upstream-archive/stable-diffusion.cpp
1
0
Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-07-29 14:20:57 -05:00
Code Issues Packages Projects Releases Wiki Activity

added a WIN32 get_files_from_dir; turn off Photomakder if receiving no input images

Browse Source
This commit is contained in:
bssrdf
2024-02-28 16:29:32 -05:00
parent 70c3397b60
commit 16c9da0cca
3 changed files with 83 additions and 39 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
examples/cli/main.cpp
View File

@@ -706,9 +706,9 @@ int main(int argc, const char* argv[]) {
}
sd_image_t* input_image = NULL;
input_image = new sd_image_t{(uint32_t)width,
(uint32_t)height,
3,
input_image_buffer};
(uint32_t)height,
3,
input_image_buffer};
input_image = preprocess_id_image(input_image);
if(input_image == NULL){
LOG_ERROR("preprocess input id image from '%s' failed", img_file.c_str());

77
stable-diffusion.cpp
View File

@@ -1679,47 +1679,52 @@ sd_image_t* txt2img(sd_ctx_t* sd_ctx,
// ggml_tensor* class_tokens_mask = NULL;
std::vector<bool> class_tokens_mask;
if(sd_ctx->sd->stacked_id){
sd_ctx->sd->pmid_model->style_strength = style_ratio;
int32_t w = input_id_images[0]->width;
int32_t h = input_id_images[0]->height;
int32_t channels = input_id_images[0]->channel;
int32_t num_input_images = input_id_images.size();
init_img = ggml_new_tensor_4d(work_ctx, GGML_TYPE_F32, w, h, channels, num_input_images);
// TODO: move these to somewhere else and be user settable
float mean[] = {0.48145466, 0.4578275, 0.40821073};
float std[] = {0.26862954, 0.26130258, 0.27577711};
for(int i = 0; i < num_input_images; i++) {
sd_image_t* init_image = input_id_images[i];
if(normalize_input)
sd_mul_images_to_tensor(init_image->data, init_img, i, mean, std);
else
sd_mul_images_to_tensor(init_image->data, init_img, i, NULL, NULL);
}
t0 = ggml_time_ms();
auto cond_tup = sd_ctx->sd->get_learned_condition_with_trigger(work_ctx, prompt,
clip_skip, width, height, num_input_images );
prompts_embeds = std::get<0>(cond_tup);
pooled_prompts_embeds = std::get<1>(cond_tup); // [adm_in_channels, ]
class_tokens_mask = std::get<2>(cond_tup); //
if(input_id_images.size() > 0){
sd_ctx->sd->pmid_model->style_strength = style_ratio;
int32_t w = input_id_images[0]->width;
int32_t h = input_id_images[0]->height;
int32_t channels = input_id_images[0]->channel;
int32_t num_input_images = input_id_images.size();
init_img = ggml_new_tensor_4d(work_ctx, GGML_TYPE_F32, w, h, channels, num_input_images);
// TODO: move these to somewhere else and be user settable
float mean[] = {0.48145466, 0.4578275, 0.40821073};
float std[] = {0.26862954, 0.26130258, 0.27577711};
for(int i = 0; i < num_input_images; i++) {
sd_image_t* init_image = input_id_images[i];
if(normalize_input)
sd_mul_images_to_tensor(init_image->data, init_img, i, mean, std);
else
sd_mul_images_to_tensor(init_image->data, init_img, i, NULL, NULL);
}
t0 = ggml_time_ms();
auto cond_tup = sd_ctx->sd->get_learned_condition_with_trigger(work_ctx, prompt,
clip_skip, width, height, num_input_images );
prompts_embeds = std::get<0>(cond_tup);
pooled_prompts_embeds = std::get<1>(cond_tup); // [adm_in_channels, ]
class_tokens_mask = std::get<2>(cond_tup); //
prompts_embeds = sd_ctx->sd->id_encoder(work_ctx, init_img, prompts_embeds, class_tokens_mask);
t1 = ggml_time_ms();
LOG_INFO("Photomaker ID Stacking, taking %" PRId64 " ms", t1 - t0);
if (sd_ctx->sd->free_params_immediately) {
sd_ctx->sd->pmid_model->free_params_buffer();
}
// Encode input prompt without the trigger word for delayed conditioning
prompt_text_only = sd_ctx->sd->remove_trigger_from_prompt(work_ctx, prompt);
// printf("%s || %s \n", prompt.c_str(), prompt_text_only.c_str());
prompt = prompt_text_only; //
if(sample_steps < 50){
LOG_INFO("sampling steps increases from %d to 50 for PHOTOMAKER", sample_steps);
sample_steps = 50;
prompts_embeds = sd_ctx->sd->id_encoder(work_ctx, init_img, prompts_embeds, class_tokens_mask);
t1 = ggml_time_ms();
LOG_INFO("Photomaker ID Stacking, taking %" PRId64 " ms", t1 - t0);
if (sd_ctx->sd->free_params_immediately) {
sd_ctx->sd->pmid_model->free_params_buffer();
}
// Encode input prompt without the trigger word for delayed conditioning
prompt_text_only = sd_ctx->sd->remove_trigger_from_prompt(work_ctx, prompt);
// printf("%s || %s \n", prompt.c_str(), prompt_text_only.c_str());
prompt = prompt_text_only; //
if(sample_steps < 50){
LOG_INFO("sampling steps increases from %d to 50 for PHOTOMAKER", sample_steps);
sample_steps = 50;
}
}else{
LOG_WARN("Provided PhotoMaker model file, but NO input ID images");
LOG_WARN("Turn off PhotoMaker");
sd_ctx->sd->stacked_id = false;
}
}
t0 = ggml_time_ms();
auto cond_pair = sd_ctx->sd->get_learned_condition(work_ctx, prompt, clip_skip, width, height);
ggml_tensor* c = cond_pair.first;

39
util.cpp
View File

@@ -91,6 +91,45 @@ 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::vector<std::string> files;
WIN32_FIND_DATA findFileData;
HANDLE hFind;
char currentDirectory[MAX_PATH];
GetCurrentDirectory(MAX_PATH, currentDirectory);
char directoryPath[MAX_PATH]; // this is absolute path
sprintf(directoryPath, "%s\\%s\\*", currentDirectory, dir.c_str());
// Find the first file in the directory
hFind = FindFirstFile(directoryPath, &findFileData);
// Check if the directory was found
if (hFind == INVALID_HANDLE_VALUE) {
printf("Unable to find directory.\n");
return files;
}
// Loop through all files in the directory
do {
// Check if the found file is a regular file (not a directory)
if (!(findFileData.dwFileAttributes & FILE_ATTRIBUTE_DIRECTORY)) {
files.push_back(std::string(currentDirectory) + "\\" + dir + "\\" + std::string(findFileData.cFileName));
}
} while (FindNextFile(hFind, &findFileData) != 0);
// Close the handle
FindClose(hFind);
sort(files.begin(), files.end());
return files;
}
#else // Unix
#include <dirent.h>
#include <sys/stat.h>