mirror of
https://github.com/leejet/stable-diffusion.cpp
synced 2026-03-03 21:49:45 +01:00
a469688e30
* first efforts at implementing photomaker; lots more to do
* added PhotoMakerIDEncoder model in SD
* fixed soem bugs; now photomaker model weights can be loaded into their tensor buffers
* added input id image loading
* added preprocessing inpit id images
* finished get_num_tensors
* fixed a bug in remove_duplicates
* add a get_learned_condition_with_trigger function to do photomaker stuff
* add a convert_token_to_id function for photomaker to extract trigger word's token id
* making progress; need to implement tokenizer decoder
* making more progress; finishing vision model forward
* debugging vision_model outputs
* corrected clip vision model output
* continue making progress in id fusion process
* finished stacked id embedding; to be tested
* remove garbage file
* debuging graph compute
* more progress; now alloc buffer failed
* fixed wtype issue; input images can only be 1 because issue with transformer when batch size > 1 (to be investigated)
* added delayed subject conditioning; now photomaker runs and generates images
* fixed stat_merge_step
* added photomaker lora model (to be tested)
* reworked pmid lora
* finished applying pmid lora; to be tested
* finalized pmid lora
* add a few print tensor; tweak in sample again
* small tweak; still not getting ID faces
* fixed a bug in FuseBlock forward; also remove diag_mask op in for vision transformer; getting better results
* disable pmid lora apply for now; 1 input image seems working; > 1 not working
* turn pmid lora apply back on
* fixed a decode bug
* fixed a bug in ggml's conv_2d, and now > 1 input images working
* add style_ratio as a cli param; reworked encode with trigger for attention weights
* merge commit fixing lora free param buffer error
* change default style ratio to 10%
* added an option to offload vae decoder to CPU for mem-limited gpus
* removing image normalization step seems making ID fidelity much higher
* revert default style ratio back ro 20%
* added an option for normalizing input ID images; cleaned up debugging code
* more clean up
* fixed bugs; now failed with cuda error; likely out-of-mem on GPU
* free pmid model params when required
* photomaker working properly now after merging and adapting to GGMLBlock API
* remove tensor renaming; fixing names in the photomaker model file
* updated README.md to include instructions and notes for running PhotoMaker
* a bit clean up
* remove -DGGML_CUDA_FORCE_MMQ; more clean up and README update
* add input image requirement in README
* bring back freeing pmid lora params buffer; simply pooled output of CLIPvision
* remove MultiheadAttention2; customized MultiheadAttention
* added a WIN32 get_files_from_dir; turn off Photomakder if receiving no input images
* update docs
* fix ci error
* make stable-diffusion.h a pure c header file
This reverts commit 27887b630d.
* fix ci error
* format code
* reuse get_learned_condition
* reuse pad_tokens
* reuse CLIPVisionModel
* reuse LoraModel
* add --clip-on-cpu
* fix lora name conversion for SDXL
---------
Co-authored-by: bssrdf <bssrdf@gmail.com>
Co-authored-by: leejet <leejet714@gmail.com>
60 lines
2.0 KiB
C++
60 lines
2.0 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);
|
|
|
|
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);
|
|
|
|
#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__
|