upstream-archive/stable-diffusion.cpp
1
0
Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-07-29 22:30:43 -05:00
Code Issues Packages Projects Releases Wiki Activity

merged with master and resolved conflicts; adapted to GGMLBlock API

Browse Source
This commit is contained in:
bssrdf
2024-02-25 14:35:37 -05:00
parent b7a454049d 193fb620b1
commit 53beb92d2f
20 changed files with 4605 additions and 4288 deletions
Download Patch File Download Diff File Expand all files Collapse all files

118
examples/cli/main.cpp
View File

@@ -43,12 +43,14 @@ const char* schedule_str[] = {
const char* modes_str[] = {
"txt2img",
"img2img",
"img2vid",
"convert",
};
enum SDMode {
TXT2IMG,
IMG2IMG,
IMG2VID,
CONVERT,
MODE_COUNT
};
@@ -73,6 +75,7 @@ struct SDParams {
std::string prompt;
std::string negative_prompt;
float min_cfg = 1.0f;
float cfg_scale = 7.0f;
float style_ratio = 20.f;
int clip_skip = -1; // <= 0 represents unspecified
@@ -80,6 +83,11 @@ struct SDParams {
int height = 512;
int batch_count = 1;
int video_frames = 6;
int motion_bucket_id = 127;
int fps = 6;
float augmentation_level = 0.f;
sample_method_t sample_method = EULER_A;
schedule_t schedule = DEFAULT;
int sample_steps = 20;
@@ -93,6 +101,7 @@ struct SDParams {
bool normalize_input = false;
bool vae_on_cpu = false;
bool canny_preprocess = false;
int upscale_repeats = 1;
};
void print_params(SDParams params) {
@@ -118,6 +127,7 @@ void print_params(SDParams params) {
printf(" strength(control): %.2f\n", params.control_strength);
printf(" prompt: %s\n", params.prompt.c_str());
printf(" negative_prompt: %s\n", params.negative_prompt.c_str());
printf(" min_cfg: %.2f\n", params.min_cfg);
printf(" cfg_scale: %.2f\n", params.cfg_scale);
printf(" clip_skip: %d\n", params.clip_skip);
printf(" width: %d\n", params.width);
@@ -130,6 +140,7 @@ void print_params(SDParams params) {
printf(" seed: %ld\n", params.seed);
printf(" batch_count: %d\n", params.batch_count);
printf(" vae_tiling: %s\n", params.vae_tiling ? "true" : "false");
printf(" upscale_repeats: %d\n", params.upscale_repeats);
}
void print_usage(int argc, const char* argv[]) {
@@ -149,6 +160,7 @@ void print_usage(int argc, const char* argv[]) {
printf(" --input-id-images-dir [DIR] path to PHOTOMAKER input id images dir.\n");
printf(" --normalize-input normalize PHOTOMAKER input id images\n");
printf(" --upscale-model [ESRGAN_PATH] path to esrgan model. Upscale images after generate, just RealESRGAN_x4plus_anime_6B supported by now.\n");
printf(" --upscale-repeats Run the ESRGAN upscaler this many times (default 1)\n");
printf(" --type [TYPE] weight type (f32, f16, q4_0, q4_1, q5_0, q5_1, q8_0)\n");
printf(" If not specified, the default is the type of the weight file.\n");
printf(" --lora-model-dir [DIR] lora model directory\n");
@@ -204,7 +216,8 @@ void parse_args(int argc, const char** argv, SDParams& params) {
}
}
if (mode_found == -1) {
fprintf(stderr, "error: invalid mode %s, must be one of [txt2img, img2img]\n",
fprintf(stderr,
"error: invalid mode %s, must be one of [txt2img, img2img, img2vid, convert]\n",
mode_selected);
exit(1);
}
@@ -312,6 +325,16 @@ void parse_args(int argc, const char** argv, SDParams& params) {
break;
}
params.prompt = argv[i];
} else if (arg == "--upscale-repeats") {
if (++i >= argc) {
invalid_arg = true;
break;
}
params.upscale_repeats = std::stoi(argv[i]);
if (params.upscale_repeats < 1) {
fprintf(stderr, "error: upscale multiplier must be at least 1\n");
exit(1);
}
} else if (arg == "-n" || arg == "--negative-prompt") {
if (++i >= argc) {
invalid_arg = true;
@@ -456,7 +479,7 @@ void parse_args(int argc, const char** argv, SDParams& params) {
params.n_threads = get_num_physical_cores();
}
if (params.mode != CONVERT && params.prompt.length() == 0) {
if (params.mode != CONVERT && params.mode != IMG2VID && params.prompt.length() == 0) {
fprintf(stderr, "error: the following arguments are required: prompt\n");
print_usage(argc, argv);
exit(1);
@@ -468,7 +491,7 @@ void parse_args(int argc, const char** argv, SDParams& params) {
exit(1);
}
if (params.mode == IMG2IMG && params.input_path.length() == 0) {
if ((params.mode == IMG2IMG || params.mode == IMG2VID) && params.input_path.length() == 0) {
fprintf(stderr, "error: when using the img2img mode, the following arguments are required: init-img\n");
print_usage(argc, argv);
exit(1);
@@ -575,9 +598,14 @@ int main(int argc, const char* argv[]) {
}
}
if (params.mode == IMG2VID) {
fprintf(stderr, "SVD support is broken, do not use it!!!\n");
return 1;
}
bool vae_decode_only = true;
uint8_t* input_image_buffer = NULL;
if (params.mode == IMG2IMG) {
if (params.mode == IMG2IMG || params.mode == IMG2VID) {
vae_decode_only = false;
int c = 0;
@@ -692,19 +720,57 @@ int main(int argc, const char* argv[]) {
3,
input_image_buffer};
results = img2img(sd_ctx,
input_image,
params.prompt.c_str(),
params.negative_prompt.c_str(),
params.clip_skip,
params.cfg_scale,
params.width,
params.height,
params.sample_method,
params.sample_steps,
params.strength,
params.seed,
params.batch_count);
if (params.mode == IMG2VID) {
results = img2vid(sd_ctx,
input_image,
params.width,
params.height,
params.video_frames,
params.motion_bucket_id,
params.fps,
params.augmentation_level,
params.min_cfg,
params.cfg_scale,
params.sample_method,
params.sample_steps,
params.strength,
params.seed);
if (results == NULL) {
printf("generate failed\n");
free_sd_ctx(sd_ctx);
return 1;
}
size_t last = params.output_path.find_last_of(".");
std::string dummy_name = last != std::string::npos ? params.output_path.substr(0, last) : params.output_path;
for (int i = 0; i < params.video_frames; i++) {
if (results[i].data == NULL) {
continue;
}
std::string final_image_path = i > 0 ? dummy_name + "_" + std::to_string(i + 1) + ".png" : dummy_name + ".png";
stbi_write_png(final_image_path.c_str(), results[i].width, results[i].height, results[i].channel,
results[i].data, 0, get_image_params(params, params.seed + i).c_str());
printf("save result image to '%s'\n", final_image_path.c_str());
free(results[i].data);
results[i].data = NULL;
}
free(results);
free_sd_ctx(sd_ctx);
return 0;
} else {
results = img2img(sd_ctx,
input_image,
params.prompt.c_str(),
params.negative_prompt.c_str(),
params.clip_skip,
params.cfg_scale,
params.width,
params.height,
params.sample_method,
params.sample_steps,
params.strength,
params.seed,
params.batch_count);
}
}
if (results == NULL) {
@@ -714,7 +780,7 @@ int main(int argc, const char* argv[]) {
}
int upscale_factor = 4; // unused for RealESRGAN_x4plus_anime_6B.pth
if (params.esrgan_path.size() > 0) {
if (params.esrgan_path.size() > 0 && params.upscale_repeats > 0) {
upscaler_ctx_t* upscaler_ctx = new_upscaler_ctx(params.esrgan_path.c_str(),
params.n_threads,
params.wtype);
@@ -726,13 +792,17 @@ int main(int argc, const char* argv[]) {
if (results[i].data == NULL) {
continue;
}
sd_image_t upscaled_image = upscale(upscaler_ctx, results[i], upscale_factor);
if (upscaled_image.data == NULL) {
printf("upscale failed\n");
continue;
sd_image_t current_image = results[i];
for (int u = 0; u < params.upscale_repeats; ++u) {
sd_image_t upscaled_image = upscale(upscaler_ctx, current_image, upscale_factor);
if (upscaled_image.data == NULL) {
printf("upscale failed\n");
break;
}
free(current_image.data);
current_image = upscaled_image;
}
free(results[i].data);
results[i] = upscaled_image;
results[i] = current_image; // Set the final upscaled image as the result
}
}
}