upstream-archive/stable-diffusion.cpp
1
0
Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-07-23 11:20:53 -05:00
Code Issues Packages Projects Releases Wiki Activity

feat: add Instruct-Pix2pix/CosXL-Edit support (#679)

Browse Source 
* Instruct-p2p support

* support 2 conditionings cfg

* Do not re-encode the exact same image twice

* fixes for 2-cfg

* Fix pix2pix latent inputs + improve inpainting a bit + fix naming

* prepare for other pix2pix-like models

* Support sdxl ip2p

* fix reference image embeddings

* Support 2-cond cfg properly in cli

* fix typo in help

* Support masks for ip2p models

* unify code style

* delete unused code

* use edit mode

* add img_cond

* format code

---------

Co-authored-by: leejet <leejet714@gmail.com>
This commit is contained in:
stduhpf
2025-07-12 09:36:45 +02:00
committed by GitHub
parent 6d84a30c66
commit a772dca27a
6 changed files with 242 additions and 197 deletions
Download Patch File Download Diff File Expand all files Collapse all files

78
examples/cli/main.cpp
View File

@@ -97,15 +97,16 @@ struct SDParams {
std::string prompt;
std::string negative_prompt;
float min_cfg = 1.0f;
float cfg_scale = 7.0f;
float guidance = 3.5f;
float eta = 0.f;
float style_ratio = 20.f;
int clip_skip = -1; // <= 0 represents unspecified
int width = 512;
int height = 512;
int batch_count = 1;
float min_cfg = 1.0f;
float cfg_scale = 7.0f;
float img_cfg_scale = INFINITY;
float guidance = 3.5f;
float eta = 0.f;
float style_ratio = 20.f;
int clip_skip = -1; // <= 0 represents unspecified
int width = 512;
int height = 512;
int batch_count = 1;
int video_frames = 6;
int motion_bucket_id = 127;
@@ -176,6 +177,7 @@ void print_params(SDParams params) {
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(" img_cfg_scale: %.2f\n", params.img_cfg_scale);
printf(" slg_scale: %.2f\n", params.slg_scale);
printf(" guidance: %.2f\n", params.guidance);
printf(" eta: %.2f\n", params.eta);
@@ -234,7 +236,8 @@ void print_usage(int argc, const char* argv[]) {
printf(" -p, --prompt [PROMPT] the prompt to render\n");
printf(" -n, --negative-prompt PROMPT the negative prompt (default: \"\")\n");
printf(" --cfg-scale SCALE unconditional guidance scale: (default: 7.0)\n");
printf(" --guidance SCALE guidance scale for img2img (default: 3.5)\n");
printf(" --img-cfg-scale SCALE image guidance scale for inpaint or instruct-pix2pix models: (default: same as --cfg-scale)\n");
printf(" --guidance SCALE distilled guidance scale for models with guidance input (default: 3.5)\n");
printf(" --slg-scale SCALE skip layer guidance (SLG) scale, only for DiT models: (default: 0)\n");
printf(" 0 means disabled, a value of 2.5 is nice for sd3.5 medium\n");
printf(" --eta SCALE eta in DDIM, only for DDIM and TCD: (default: 0)\n");
@@ -470,6 +473,12 @@ void parse_args(int argc, const char** argv, SDParams& params) {
break;
}
params.cfg_scale = std::stof(argv[i]);
} else if (arg == "--img-cfg-scale") {
if (++i >= argc) {
invalid_arg = true;
break;
}
params.img_cfg_scale = std::stof(argv[i]);
} else if (arg == "--guidance") {
if (++i >= argc) {
invalid_arg = true;
@@ -755,6 +764,10 @@ void parse_args(int argc, const char** argv, SDParams& params) {
params.output_path = "output.gguf";
}
}
if (!isfinite(params.img_cfg_scale)) {
params.img_cfg_scale = params.cfg_scale;
}
}
static std::string sd_basename(const std::string& path) {
@@ -849,6 +862,18 @@ int main(int argc, const char* argv[]) {
parse_args(argc, argv, params);
sd_guidance_params_t guidance_params = {params.cfg_scale,
params.img_cfg_scale,
params.min_cfg,
params.guidance,
{
params.skip_layers.data(),
params.skip_layers.size(),
params.skip_layer_start,
params.skip_layer_end,
params.slg_scale,
}};
sd_set_log_callback(sd_log_cb, (void*)&params);
if (params.verbose) {
@@ -1041,8 +1066,7 @@ int main(int argc, const char* argv[]) {
params.prompt.c_str(),
params.negative_prompt.c_str(),
params.clip_skip,
params.cfg_scale,
params.guidance,
guidance_params,
params.eta,
params.width,
params.height,
@@ -1054,12 +1078,7 @@ int main(int argc, const char* argv[]) {
params.control_strength,
params.style_ratio,
params.normalize_input,
params.input_id_images_path.c_str(),
params.skip_layers.data(),
params.skip_layers.size(),
params.slg_scale,
params.skip_layer_start,
params.skip_layer_end);
params.input_id_images_path.c_str());
} else if (params.mode == IMG2IMG || params.mode == IMG2VID) {
sd_image_t input_image = {(uint32_t)params.width,
(uint32_t)params.height,
@@ -1075,8 +1094,7 @@ int main(int argc, const char* argv[]) {
params.motion_bucket_id,
params.fps,
params.augmentation_level,
params.min_cfg,
params.cfg_scale,
guidance_params,
params.sample_method,
params.sample_steps,
params.strength,
@@ -1109,8 +1127,7 @@ int main(int argc, const char* argv[]) {
params.prompt.c_str(),
params.negative_prompt.c_str(),
params.clip_skip,
params.cfg_scale,
params.guidance,
guidance_params,
params.eta,
params.width,
params.height,
@@ -1123,12 +1140,7 @@ int main(int argc, const char* argv[]) {
params.control_strength,
params.style_ratio,
params.normalize_input,
params.input_id_images_path.c_str(),
params.skip_layers.data(),
params.skip_layers.size(),
params.slg_scale,
params.skip_layer_start,
params.skip_layer_end);
params.input_id_images_path.c_str());
}
} else { // EDIT
results = edit(sd_ctx,
@@ -1137,25 +1149,19 @@ int main(int argc, const char* argv[]) {
params.prompt.c_str(),
params.negative_prompt.c_str(),
params.clip_skip,
params.cfg_scale,
params.guidance,
guidance_params,
params.eta,
params.width,
params.height,
params.sample_method,
params.sample_steps,
params.strength,
params.seed,
params.batch_count,
control_image,
params.control_strength,
params.style_ratio,
params.normalize_input,
params.skip_layers.data(),
params.skip_layers.size(),
params.slg_scale,
params.skip_layer_start,
params.skip_layer_end);
params.input_id_images_path.c_str());
}
if (results == NULL) {