Skip to content

sd: sync with master-782-b290693 #2338

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wbruna wants to merge 2 commits into
base: concedo_experimental
Choose a base branch
from
Open

sd: sync with master-782-b290693 #2338

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
cbfc17b
sd: sync with master-782-b290693
wbruna Jul 17, 2026
68d4cdd
sd: expose ref_image_args
wbruna Jul 18, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions Makefile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -703,7 +703,7 @@ budget.o: common/reasoning-budget.cpp common/reasoning-budget.h
chat.o: common/chat.cpp common/chat.h
$(CXX) $(CXXFLAGS) -c $< -o $@

SDCPP_COMMON_BASENAMES := include/stable-diffusion.h src/conditioning/conditioner.hpp src/core/backend_fit.cpp src/core/backend_fit.h src/core/ggml_extend_backend.cpp src/core/ggml_extend_backend.h src/core/ggml_extend.hpp src/core/ggml_graph_cut.cpp src/core/ggml_graph_cut.h src/core/layer_split_partition.cpp src/core/layer_split_partition.h src/core/ordered_map.hpp src/core/rng.hpp src/core/rng_mt19937.hpp src/core/rng_philox.hpp src/core/tensor_ggml.hpp src/core/tensor.hpp src/core/util.cpp src/core/util.h src/extensions/generation_extension.h src/extensions/photomaker_extension.cpp src/extensions/pulid_extension.cpp src/kcpp_sd_extensions.h src/model/adapter/lora.hpp src/model/adapter/pmid.hpp src/model/adapter/pulid.hpp src/model/common/block.hpp src/model/common/rope.hpp src/model/diffusion/anima.hpp src/model/diffusion/boogu.hpp src/model/diffusion/control.hpp src/model/diffusion/dit.hpp src/model/diffusion/ernie_image.hpp src/model/diffusion/flux.hpp src/model/diffusion/hidream_o1.hpp src/model/diffusion/ideogram4.hpp src/model/diffusion/krea2.hpp src/model/diffusion/lens.hpp src/model/diffusion/lingbot_video.hpp src/model/diffusion/ltxv.hpp src/model/diffusion/minit2i.hpp src/model/diffusion/mmdit.hpp src/model/diffusion/model.hpp src/model/diffusion/pid.hpp src/model/diffusion/qwen_image.hpp src/model/diffusion/sefi_image.hpp src/model/diffusion/unet.hpp src/model/diffusion/wan.hpp src/model/diffusion/z_image.hpp src/model.h src/model_io/binary_io.h src/model_io/gguf_io.cpp src/model_io/gguf_io.h src/model_io/gguf_reader_ext.h src/model_io/pickle_io.cpp src/model_io/pickle_io.h src/model_io/safetensors_io.cpp src/model_io/safetensors_io.h src/model_io/streaming_writer.h src/model_io/tensor_storage.h src/model_io/torch_legacy_io.cpp src/model_io/torch_legacy_io.h src/model_io/torch_zip_io.cpp src/model_io/torch_zip_io.h src/model_loader.cpp src/model_loader.h src/model_manager.cpp src/model_manager.h src/model/te/clip.hpp src/model/te/llm.hpp src/model/te/t5.hpp src/model/upscaler/esrgan.hpp src/model/upscaler/ltx_latent_upscaler.hpp src/model/vae/auto_encoder_kl.hpp src/model/vae/ltx_audio_vae.hpp src/model/vae/ltx_vae.hpp src/model/vae/tae.hpp src/model/vae/vae.hpp src/model/vae/wan_vae.hpp src/name_conversion.cpp src/name_conversion.h src/runtime/cache_dit.hpp src/runtime/condition_cache_utils.hpp src/runtime/denoiser.hpp src/runtime/easycache.hpp src/runtime/gits_noise.h src/runtime/guidance.cpp src/runtime/guidance.h src/runtime/imatrix.cpp src/runtime/imatrix.h src/runtime/latent-preview.h src/runtime/preprocessing.hpp src/runtime/sample-cache.cpp src/runtime/sample-cache.h src/runtime/spectrum.hpp src/runtime/ucache.hpp src/stable-diffusion.cpp src/tokenizers/bpe_tokenizer.cpp src/tokenizers/bpe_tokenizer.h src/tokenizers/clip_tokenizer.cpp src/tokenizers/clip_tokenizer.h src/tokenizers/gemma_tokenizer.cpp src/tokenizers/gemma_tokenizer.h src/tokenizers/gpt_oss_tokenizer.cpp src/tokenizers/gpt_oss_tokenizer.h src/tokenizers/mistral_tokenizer.cpp src/tokenizers/mistral_tokenizer.h src/tokenizers/qwen2_tokenizer.cpp src/tokenizers/qwen2_tokenizer.h src/tokenizers/t5_unigram_tokenizer.cpp src/tokenizers/t5_unigram_tokenizer.h src/tokenizers/tokenizer.cpp src/tokenizers/tokenizer.h src/tokenizers/tokenize_util.cpp src/tokenizers/tokenize_util.h src/tokenizers/vocab/vocab.h src/upscaler.cpp src/upscaler.h src/weight_manager.h
SDCPP_COMMON_BASENAMES := include/stable-diffusion.h src/conditioning/conditioner.hpp src/core/backend_fit.cpp src/core/backend_fit.h src/core/ggml_extend_backend.cpp src/core/ggml_extend_backend.h src/core/ggml_extend.hpp src/core/ggml_graph_cut.cpp src/core/ggml_graph_cut.h src/core/layer_split_partition.cpp src/core/layer_split_partition.h src/core/ordered_map.hpp src/core/rng.hpp src/core/rng_mt19937.hpp src/core/rng_philox.hpp src/core/tensor_ggml.hpp src/core/tensor.hpp src/core/util.cpp src/core/util.h src/detailer.cpp src/detailer.h src/extensions/generation_extension.h src/extensions/photomaker_extension.cpp src/extensions/pulid_extension.cpp src/kcpp_sd_extensions.h src/model/adapter/lora.hpp src/model/adapter/pmid.hpp src/model/adapter/pulid.hpp src/model/common/block.hpp src/model/common/rope.hpp src/model/detector/yolov8.h src/model/diffusion/anima.hpp src/model/diffusion/animatediff.hpp src/model/diffusion/boogu.hpp src/model/diffusion/control.hpp src/model/diffusion/dit.hpp src/model/diffusion/ernie_image.hpp src/model/diffusion/flux.hpp src/model/diffusion/hidream_o1.hpp src/model/diffusion/ideogram4.hpp src/model/diffusion/krea2.hpp src/model/diffusion/lens.hpp src/model/diffusion/lingbot_video.hpp src/model/diffusion/ltxv.hpp src/model/diffusion/minit2i.hpp src/model/diffusion/mmdit.hpp src/model/diffusion/model.hpp src/model/diffusion/pid.hpp src/model/diffusion/qwen_image.hpp src/model/diffusion/sefi_image.hpp src/model/diffusion/unet.hpp src/model/diffusion/wan.hpp src/model/diffusion/z_image.hpp src/model.h src/model_io/binary_io.h src/model_io/gguf_io.cpp src/model_io/gguf_io.h src/model_io/gguf_reader_ext.h src/model_io/kcpp_sdcpp_quantized_safetensors.hpp src/model_io/pickle_io.cpp src/model_io/pickle_io.h src/model_io/safetensors_io.cpp src/model_io/safetensors_io.h src/model_io/streaming_writer.h src/model_io/tensor_storage.h src/model_io/torch_legacy_io.cpp src/model_io/torch_legacy_io.h src/model_io/torch_zip_io.cpp src/model_io/torch_zip_io.h src/model_loader.cpp src/model_loader.h src/model_manager.cpp src/model_manager.h src/model/te/clip.hpp src/model/te/llm.hpp src/model/te/t5.hpp src/model/upscaler/esrgan.hpp src/model/upscaler/ltx_latent_upscaler.hpp src/model/vae/auto_encoder_kl.hpp src/model/vae/ltx_audio_vae.hpp src/model/vae/ltx_vae.hpp src/model/vae/tae.hpp src/model/vae/vae.hpp src/model/vae/wan_vae.hpp src/name_conversion.cpp src/name_conversion.h src/runtime/cache_dit.hpp src/runtime/condition_cache_utils.hpp src/runtime/denoiser.hpp src/runtime/easycache.hpp src/runtime/gits_noise.h src/runtime/guidance.cpp src/runtime/guidance.h src/runtime/imatrix.cpp src/runtime/imatrix.h src/runtime/latent-preview.h src/runtime/preprocessing.hpp src/runtime/sample-cache.cpp src/runtime/sample-cache.h src/runtime/spectrum.hpp src/runtime/ucache.hpp src/stable-diffusion.cpp src/tokenizers/bpe_tokenizer.cpp src/tokenizers/bpe_tokenizer.h src/tokenizers/clip_tokenizer.cpp src/tokenizers/clip_tokenizer.h src/tokenizers/gemma_tokenizer.cpp src/tokenizers/gemma_tokenizer.h src/tokenizers/gpt_oss_tokenizer.cpp src/tokenizers/gpt_oss_tokenizer.h src/tokenizers/mistral_tokenizer.cpp src/tokenizers/mistral_tokenizer.h src/tokenizers/qwen2_tokenizer.cpp src/tokenizers/qwen2_tokenizer.h src/tokenizers/t5_unigram_tokenizer.cpp src/tokenizers/t5_unigram_tokenizer.h src/tokenizers/tokenizer.cpp src/tokenizers/tokenizer.h src/tokenizers/tokenize_util.cpp src/tokenizers/tokenize_util.h src/tokenizers/vocab/vocab.h src/upscaler.cpp src/upscaler.h src/weight_manager.h

SDCPP_MAIN_BASENAMES := examples/cli/image_metadata.cpp examples/cli/image_metadata.h examples/cli/main.cpp examples/cli/msf_gif.h examples/common/common.cpp examples/common/common.h examples/common/log.cpp examples/common/log.h examples/common/media_io.cpp examples/common/media_io.h examples/common/resource_owners.hpp src/tokenizers/vocab/clip_merges.hpp src/tokenizers/vocab/gemma2_merges.hpp src/tokenizers/vocab/gemma2_vocab.hpp src/tokenizers/vocab/gemma_merges.hpp src/tokenizers/vocab/gemma_vocab.hpp src/tokenizers/vocab/gpt_oss_merges.hpp src/tokenizers/vocab/gpt_oss_vocab.hpp src/tokenizers/vocab/mistral_merges.hpp src/tokenizers/vocab/mistral_vocab.hpp src/tokenizers/vocab/qwen_merges.hpp src/tokenizers/vocab/t5.hpp src/tokenizers/vocab/umt5.hpp src/tokenizers/vocab/vocab.cpp src/convert.cpp src/version.cpp

Expand All @@ -726,7 +726,7 @@ otherarch/sdcpp/src/%.o: otherarch/sdcpp/src/%.cpp
otherarch/sdcpp/examples/%.o: otherarch/sdcpp/examples/%.cpp
$(CXX) -I./otherarch/sdcpp/include -I./otherarch/sdcpp/examples -I./vendor/nlohmann $(CXXFLAGS) -c $< -o $@

otherarch/sdcpp/sdtype_adapter.o: otherarch/sdcpp/sdtype_adapter.cpp
otherarch/sdcpp/sdtype_adapter.o: otherarch/sdcpp/sdtype_adapter.cpp otherarch/sdcpp/include/stable-diffusion.h otherarch/sdcpp/src/kcpp_sd_extensions.h model_adapter.h otherarch/utils.h
$(CXX) -I./otherarch/sdcpp/include -I./otherarch/sdcpp/src $(CXXFLAGS) -c $< -o $@

otherarch/sdcpp/thirdparty/zip.o: otherarch/sdcpp/thirdparty/zip.c
Expand Down
1 change: 1 addition & 0 deletions expose.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -241,6 +241,7 @@ struct sd_generation_inputs
const char * scheduler = nullptr;
const float eta = -1.0f;
const char * extra_sample_args = nullptr;
const char * ref_image_args = nullptr;
const int clip_skip = -1;
const int vid_req_frames = 1;
const int vid_fps = 16;
Expand Down
3 changes: 3 additions & 0 deletions koboldcpp.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -433,6 +433,7 @@ class sd_generation_inputs(ctypes.Structure):
("scheduler", ctypes.c_char_p),
("eta", ctypes.c_float),
("extra_sample_args", ctypes.c_char_p),
("ref_image_args", ctypes.c_char_p),
("clip_skip", ctypes.c_int),
("vid_req_frames", ctypes.c_int),
("vid_fps", ctypes.c_int),
Expand Down Expand Up @@ -2697,6 +2698,7 @@ def gendefaults_parse_meta_field(value):
'cache-option': 'cache_options',
'cache_option': 'cache_options',
'extra-sample-args': 'extra_sample_args',
'ref-image-args': 'ref_image_args',
}
parsed = parse_json_object(value, 'gendefaults') or {}
result = {}
Expand Down Expand Up @@ -2866,6 +2868,7 @@ def build_prompt(prompt, forced):
sample_method = (genparams.get("sampler_name") or "default")
scheduler = (genparams.get("scheduler") or "default").lower()
extra_sample_args = str(genparams.get("extra_sample_args") or "")
ref_image_args = str(genparams.get("ref_image_args") or "")
clip_skip = tryparseint(genparams.get("clip_skip", -1),-1)
eta = tryparsefloat(genparams.get("eta", None), None)
vid_req_frames = tryparseint(genparams.get("frames", 1),1)
Expand Down
89 changes: 86 additions & 3 deletions otherarch/sdcpp/examples/cli/main.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -199,7 +199,7 @@ struct SDCliParams {
options.manual_options = {
{"-M",
"--mode",
"run mode, one of [img_gen, vid_gen, upscale, convert, metadata], default: img_gen",
"run mode, one of [img_gen, adetailer, vid_gen, upscale, convert, metadata], default: img_gen",
on_mode_arg},
{"",
"--preview",
Expand Down Expand Up @@ -566,6 +566,65 @@ bool save_results(const SDCliParams& cli_params,
return sucessful_reults != 0;
}

static bool apply_adetailer(sd_ctx_t* sd_ctx,
const sd_ctx_params_t& sd_ctx_params,
const SDContextParams& ctx_params,
const SDGenerationParams& gen_params,
const sd_img_gen_params_t& img_gen_params,
SDMode mode,
SDImageVec& results,
int num_results) {
if (gen_params.ad_model_path.empty()) {
return true;
}

sd_adetailer_params_t ad_params{};
ad_params.prompt = gen_params.ad_prompt.empty() ? nullptr : gen_params.ad_prompt.c_str();
ad_params.negative_prompt = gen_params.ad_negative_prompt.empty() ? nullptr : gen_params.ad_negative_prompt.c_str();
ad_params.extra_ad_args = gen_params.extra_ad_args.c_str();

ADetailerCtxPtr ad_ctx(new_adetailer_ctx(gen_params.ad_model_path.c_str(),
ctx_params.n_threads,
sd_ctx_params.backend,
sd_ctx_params.params_backend));
if (ad_ctx == nullptr) {
LOG_ERROR("new_adetailer_ctx failed");
return false;
}

for (int i = 0; i < num_results; ++i) {
if (results[i].data == nullptr) {
continue;
}
sd_img_gen_params_t ad_generation_params = img_gen_params;
ad_generation_params.seed = img_gen_params.seed + i;
if (mode == IMG_GEN) {
ad_generation_params.width = 512;
ad_generation_params.height = 512;
ad_generation_params.strength = 0.4f;
}
sd_image_t* detailed_images = nullptr;
int detailed_count = 0;
if (!adetail_image(ad_ctx.get(),
sd_ctx,
results[i],
&ad_params,
&ad_generation_params,
&detailed_images,
&detailed_count) ||
detailed_count <= 0 || detailed_images == nullptr || detailed_images[0].data == nullptr) {
free_sd_images(detailed_images, detailed_count);
LOG_ERROR("ADetailer failed for image %d", i + 1);
return false;
}
free(results[i].data);
results[i] = detailed_images[0];
detailed_images[0] = {0, 0, 0, nullptr};
free_sd_images(detailed_images, detailed_count);
}
return true;
}

int main(int argc, const char* argv[]) {
if (argc > 1 && std::string(argv[1]) == "--version") {
std::cout << version_string() << "\n";
Expand Down Expand Up @@ -598,6 +657,11 @@ int main(int argc, const char* argv[]) {
return 0;
}

if (!gen_params.ad_model_path.empty() && cli_params.mode != IMG_GEN && cli_params.mode != ADETAILER) {
LOG_ERROR("--ad-model is only supported in image generation and adetailer modes");
return 1;
}

if (gen_params.video_frames > 4) {
size_t last_dot_pos = cli_params.preview_path.find_last_of(".");
std::string base_path = cli_params.preview_path;
Expand Down Expand Up @@ -806,15 +870,22 @@ int main(int argc, const char* argv[]) {
gen_params.sample_params.scheduler = sd_get_default_scheduler(sd_ctx.get(), gen_params.sample_params.sample_method);
}

if (cli_params.mode == IMG_GEN) {
sd_img_gen_params_t img_gen_params = gen_params.to_sd_img_gen_params_t();
sd_img_gen_params_t img_gen_params{};
const bool use_img_gen_params = cli_params.mode == IMG_GEN || cli_params.mode == ADETAILER;
if (use_img_gen_params) {
img_gen_params = gen_params.to_sd_img_gen_params_t();
}

if (cli_params.mode == IMG_GEN) {
sd_image_t* generated_images = nullptr;
if (!generate_image(sd_ctx.get(), &img_gen_params, &generated_images, &num_results)) {
generated_images = nullptr;
num_results = 0;
}
results.adopt(generated_images, num_results);
} else if (cli_params.mode == ADETAILER) {
num_results = 1;
results.push_back(gen_params.init_image.release());
} else if (cli_params.mode == VID_GEN) {
sd_vid_gen_params_t vid_gen_params = gen_params.to_sd_vid_gen_params_t();
sd_image_t* generated_video = nullptr;
Expand All @@ -828,6 +899,18 @@ int main(int argc, const char* argv[]) {
LOG_ERROR("generate failed");
return 1;
}

if (use_img_gen_params &&
!apply_adetailer(sd_ctx.get(),
sd_ctx_params,
ctx_params,
gen_params,
img_gen_params,
cli_params.mode,
results,
num_results)) {
return 1;
}
}

int upscale_factor = 4; // unused for RealESRGAN_x4plus_anime_6B.pth
Expand Down
Loading