_ctx_params->clip_g_path, "clip_g.")) {
LOG_WARN("loading clip_g from '%s' failed", sd_ctx_params->clip_g_path);
}
}
if (strlen(SAFE_STR(sd_ctx_params->clip_vision_path)) > 0) {
LOG_INFO("loading clip_vision from '%s'", sd_ctx_params->clip_vision_path);
if (!model_loader.init_from_file(sd_ctx_params->clip_vision_path, "clip_vision.")) {
if (!load_model("clip_vision", sd_ctx_params->clip_vision_path, "clip_vision.")) {
LOG_WARN("loading clip_vision from '%s' failed", sd_ctx_params->clip_vision_path);
}
}
if (strlen(SAFE_STR(sd_ctx_params->t5xxl_path)) > 0) {
LOG_INFO("loading t5xxl from '%s'", sd_ctx_params->t5xxl_path);
if (!model_loader.init_from_file(sd_ctx_params->t5xxl_path, "text_encoders.t5xxl.transformer.")) {
if (!load_model("t5xxl", sd_ctx_params->t5xxl_path, "text_encoders.t5xxl.transformer.")) {
LOG_WARN("loading t5xxl from '%s' failed", sd_ctx_params->t5xxl_path);
}
}
if (strlen(SAFE_STR(sd_ctx_params->pulid_weights_path)) > 0) {
LOG_INFO("loading PuLID weights from '%s'", sd_ctx_params->pulid_weights_path);
if (!model_loader.init_from_file(sd_ctx_params->pulid_weights_path,
"model.diffusion_model.")) {
if (!load_model("pulid_weights", sd_ctx_params->pulid_weights_path,
"model.diffusion_model.")) {
LOG_WARN("loading PuLID weights from '%s' failed", sd_ctx_params->pulid_weights_path);
}
}
if (strlen(SAFE_STR(sd_ctx_params->llm_path)) > 0) {
LOG_INFO("loading llm from '%s'", sd_ctx_params->llm_path);
if (!model_loader.init_from_file(sd_ctx_params->llm_path, "text_encoders.llm.")) {
if (!load_model("llm", sd_ctx_params->llm_path, "text_encoders.llm.")) {
LOG_WARN("loading llm from '%s' failed", sd_ctx_params->llm_path);
}
}
if (strlen(SAFE_STR(sd_ctx_params->llm_vision_path)) > 0) {
LOG_INFO("loading llm vision from '%s'", sd_ctx_params->llm_vision_path);
if (!model_loader.init_from_file(sd_ctx_params->llm_vision_path, "text_encoders.llm.visual.")) {
if (!load_model("llm_vision", sd_ctx_params->llm_vision_path, "text_encoders.llm.visual.")) {
LOG_WARN("loading llm vision from '%s' failed", sd_ctx_params->llm_vision_path);
}
}
if (strlen(SAFE_STR(sd_ctx_params->vae_path)) > 0) {
LOG_INFO("loading vae from '%s'", sd_ctx_params->vae_path);
if (!model_loader.init_from_file(sd_ctx_params->vae_path, "vae.")) {
if (!load_model("vae", sd_ctx_params->vae_path, "vae.")) {
LOG_WARN("loading vae from '%s' failed", sd_ctx_params->vae_path);
external_vae_is_invalid = true;
}
@@ -763,7 +769,7 @@ bool StableDiffusionGGML::init_model_loader(ModelLoader& model_loader, ModelConf
if (strlen(SAFE_STR(sd_ctx_params->taesd_path)) > 0) {
LOG_INFO("loading tae from '%s'", sd_ctx_params->taesd_path);
if (!model_loader.init_from_file(sd_ctx_params->taesd_path, "tae.")) {
if (!load_model("taesd", sd_ctx_params->taesd_path, "tae.")) {
LOG_WARN("loading tae from '%s' failed", sd_ctx_params->taesd_path);
} else {
use_tae = true;
@@ -772,14 +778,14 @@ bool StableDiffusionGGML::init_model_loader(ModelLoader& model_loader, ModelConf
if (strlen(SAFE_STR(sd_ctx_params->embeddings_connectors_path)) > 0) {
LOG_INFO("loading embeddings connectors from '%s'", sd_ctx_params->embeddings_connectors_path);
if (!model_loader.init_from_file(sd_ctx_params->embeddings_connectors_path)) {
if (!load_model("embeddings_connectors", sd_ctx_params->embeddings_connectors_path)) {
LOG_WARN("loading embeddings connectors from '%s' failed", sd_ctx_params->embeddings_connectors_path);
}
}
if (strlen(SAFE_STR(sd_ctx_params->audio_vae_path)) > 0) {
LOG_INFO("loading audio VAE from '%s'", sd_ctx_params->audio_vae_path);
if (!model_loader.init_from_file(sd_ctx_params->audio_vae_path)) {
if (!load_model("audio_vae", sd_ctx_params->audio_vae_path)) {
LOG_WARN("loading audio VAE weights from '%s' failed", sd_ctx_params->audio_vae_path);
} else {
use_audio_vae = true;
@@ -788,15 +794,15 @@ bool StableDiffusionGGML::init_model_loader(ModelLoader& model_loader, ModelConf
if (strlen(SAFE_STR(sd_ctx_params->audio_encoder_path)) > 0) {
LOG_INFO("loading audio encoder (wav2vec2) from '%s'", sd_ctx_params->audio_encoder_path);
if (!model_loader.init_from_file(sd_ctx_params->audio_encoder_path, "wav2vec2.")) {
if (!load_model("audio_encoder", sd_ctx_params->audio_encoder_path, "wav2vec2.")) {
LOG_WARN("loading audio encoder weights from '%s' failed", sd_ctx_params->audio_encoder_path);
}
}
if (strlen(SAFE_STR(sd_ctx_params->motion_module_path)) > 0) {
LOG_INFO("loading motion module (AnimateDiff) from '%s'", sd_ctx_params->motion_module_path);
if (!model_loader.init_from_file(sd_ctx_params->motion_module_path,
"model.diffusion_model.motion_module.")) {
if (!load_model("motion_module", sd_ctx_params->motion_module_path,
"model.diffusion_model.motion_module.")) {
LOG_WARN("loading motion module from '%s' failed", sd_ctx_params->motion_module_path);
} else {
configuration.animatediff_loaded = true;
@@ -810,8 +816,11 @@ bool StableDiffusionGGML::init_model_loader(ModelLoader& model_loader, ModelConf
}
}
if (configuration.control_net_file)
configuration.record_model("control_net", sd_ctx_params->control_net_path);
if (strlen(SAFE_STR(sd_ctx_params->ip_adapter_path)) > 0) {
if (!model_loader.init_from_file(sd_ctx_params->ip_adapter_path)) {
if (!load_model("ip_adapter", sd_ctx_params->ip_adapter_path)) {
LOG_ERROR("init ip-adapter model loader from file failed: '%s'", sd_ctx_params->ip_adapter_path);
return false;
}
@@ -819,6 +828,8 @@ bool StableDiffusionGGML::init_model_loader(ModelLoader& model_loader, ModelConf
if (strlen(SAFE_STR(sd_ctx_params->photo_maker_path)) > 0) {
configuration.photomaker_source_available = model_loader.add_file(sd_ctx_params->photo_maker_path, "pmid.");
if (configuration.photomaker_source_available)
configuration.record_model("photo_maker", sd_ctx_params->photo_maker_path);
if (!configuration.photomaker_source_available) {
LOG_WARN("loading stacked ID embedding from '%s' failed", sd_ctx_params->photo_maker_path);
}