mirror of
https://github.com/leejet/stable-diffusion.cpp.git
synced 2026-10-26 07:04:10 +08:00
865 lines
39 KiB
C++
865 lines
39 KiB
C++
#include "routes.h"
|
|
|
|
#include <algorithm>
|
|
#include <cctype>
|
|
#include <cstring>
|
|
#include <limits>
|
|
#include <regex>
|
|
#include <stdexcept>
|
|
#include <string_view>
|
|
#include <unordered_map>
|
|
#include <unordered_set>
|
|
|
|
#include "common/common.h"
|
|
#include "common/media_io.h"
|
|
#include "common/resource_owners.hpp"
|
|
#include "model_catalog.h"
|
|
|
|
namespace fs = std::filesystem;
|
|
|
|
static std::string extract_and_remove_sd_cpp_extra_args(std::string& text) {
|
|
std::regex re("<sd_cpp_extra_args>(.*?)</sd_cpp_extra_args>");
|
|
std::smatch match;
|
|
|
|
std::string extracted;
|
|
if (std::regex_search(text, match, re)) {
|
|
extracted = match[1].str();
|
|
text = std::regex_replace(text, re, "");
|
|
}
|
|
return extracted;
|
|
}
|
|
|
|
static fs::path resolve_display_model_path(const ServerRuntime& runtime) {
|
|
const auto& ctx = *runtime.ctx_params;
|
|
if (!ctx.model_path.empty()) {
|
|
return fs::u8path(ctx.model_path);
|
|
}
|
|
if (!ctx.diffusion_model_path.empty()) {
|
|
return fs::u8path(ctx.diffusion_model_path);
|
|
}
|
|
return {};
|
|
}
|
|
|
|
static std::string lower_ascii(std::string value) {
|
|
std::transform(value.begin(), value.end(), value.begin(), [](unsigned char c) {
|
|
return static_cast<char>(std::tolower(c));
|
|
});
|
|
return value;
|
|
}
|
|
|
|
static enum sample_method_t get_sdapi_sample_method(std::string name) {
|
|
enum sample_method_t result = str_to_sample_method(name.c_str());
|
|
if (result != SAMPLE_METHOD_COUNT) {
|
|
return result;
|
|
}
|
|
|
|
name = lower_ascii(name);
|
|
static const std::unordered_map<std::string_view, sample_method_t> hardcoded{
|
|
{"euler a", EULER_A_SAMPLE_METHOD},
|
|
{"k_euler_a", EULER_A_SAMPLE_METHOD},
|
|
{"euler", EULER_SAMPLE_METHOD},
|
|
{"k_euler", EULER_SAMPLE_METHOD},
|
|
{"heun", HEUN_SAMPLE_METHOD},
|
|
{"k_heun", HEUN_SAMPLE_METHOD},
|
|
{"dpm2", DPM2_SAMPLE_METHOD},
|
|
{"k_dpm_2", DPM2_SAMPLE_METHOD},
|
|
{"lcm", LCM_SAMPLE_METHOD},
|
|
{"ddim", DDIM_TRAILING_SAMPLE_METHOD},
|
|
{"dpm++ 2m", DPMPP2M_SAMPLE_METHOD},
|
|
{"k_dpmpp_2m", DPMPP2M_SAMPLE_METHOD},
|
|
{"dpm++ 2m sde", DPMPP2M_SDE_SAMPLE_METHOD},
|
|
{"k_dpmpp_2m_sde", DPMPP2M_SDE_SAMPLE_METHOD},
|
|
{"dpm++ 2m sde gpu", DPMPP2M_SDE_BT_SAMPLE_METHOD},
|
|
{"k_dpmpp_2m_sde_gpu", DPMPP2M_SDE_BT_SAMPLE_METHOD},
|
|
{"res multistep", RES_MULTISTEP_SAMPLE_METHOD},
|
|
{"k_res_multistep", RES_MULTISTEP_SAMPLE_METHOD},
|
|
{"res 2s", RES_2S_SAMPLE_METHOD},
|
|
{"k_res_2s", RES_2S_SAMPLE_METHOD},
|
|
{"euler_cfg_pp", EULER_CFG_PP_SAMPLE_METHOD},
|
|
{"k_euler_cfg_pp", EULER_CFG_PP_SAMPLE_METHOD},
|
|
{"euler_a_cfg_pp", EULER_CFG_PP_SAMPLE_METHOD},
|
|
{"k_euler_a_cfg_pp", EULER_CFG_PP_SAMPLE_METHOD},
|
|
};
|
|
auto it = hardcoded.find(name);
|
|
return it != hardcoded.end() ? it->second : SAMPLE_METHOD_COUNT;
|
|
}
|
|
|
|
static bool parse_sdapi_adetailer(const json& body,
|
|
ServerRuntime& runtime,
|
|
bool img2img,
|
|
ImgGenJobRequest& request,
|
|
std::string& error_message) {
|
|
request.adetailer_enabled = false;
|
|
request.adetailer_passes.clear();
|
|
if (!body.contains("alwayson_scripts")) {
|
|
return true;
|
|
}
|
|
try {
|
|
const auto& scripts = body.at("alwayson_scripts");
|
|
if (!scripts.is_object()) {
|
|
throw std::invalid_argument("alwayson_scripts must be an object");
|
|
}
|
|
if (!scripts.contains("ADetailer")) {
|
|
return true;
|
|
}
|
|
const auto& args = scripts.at("ADetailer").at("args");
|
|
if (!args.is_array()) {
|
|
throw std::invalid_argument("ADetailer.args must be an array");
|
|
}
|
|
if (args.empty() || (args[0].is_boolean() && !args[0].get<bool>())) {
|
|
return true;
|
|
}
|
|
static const std::unordered_set<std::string> keys = {
|
|
"ad_model", "ad_model_classes", "ad_tab_enable", "ad_prompt", "ad_negative_prompt",
|
|
"ad_confidence", "ad_mask_filter_method", "ad_mask_k", "ad_mask_min_ratio", "ad_mask_max_ratio",
|
|
"ad_dilate_erode", "ad_x_offset", "ad_y_offset", "ad_mask_merge_invert", "ad_mask_blur",
|
|
"ad_denoising_strength", "ad_inpaint_only_masked", "ad_inpaint_only_masked_padding",
|
|
"ad_use_inpaint_width_height", "ad_inpaint_width", "ad_inpaint_height", "ad_use_steps", "ad_steps",
|
|
"ad_use_cfg_scale", "ad_cfg_scale", "ad_use_sampler", "ad_sampler", "ad_scheduler",
|
|
"ad_use_checkpoint", "ad_checkpoint", "ad_use_vae", "ad_vae", "ad_use_noise_multiplier",
|
|
"ad_noise_multiplier", "ad_use_clip_skip", "ad_clip_skip", "ad_restore_face", "ad_controlnet_model",
|
|
"ad_controlnet_module", "ad_controlnet_weight", "ad_controlnet_guidance_start", "ad_controlnet_guidance_end", "is_api"};
|
|
for (const auto& config : args) {
|
|
if (!config.is_object()) {
|
|
continue;
|
|
}
|
|
auto boolean = [&](const char* key, bool fallback) {
|
|
if (!config.contains(key))
|
|
return fallback;
|
|
if (!config.at(key).is_boolean())
|
|
throw std::invalid_argument(std::string(key) + " must be boolean");
|
|
return config.at(key).get<bool>();
|
|
};
|
|
auto text = [&](const char* key, const char* fallback) {
|
|
if (!config.contains(key))
|
|
return std::string(fallback);
|
|
if (!config.at(key).is_string())
|
|
throw std::invalid_argument(std::string(key) + " must be a string");
|
|
return config.at(key).get<std::string>();
|
|
};
|
|
auto number = [&](const char* key, double fallback, double minimum, double maximum) {
|
|
double value = fallback;
|
|
if (config.contains(key)) {
|
|
if (!config.at(key).is_number())
|
|
throw std::invalid_argument(std::string(key) + " must be numeric");
|
|
value = config.at(key).get<double>();
|
|
}
|
|
if (!std::isfinite(value) || value < minimum || value > maximum)
|
|
throw std::invalid_argument(std::string(key) + " is out of range");
|
|
return value;
|
|
};
|
|
auto integer = [&](const char* key, int fallback, int minimum, int maximum = std::numeric_limits<int>::max()) {
|
|
if (config.contains(key) && !config.at(key).is_number_integer())
|
|
throw std::invalid_argument(std::string(key) + " must be an integer");
|
|
return static_cast<int>(number(key, fallback, minimum, maximum));
|
|
};
|
|
const std::string model = text("ad_model", "None");
|
|
if (model == "None" || !boolean("ad_tab_enable", true)) {
|
|
continue;
|
|
}
|
|
for (const auto& item : config.items()) {
|
|
if (keys.count(item.key()) == 0)
|
|
throw std::invalid_argument("unsupported ADetailer setting: " + item.key());
|
|
}
|
|
const auto& configured = runtime.default_gen_params->ad_model_path;
|
|
if (configured.empty())
|
|
throw std::invalid_argument("ADetailer requires a server-configured --ad-model");
|
|
const auto path = fs::u8path(configured);
|
|
if (model.find_first_of("/\\") != std::string::npos ||
|
|
(lower_ascii(model) != lower_ascii(path.filename().u8string()) && lower_ascii(model) != lower_ascii(path.stem().u8string() + ".pt"))) {
|
|
throw std::invalid_argument("ADetailer model must match the server-configured detector");
|
|
}
|
|
if (!text("ad_model_classes", "").empty())
|
|
throw std::invalid_argument("ad_model_classes is not supported");
|
|
if (boolean("ad_use_checkpoint", false)) {
|
|
const auto checkpoint = config.contains("ad_checkpoint") && config.at("ad_checkpoint").is_null() ? "" : text("ad_checkpoint", "Use same checkpoint");
|
|
if (!checkpoint.empty() && checkpoint != "None" && checkpoint != "Use same checkpoint")
|
|
throw std::invalid_argument("ADetailer checkpoint switching is not supported");
|
|
}
|
|
if (boolean("ad_use_vae", false)) {
|
|
const auto vae = config.contains("ad_vae") && config.at("ad_vae").is_null() ? "" : text("ad_vae", "Use same VAE");
|
|
if (!vae.empty() && vae != "None" && vae != "Use same VAE")
|
|
throw std::invalid_argument("ADetailer VAE switching is not supported");
|
|
}
|
|
if (boolean("ad_use_noise_multiplier", false) && number("ad_noise_multiplier", 1, 0.5, 1.5) != 1)
|
|
throw std::invalid_argument("ADetailer noise multiplier is not supported");
|
|
if (boolean("ad_restore_face", false))
|
|
throw std::invalid_argument("ADetailer face restoration is not supported");
|
|
if (text("ad_controlnet_model", "None") != "None")
|
|
throw std::invalid_argument("ADetailer ControlNet is not supported");
|
|
|
|
ServerADetailerPass pass;
|
|
pass.prompt = text("ad_prompt", "");
|
|
pass.negative_prompt = text("ad_negative_prompt", "");
|
|
pass.width = request.gen_params.get_resolved_width();
|
|
pass.height = request.gen_params.get_resolved_height();
|
|
pass.strength = static_cast<float>(number("ad_denoising_strength", 0.4, 0, 1));
|
|
auto append = [&](const char* key, const std::string& value) {
|
|
if (!pass.extra_args.empty())
|
|
pass.extra_args += ",";
|
|
pass.extra_args += std::string(key) + "=" + value;
|
|
};
|
|
auto append_number = [&](const char* target, const char* key, double fallback, double minimum, double maximum) {
|
|
append(target, json(number(key, fallback, minimum, maximum)).dump());
|
|
};
|
|
auto append_integer = [&](const char* target, const char* key, int fallback, int minimum, int maximum = std::numeric_limits<int>::max()) {
|
|
append(target, std::to_string(integer(key, fallback, minimum, maximum)));
|
|
};
|
|
append_number("confidence", "ad_confidence", 0.3, 0, 1);
|
|
append_integer("mask_k_largest", "ad_mask_k", 0, 0);
|
|
const auto filter = text("ad_mask_filter_method", "Area");
|
|
if (filter != "Area" && filter != "Confidence")
|
|
throw std::invalid_argument("invalid ad_mask_filter_method");
|
|
append("mask_filter_method", lower_ascii(filter));
|
|
const auto min_ratio = number("ad_mask_min_ratio", 0, 0, 1);
|
|
const auto max_ratio = number("ad_mask_max_ratio", 1, 0, 1);
|
|
if (min_ratio > max_ratio)
|
|
throw std::invalid_argument("ad_mask_min_ratio exceeds ad_mask_max_ratio");
|
|
append("mask_min_ratio", json(min_ratio).dump());
|
|
append("mask_max_ratio", json(max_ratio).dump());
|
|
// Bound pixel operations before converting them to the native mask parameters.
|
|
const int mask_limit = std::clamp(std::max(pass.width, pass.height), 32, 16384);
|
|
append_integer("dilate_erode", "ad_dilate_erode", 4, -mask_limit, mask_limit);
|
|
append_integer("x_offset", "ad_x_offset", 0, -mask_limit, mask_limit);
|
|
append_integer("y_offset", "ad_y_offset", 0, -mask_limit, mask_limit);
|
|
append_integer("mask_blur", "ad_mask_blur", 4, 0, mask_limit);
|
|
append_integer("inpaint_padding", "ad_inpaint_only_masked_padding", 32, 0, mask_limit);
|
|
append("inpaint_only_masked", boolean("ad_inpaint_only_masked", true) ? "true" : "false");
|
|
const auto merge = text("ad_mask_merge_invert", "None");
|
|
if (merge != "None" && merge != "Merge" && merge != "Merge and Invert")
|
|
throw std::invalid_argument("invalid ad_mask_merge_invert");
|
|
append("mask_mode", merge == "None" ? "none" : merge == "Merge" ? "merge"
|
|
: "merge_invert");
|
|
if (boolean("ad_use_inpaint_width_height", false)) {
|
|
pass.width = integer("ad_inpaint_width", 512, 1, k_max_generation_dimension);
|
|
pass.height = integer("ad_inpaint_height", 512, 1, k_max_generation_dimension);
|
|
}
|
|
if (boolean("ad_use_steps", false))
|
|
append_integer("steps", "ad_steps", 28, 1, k_max_adetailer_steps);
|
|
if (boolean("ad_use_cfg_scale", false))
|
|
append_number("cfg_scale", "ad_cfg_scale", 7, 0, std::numeric_limits<float>::max());
|
|
if (boolean("ad_use_clip_skip", false)) {
|
|
pass.clip_skip = integer("ad_clip_skip", 1, 1);
|
|
if (pass.clip_skip > 12)
|
|
throw std::invalid_argument("ad_clip_skip is out of range");
|
|
}
|
|
if (boolean("ad_use_sampler", false)) {
|
|
std::string sampler = text("ad_sampler", "DPM++ 2M Karras");
|
|
if (sampler != "Use same sampler") {
|
|
const std::string suffix = " karras";
|
|
const bool legacy_karras = sampler.size() > suffix.size() && lower_ascii(sampler.substr(sampler.size() - suffix.size())) == suffix;
|
|
if (legacy_karras)
|
|
sampler.resize(sampler.size() - suffix.size());
|
|
const auto method = get_sdapi_sample_method(sampler);
|
|
if (method == SAMPLE_METHOD_COUNT)
|
|
throw std::invalid_argument("unsupported ADetailer sampler");
|
|
append("sample_method", sd_sample_method_name(method));
|
|
if (legacy_karras && text("ad_scheduler", "Use same scheduler") == "Use same scheduler")
|
|
append("scheduler", sd_scheduler_name(KARRAS_SCHEDULER));
|
|
}
|
|
const auto scheduler = text("ad_scheduler", "Use same scheduler");
|
|
if (scheduler == "Automatic") {
|
|
pass.automatic_scheduler = true;
|
|
} else if (scheduler != "Use same scheduler") {
|
|
const auto value = str_to_scheduler(scheduler.c_str());
|
|
if (value == SCHEDULER_COUNT)
|
|
throw std::invalid_argument("unsupported ADetailer scheduler");
|
|
append("scheduler", sd_scheduler_name(value));
|
|
}
|
|
}
|
|
request.adetailer_passes.push_back(std::move(pass));
|
|
}
|
|
if (!request.adetailer_passes.empty() && img2img && args.size() > 1 && args[1].is_boolean() && args[1].get<bool>()) {
|
|
throw std::invalid_argument("ADetailer skip img2img is not supported");
|
|
}
|
|
request.adetailer_enabled = !request.adetailer_passes.empty();
|
|
return true;
|
|
} catch (const std::exception& error) {
|
|
error_message = std::string("invalid ADetailer args: ") + error.what();
|
|
return false;
|
|
}
|
|
}
|
|
|
|
static bool build_sdapi_img_gen_request(const json& j,
|
|
ServerRuntime& runtime,
|
|
bool img2img,
|
|
ImgGenJobRequest& request,
|
|
std::string& error_message) {
|
|
std::string prompt = j.value("prompt", "");
|
|
std::string negative_prompt = j.value("negative_prompt", "");
|
|
int width = j.value("width", 512);
|
|
int height = j.value("height", 512);
|
|
int steps = j.value("steps", runtime.default_gen_params->sample_params.sample_steps);
|
|
float cfg_scale = j.value("cfg_scale", runtime.default_gen_params->sample_params.guidance.txt_cfg);
|
|
int64_t seed = j.value("seed", -1);
|
|
int batch_size = j.value("batch_size", 1);
|
|
int clip_skip = j.value("clip_skip", -1);
|
|
std::string sampler_name = j.value("sampler_name", "");
|
|
std::string scheduler_name = j.value("scheduler", "");
|
|
|
|
if (width <= 0 || height <= 0) {
|
|
error_message = "width and height must be positive";
|
|
return false;
|
|
}
|
|
|
|
if (prompt.empty()) {
|
|
error_message = "prompt required";
|
|
return false;
|
|
}
|
|
|
|
request.gen_params = *runtime.default_gen_params;
|
|
|
|
request.gen_params.prompt = prompt;
|
|
request.gen_params.negative_prompt = negative_prompt;
|
|
request.gen_params.seed = seed;
|
|
request.gen_params.sample_params.sample_steps = steps;
|
|
request.gen_params.batch_count = batch_size;
|
|
request.gen_params.sample_params.guidance.txt_cfg = cfg_scale;
|
|
const bool recipe_dimensions = !img2img && model_status(runtime)["recipe"].is_string();
|
|
request.gen_params.width = j.value("width", recipe_dimensions ? runtime.default_gen_params->width : -1);
|
|
request.gen_params.height = j.value("height", recipe_dimensions ? runtime.default_gen_params->height : -1);
|
|
|
|
if (!img2img && j.value("enable_hr", false)) {
|
|
request.gen_params.hires_enabled = true;
|
|
request.gen_params.hires_scale = j.value("hr_scale", request.gen_params.hires_scale);
|
|
request.gen_params.hires_width = j.value("hr_resize_x", request.gen_params.hires_width);
|
|
request.gen_params.hires_height = j.value("hr_resize_y", request.gen_params.hires_height);
|
|
request.gen_params.hires_steps = j.value("hr_steps", request.gen_params.hires_steps);
|
|
request.gen_params.hires_denoising_strength =
|
|
j.value("denoising_strength", request.gen_params.hires_denoising_strength);
|
|
|
|
request.gen_params.hires_upscaler = j.value("hr_upscaler", request.gen_params.hires_upscaler);
|
|
}
|
|
|
|
std::string sd_cpp_extra_args_str = extract_and_remove_sd_cpp_extra_args(request.gen_params.prompt);
|
|
if (!sd_cpp_extra_args_str.empty() && !request.gen_params.from_json_str(sd_cpp_extra_args_str)) {
|
|
error_message = "invalid sd_cpp_extra_args";
|
|
return false;
|
|
}
|
|
|
|
if (clip_skip > 0) {
|
|
request.gen_params.clip_skip = clip_skip;
|
|
}
|
|
|
|
enum sample_method_t sample_method = get_sdapi_sample_method(sampler_name);
|
|
if (sample_method != SAMPLE_METHOD_COUNT) {
|
|
request.gen_params.sample_params.sample_method = sample_method;
|
|
}
|
|
|
|
enum scheduler_t scheduler = str_to_scheduler(scheduler_name.c_str());
|
|
if (scheduler != SCHEDULER_COUNT) {
|
|
request.gen_params.sample_params.scheduler = scheduler;
|
|
}
|
|
|
|
if (j.contains("lora") && j["lora"].is_array()) {
|
|
refresh_lora_cache(runtime);
|
|
request.gen_params.lora_map.clear();
|
|
request.gen_params.high_noise_lora_map.clear();
|
|
|
|
for (const auto& item : j["lora"]) {
|
|
if (!item.is_object()) {
|
|
continue;
|
|
}
|
|
|
|
std::string path = item.value("path", "");
|
|
float multiplier = item.value("multiplier", 1.0f);
|
|
bool is_high_noise = item.value("is_high_noise", false);
|
|
|
|
if (path.empty()) {
|
|
error_message = "lora.path required";
|
|
return false;
|
|
}
|
|
|
|
std::string fullpath = get_lora_full_path(runtime, path);
|
|
if (fullpath.empty()) {
|
|
error_message = "invalid lora path: " + path;
|
|
return false;
|
|
}
|
|
|
|
if (is_high_noise) {
|
|
request.gen_params.high_noise_lora_map[fullpath] += multiplier;
|
|
} else {
|
|
request.gen_params.lora_map[fullpath] += multiplier;
|
|
}
|
|
}
|
|
}
|
|
|
|
if (j.contains("ref_image_args")) {
|
|
if (!j["ref_image_args"].is_string()) {
|
|
error_message = "ref_image_args must be a string";
|
|
return false;
|
|
}
|
|
request.gen_params.ref_image_args = j["ref_image_args"].get<std::string>();
|
|
}
|
|
|
|
if (j.contains("image_preprocess") && !request.gen_params.parse_image_preprocess_json(j["image_preprocess"].dump())) {
|
|
error_message = "invalid image_preprocess";
|
|
return false;
|
|
}
|
|
|
|
if (img2img) {
|
|
if (j.contains("init_images") && j["init_images"].is_array() && !j["init_images"].empty()) {
|
|
if (decode_base64_image(j["init_images"][0].get<std::string>(),
|
|
0,
|
|
0,
|
|
0,
|
|
request.gen_params.init_image)) {
|
|
const sd_image_t& image = request.gen_params.init_image.get();
|
|
request.gen_params.set_width_and_height_if_unset(image.width, image.height);
|
|
}
|
|
}
|
|
|
|
if (j.contains("mask") && j["mask"].is_string()) {
|
|
if (decode_base64_image(j["mask"].get<std::string>(),
|
|
1,
|
|
0,
|
|
0,
|
|
request.gen_params.mask_image)) {
|
|
const sd_image_t& image = request.gen_params.mask_image.get();
|
|
request.gen_params.set_width_and_height_if_unset(image.width, image.height);
|
|
}
|
|
sd_image_t& mask_image = request.gen_params.mask_image.get();
|
|
bool inpainting_mask_invert = j.value("inpainting_mask_invert", 0) != 0;
|
|
if (inpainting_mask_invert && mask_image.data != nullptr) {
|
|
for (uint32_t i = 0; i < mask_image.width * mask_image.height; ++i) {
|
|
mask_image.data[i] = 255 - mask_image.data[i];
|
|
}
|
|
}
|
|
} else {
|
|
request.gen_params.mask_image.reset({0, 0, 1, nullptr});
|
|
}
|
|
|
|
float denoising_strength = j.value("denoising_strength", -1.f);
|
|
if (denoising_strength >= 0.f) {
|
|
request.gen_params.strength = std::min(denoising_strength, 1.0f);
|
|
}
|
|
}
|
|
|
|
if (j.contains("extra_images") && j["extra_images"].is_array()) {
|
|
for (const auto& extra_image : j["extra_images"]) {
|
|
if (!extra_image.is_string()) {
|
|
continue;
|
|
}
|
|
SDImageOwner image_owner;
|
|
if (decode_base64_image(extra_image.get<std::string>(),
|
|
0,
|
|
0, 0,
|
|
image_owner)) {
|
|
const sd_image_t& image = image_owner.get();
|
|
request.gen_params.set_width_and_height_if_unset(image.width, image.height);
|
|
request.gen_params.ref_images.push_back(std::move(image_owner));
|
|
}
|
|
}
|
|
}
|
|
|
|
// 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";
|
|
return false;
|
|
}
|
|
|
|
return parse_sdapi_adetailer(j, runtime, img2img, request, error_message) &&
|
|
validate_server_img_gen_request(runtime, request, error_message);
|
|
}
|
|
|
|
static nlohmann::json prepare_info_field(const std::string& generation_info) {
|
|
const auto info = nlohmann::json::parse(generation_info);
|
|
const auto& sampling = info.at("sample_params");
|
|
nlohmann::json result = {{"prompt", info.at("prompt")},
|
|
{"negative_prompt", info.at("negative_prompt")},
|
|
{"seed", generation_seed(generation_info)},
|
|
{"cfg_scale", sampling.at("guidance").at("txt_cfg")},
|
|
{"width", info.at("width")},
|
|
{"height", info.at("height")},
|
|
{"steps", sampling.contains("custom_sigmas") ? json(sampling.at("custom_sigmas").size() - 1) : sampling.at("sample_steps")},
|
|
{"sampler_name", sampling.at("sample_method")},
|
|
{"version", "stable-diffusion.cpp"}};
|
|
if (info.contains("clip_skip"))
|
|
result["clip_skip"] = info.at("clip_skip");
|
|
if (info.contains("strength"))
|
|
result["denoising_strength"] = info.at("strength");
|
|
if (sampling.contains("scheduler"))
|
|
result["extra_generation_params"]["Schedule type"] = sampling.at("scheduler");
|
|
for (const auto* key : {"infotexts", "all_prompts", "all_negative_prompts", "all_seeds", "generation_info"})
|
|
result[key] = nlohmann::json::array();
|
|
return result;
|
|
}
|
|
|
|
struct SDAPIPreviewState {
|
|
std::mutex mutex;
|
|
std::string b64;
|
|
std::string id_task;
|
|
std::string job_type;
|
|
int step = 0;
|
|
int total = 0;
|
|
bool active = false;
|
|
int64_t job_count = 0;
|
|
int job_no = 0;
|
|
};
|
|
|
|
static SDAPIPreviewState g_preview;
|
|
|
|
static void preview_callback(int step, int frame_count, sd_image_t* frames, bool is_noisy, void* data) {
|
|
(void)is_noisy;
|
|
(void)data;
|
|
if (frame_count <= 0 || frames == nullptr || frames[0].data == nullptr) {
|
|
return;
|
|
}
|
|
|
|
const sd_image_t& frame = frames[0];
|
|
const sd_preview_info_t info = sd_get_preview_info();
|
|
|
|
auto image_bytes = encode_image_to_vector(EncodedImageFormat::JPEG,
|
|
frame.data,
|
|
frame.width,
|
|
frame.height,
|
|
frame.channel,
|
|
"",
|
|
80);
|
|
if (image_bytes.empty()) {
|
|
return;
|
|
}
|
|
|
|
std::string b64 = base64_encode(image_bytes);
|
|
std::lock_guard<std::mutex> lock(g_preview.mutex);
|
|
g_preview.b64 = std::move(b64);
|
|
g_preview.step = static_cast<int>(std::min<int64_t>(step < 0 ? -static_cast<int64_t>(step) : step,
|
|
std::max(0, info.total_steps)));
|
|
g_preview.total = std::max(0, info.total_steps);
|
|
g_preview.job_no = std::max(0, info.sample_pass - 1);
|
|
}
|
|
|
|
struct SDAPIPreviewGuard {
|
|
SDAPIPreviewGuard(const std::string& id_task, const sd_img_gen_params_t& params, const std::string& job_type, bool detailing = false) {
|
|
std::lock_guard<std::mutex> lock(g_preview.mutex);
|
|
g_preview.id_task = id_task;
|
|
g_preview.total = 0;
|
|
g_preview.job_type = job_type;
|
|
g_preview.b64.clear();
|
|
g_preview.step = 0;
|
|
g_preview.active = true;
|
|
// Each batch item has a base pass and, when enabled, a hires pass.
|
|
g_preview.job_count = static_cast<int64_t>(std::max(1, params.batch_count)) * (params.hires.enabled ? 2 : 1) + (detailing ? 1 : 0);
|
|
g_preview.job_no = 0;
|
|
sd_set_preview_callback(preview_callback, PREVIEW_PROJ, 1, true, false, nullptr);
|
|
}
|
|
|
|
void begin_detailing() {
|
|
sd_set_preview_callback(nullptr, PREVIEW_NONE, 1, false, false, nullptr);
|
|
std::lock_guard<std::mutex> lock(g_preview.mutex);
|
|
g_preview.job_type = "adetailer";
|
|
g_preview.job_no = static_cast<int>(g_preview.job_count - 1);
|
|
g_preview.step = 0;
|
|
g_preview.total = 0;
|
|
}
|
|
|
|
~SDAPIPreviewGuard() {
|
|
sd_set_preview_callback(nullptr, PREVIEW_NONE, 1, false, false, nullptr);
|
|
std::lock_guard<std::mutex> lock(g_preview.mutex);
|
|
g_preview.active = false;
|
|
g_preview.b64.clear();
|
|
}
|
|
|
|
SDAPIPreviewGuard(const SDAPIPreviewGuard&) = delete;
|
|
SDAPIPreviewGuard& operator=(const SDAPIPreviewGuard&) = delete;
|
|
};
|
|
|
|
void register_sdapi_endpoints(httplib::Server& svr, ServerRuntime& rt) {
|
|
ServerRuntime* runtime = &rt;
|
|
RuntimeRoutes routes(svr, rt);
|
|
|
|
auto sdapi_any2img = [runtime](const httplib::Request& req, httplib::Response& res, bool img2img) {
|
|
try {
|
|
if (req.body.empty()) {
|
|
res.status = 400;
|
|
res.set_content(R"({"error":"empty body"})", "application/json");
|
|
return;
|
|
}
|
|
if (!runtime_supports_generation_mode(*runtime, IMG_GEN)) {
|
|
res.status = 400;
|
|
res.set_content(json({{"error", unsupported_generation_mode_error(IMG_GEN)}}).dump(), "application/json");
|
|
return;
|
|
}
|
|
|
|
std::string id_task = "sdapi";
|
|
json j = json::parse(req.body);
|
|
id_task = j.value("id_task", id_task);
|
|
ImgGenJobRequest request;
|
|
std::string error_message;
|
|
if (!build_sdapi_img_gen_request(j, *runtime, img2img, request, error_message)) {
|
|
res.status = 400;
|
|
res.set_content(json({{"error", error_message}}).dump(), "application/json");
|
|
return;
|
|
}
|
|
|
|
LOG_DEBUG("%s\n", request.gen_params.to_string().c_str());
|
|
|
|
sd_img_gen_params_t img_gen_params = request.to_sd_img_gen_params_t();
|
|
SDImageVec results;
|
|
int num_results = 0;
|
|
|
|
{
|
|
std::lock_guard<std::mutex> lock(*runtime->sd_ctx_mutex);
|
|
const bool detailing = request.adetailer_enabled && !runtime->default_gen_params->ad_model_path.empty();
|
|
SDAPIPreviewGuard preview_guard(id_task, img_gen_params, img2img ? "img2img" : "txt2img", detailing);
|
|
sd_image_generation_result_t* generated = nullptr;
|
|
generate_image(runtime->sd_ctx, &img_gen_params, &generated);
|
|
results.adopt(generated, runtime->ctx_params->lora_model_dir);
|
|
num_results = results.count();
|
|
if (detailing && !results.empty())
|
|
preview_guard.begin_detailing();
|
|
if (!results.empty() && !apply_server_adetailer(*runtime, request, img_gen_params, results)) {
|
|
res.status = 500;
|
|
res.set_content(R"({"error":"ADetailer failed"})", "application/json");
|
|
return;
|
|
}
|
|
}
|
|
|
|
if (results.empty()) {
|
|
res.status = 500;
|
|
res.set_content(R"({"error":"generate_image returned no results"})", "application/json");
|
|
return;
|
|
}
|
|
|
|
json out;
|
|
out["images"] = json::array();
|
|
out["parameters"] = j;
|
|
json jsoninfo = prepare_info_field(results.generation_info(0));
|
|
|
|
for (int i = 0; i < num_results; ++i) {
|
|
if (results[i].data == nullptr) {
|
|
continue;
|
|
}
|
|
|
|
bool embed_meta = request.gen_params.embed_image_metadata;
|
|
|
|
std::string params = generation_info_to_webui(results.generation_info(i));
|
|
|
|
auto image_bytes = encode_image_to_vector(EncodedImageFormat::PNG,
|
|
results[i].data,
|
|
results[i].width,
|
|
results[i].height,
|
|
results[i].channel,
|
|
embed_meta ? results.generation_info(i) : "");
|
|
|
|
if (image_bytes.empty()) {
|
|
LOG_ERROR("write image to mem failed");
|
|
continue;
|
|
}
|
|
|
|
out["images"].push_back(base64_encode(image_bytes));
|
|
|
|
const auto actual = json::parse(results.generation_info(i));
|
|
jsoninfo["infotexts"].push_back(params);
|
|
jsoninfo["all_seeds"].push_back(generation_seed(results.generation_info(i)));
|
|
jsoninfo["generation_info"].push_back(actual);
|
|
jsoninfo["all_prompts"].push_back(actual["prompt"]);
|
|
jsoninfo["all_negative_prompts"].push_back(actual["negative_prompt"]);
|
|
}
|
|
|
|
// not a mistake: it is supposed to be a string in json format
|
|
out["info"] = jsoninfo.dump();
|
|
|
|
res.set_content(out.dump(), "application/json");
|
|
res.status = 200;
|
|
|
|
} catch (const std::exception& e) {
|
|
res.status = 500;
|
|
json err;
|
|
err["error"] = "server_error";
|
|
err["message"] = e.what();
|
|
res.set_content(err.dump(), "application/json");
|
|
}
|
|
};
|
|
|
|
routes.post("/sdapi/v1/txt2img", [sdapi_any2img](const httplib::Request& req, httplib::Response& res) {
|
|
sdapi_any2img(req, res, false);
|
|
});
|
|
|
|
routes.post("/sdapi/v1/img2img", [sdapi_any2img](const httplib::Request& req, httplib::Response& res) {
|
|
sdapi_any2img(req, res, true);
|
|
});
|
|
|
|
routes.get("/sdapi/v1/loras", [runtime](const httplib::Request&, httplib::Response& res) {
|
|
refresh_lora_cache(*runtime);
|
|
|
|
json result = json::array();
|
|
{
|
|
std::lock_guard<std::mutex> lock(*runtime->lora_mutex);
|
|
for (const auto& e : *runtime->lora_cache) {
|
|
json item;
|
|
item["name"] = e.name;
|
|
item["path"] = e.path;
|
|
item["display_path"] = e.display_path;
|
|
result.push_back(item);
|
|
}
|
|
}
|
|
|
|
res.set_content(result.dump(), "application/json");
|
|
});
|
|
|
|
routes.get("/sdapi/v1/upscalers", [runtime](const httplib::Request&, httplib::Response& res) {
|
|
refresh_upscaler_cache(*runtime);
|
|
|
|
auto make_builtin = [](const char* name) {
|
|
json item;
|
|
item["name"] = name;
|
|
item["model_name"] = nullptr;
|
|
item["model_path"] = nullptr;
|
|
item["model_url"] = nullptr;
|
|
item["scale"] = 4;
|
|
return item;
|
|
};
|
|
|
|
json result = json::array();
|
|
result.push_back(make_builtin("None"));
|
|
result.push_back(make_builtin("Lanczos"));
|
|
result.push_back(make_builtin("Nearest"));
|
|
|
|
{
|
|
std::lock_guard<std::mutex> lock(*runtime->upscaler_mutex);
|
|
for (const auto& e : *runtime->upscaler_cache) {
|
|
json item;
|
|
item["name"] = e.name;
|
|
item["model_name"] = e.model_name;
|
|
item["model_path"] = e.fullpath;
|
|
item["model_url"] = nullptr;
|
|
item["scale"] = e.scale;
|
|
result.push_back(item);
|
|
}
|
|
}
|
|
|
|
res.set_content(result.dump(), "application/json");
|
|
});
|
|
|
|
routes.get("/sdapi/v1/latent-upscale-modes", [](const httplib::Request&, httplib::Response& res) {
|
|
json result = json::array({
|
|
{{"name", "Latent"}},
|
|
{{"name", "Latent (nearest)"}},
|
|
{{"name", "Latent (nearest-exact)"}},
|
|
{{"name", "Latent (antialiased)"}},
|
|
{{"name", "Latent (bicubic)"}},
|
|
{{"name", "Latent (bicubic antialiased)"}},
|
|
});
|
|
res.set_content(result.dump(), "application/json");
|
|
});
|
|
|
|
routes.get("/sdapi/v1/samplers", [runtime](const httplib::Request&, httplib::Response& res) {
|
|
std::vector<std::string> sampler_names;
|
|
sampler_names.push_back("default");
|
|
for (int i = 0; i < SAMPLE_METHOD_COUNT; i++) {
|
|
sampler_names.push_back(sd_sample_method_name((sample_method_t)i));
|
|
}
|
|
json r = json::array();
|
|
for (auto name : sampler_names) {
|
|
json entry;
|
|
entry["name"] = name;
|
|
entry["aliases"] = json::array({name});
|
|
entry["options"] = json::object();
|
|
r.push_back(entry);
|
|
}
|
|
res.set_content(r.dump(), "application/json");
|
|
});
|
|
|
|
routes.get("/sdapi/v1/schedulers", [runtime](const httplib::Request&, httplib::Response& res) {
|
|
std::vector<std::string> scheduler_names;
|
|
scheduler_names.push_back("default");
|
|
for (int i = 0; i < SCHEDULER_COUNT; i++) {
|
|
scheduler_names.push_back(sd_scheduler_name((scheduler_t)i));
|
|
if (i == DISCRETE_SCHEDULER) {
|
|
scheduler_names.push_back("normal");
|
|
}
|
|
}
|
|
json r = json::array();
|
|
for (auto name : scheduler_names) {
|
|
json entry;
|
|
entry["name"] = name;
|
|
entry["label"] = name;
|
|
r.push_back(entry);
|
|
}
|
|
res.set_content(r.dump(), "application/json");
|
|
});
|
|
|
|
routes.get("/sdapi/v1/sd-models", [runtime](const httplib::Request&, httplib::Response& res) {
|
|
fs::path model_path = resolve_display_model_path(*runtime);
|
|
json entry;
|
|
entry["title"] = model_path.stem().u8string();
|
|
entry["model_name"] = model_path.stem().u8string();
|
|
entry["filename"] = model_path.filename().u8string();
|
|
entry["hash"] = "8888888888";
|
|
entry["sha256"] = "8888888888888888888888888888888888888888888888888888888888888888";
|
|
entry["config"] = nullptr;
|
|
json r = json::array();
|
|
if (runtime->sd_ctx) {
|
|
r.push_back(entry);
|
|
}
|
|
res.set_content(r.dump(), "application/json");
|
|
});
|
|
|
|
routes.get("/sdapi/v1/options", [runtime](const httplib::Request&, httplib::Response& res) {
|
|
fs::path model_path = resolve_display_model_path(*runtime);
|
|
json r;
|
|
r["samples_format"] = "png";
|
|
r["sd_model_checkpoint"] = model_path.stem().u8string();
|
|
res.set_content(r.dump(), "application/json");
|
|
});
|
|
|
|
routes.get("/sdapi/v1/progress", [](const httplib::Request& req, httplib::Response& res) {
|
|
bool skip_current_image = false;
|
|
bool has_id_param = req.has_param("id_task");
|
|
std::string req_id_task = has_id_param ? req.get_param_value("id_task") : "";
|
|
|
|
if (req.has_param("skip_current_image")) {
|
|
std::string skip_str = req.get_param_value("skip_current_image");
|
|
skip_current_image = (skip_str == "true" || skip_str == "1");
|
|
}
|
|
|
|
json r;
|
|
r["eta_relative"] = 0.0f;
|
|
json state;
|
|
state["skipped"] = false;
|
|
state["interrupted"] = false;
|
|
state["job_timestamp"] = "0";
|
|
r["textinfo"] = nullptr;
|
|
|
|
{
|
|
std::lock_guard<std::mutex> lock(g_preview.mutex);
|
|
|
|
bool is_matching_task = g_preview.active && (!has_id_param || req_id_task == g_preview.id_task);
|
|
|
|
int step = is_matching_task ? g_preview.step : 0;
|
|
int steps = is_matching_task ? g_preview.total : 0;
|
|
std::string b64 = is_matching_task ? g_preview.b64 : "";
|
|
std::string job_type = is_matching_task ? g_preview.job_type : "";
|
|
int64_t job_count = is_matching_task ? g_preview.job_count : 0;
|
|
int job_no = is_matching_task ? g_preview.job_no : 0;
|
|
|
|
float batch_progress = (steps > 0) ? (static_cast<float>(step) / static_cast<float>(steps)) : 0.0f;
|
|
if (batch_progress > 1.0f)
|
|
batch_progress = 1.0f;
|
|
|
|
float overall_progress = job_count > 0
|
|
? (static_cast<float>(job_no) + batch_progress) / static_cast<float>(job_count)
|
|
: 0.0f;
|
|
if (overall_progress > 1.0f)
|
|
overall_progress = 1.0f;
|
|
|
|
r["progress"] = overall_progress;
|
|
state["job"] = job_type;
|
|
state["sampling_step"] = step;
|
|
state["sampling_steps"] = steps;
|
|
state["job_count"] = job_count;
|
|
state["job_no"] = job_no;
|
|
r["state"] = state;
|
|
|
|
if (!skip_current_image && !b64.empty()) {
|
|
r["current_image"] = b64;
|
|
} else {
|
|
r["current_image"] = nullptr;
|
|
}
|
|
}
|
|
|
|
res.set_content(r.dump(), "application/json");
|
|
});
|
|
}
|