2b1bc06477
* first attempt at updating to photomaker v2 * continue adding photomaker v2 modules * finishing the last few pieces for photomaker v2; id_embeds need to be done by a manual step and pass as an input file * added a name converter for Photomaker V2; build ok * more debugging underway * failing at cuda mat_mul * updated chunk_half to be more efficient; redo feedforward * fixed a bug: carefully using ggml_view_4d to get chunks of a tensor; strides need to be recalculated or set properly; still failing at soft_max cuda op * redo weight calculation and weight*v * fixed a bug now Photomaker V2 kinds of working * add python script for face detection (Photomaker V2 needs) * updated readme for photomaker * fixed a bug causing PMV1 crashing; both V1 and V2 work * fixed clean_input_ids for PMV2 * fixed a double counting bug in tokenize_with_trigger_token * updated photomaker readme * removed some commented code * improved reconstructing class word free prompt * changed reading id_embed to raw binary using existing load tensor function; this is more efficient than using model load and also makes it easier to work with sd server * minor clean up --------- Co-authored-by: bssrdf <bssrdf@gmail.com>
62 lines
2.2 KiB
C++
62 lines
2.2 KiB
C++
#ifndef __UTIL_H__
|
|
#define __UTIL_H__
|
|
|
|
#include <cstdint>
|
|
#include <string>
|
|
#include <vector>
|
|
|
|
#include "stable-diffusion.h"
|
|
|
|
bool ends_with(const std::string& str, const std::string& ending);
|
|
bool starts_with(const std::string& str, const std::string& start);
|
|
bool contains(const std::string& str, const std::string& substr);
|
|
|
|
std::string format(const char* fmt, ...);
|
|
|
|
void replace_all_chars(std::string& str, char target, char replacement);
|
|
|
|
bool file_exists(const std::string& filename);
|
|
bool is_directory(const std::string& path);
|
|
std::string get_full_path(const std::string& dir, const std::string& filename);
|
|
|
|
std::vector<std::string> get_files_from_dir(const std::string& dir);
|
|
|
|
std::u32string utf8_to_utf32(const std::string& utf8_str);
|
|
std::string utf32_to_utf8(const std::u32string& utf32_str);
|
|
std::u32string unicode_value_to_utf32(int unicode_value);
|
|
|
|
sd_image_t* preprocess_id_image(sd_image_t* img);
|
|
|
|
// std::string sd_basename(const std::string& path);
|
|
|
|
typedef struct {
|
|
uint32_t width;
|
|
uint32_t height;
|
|
uint32_t channel;
|
|
float* data;
|
|
} sd_image_f32_t;
|
|
|
|
void normalize_sd_image_f32_t(sd_image_f32_t image, float means[3], float stds[3]);
|
|
|
|
sd_image_f32_t sd_image_t_to_sd_image_f32_t(sd_image_t image);
|
|
|
|
sd_image_f32_t resize_sd_image_f32_t(sd_image_f32_t image, int target_width, int target_height);
|
|
|
|
sd_image_f32_t clip_preprocess(sd_image_f32_t image, int size);
|
|
|
|
std::string path_join(const std::string& p1, const std::string& p2);
|
|
std::vector<std::string> splitString(const std::string& str, char delimiter);
|
|
void pretty_progress(int step, int steps, float time);
|
|
|
|
void log_printf(sd_log_level_t level, const char* file, int line, const char* format, ...);
|
|
|
|
std::string trim(const std::string& s);
|
|
|
|
std::vector<std::pair<std::string, float>> parse_prompt_attention(const std::string& text);
|
|
|
|
#define LOG_DEBUG(format, ...) log_printf(SD_LOG_DEBUG, __FILE__, __LINE__, format, ##__VA_ARGS__)
|
|
#define LOG_INFO(format, ...) log_printf(SD_LOG_INFO, __FILE__, __LINE__, format, ##__VA_ARGS__)
|
|
#define LOG_WARN(format, ...) log_printf(SD_LOG_WARN, __FILE__, __LINE__, format, ##__VA_ARGS__)
|
|
#define LOG_ERROR(format, ...) log_printf(SD_LOG_ERROR, __FILE__, __LINE__, format, ##__VA_ARGS__)
|
|
#endif // __UTIL_H__
|