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 Qwen Image Edit support (#877)

Browse Source 
* add ref latent support for qwen image

* optimize clip_preprocess and fix get_first_stage_encoding

* add qwen2vl vit support

* add qwen image edit support

* fix qwen image edit pipeline

* add mmproj file support

* support dynamic number of Qwen image transformer blocks

* set prompt_template_encode_start_idx every time

* to_add_out precision fix

* to_out.0 precision fix

* update docs
This commit is contained in:
leejet
2025-10-13 23:17:18 +08:00
committed by GitHub
parent c64994dc1d
commit 2e9242e37f
18 changed files with 1339 additions and 365 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
examples/cli/main.cpp
View File

@@ -62,6 +62,7 @@ struct SDParams {
std::string clip_vision_path;
std::string t5xxl_path;
std::string qwen2vl_path;
std::string qwen2vl_vision_path;
std::string diffusion_model_path;
std::string high_noise_diffusion_model_path;
std::string vae_path;
@@ -148,6 +149,7 @@ void print_params(SDParams params) {
printf(" clip_vision_path: %s\n", params.clip_vision_path.c_str());
printf(" t5xxl_path: %s\n", params.t5xxl_path.c_str());
printf(" qwen2vl_path: %s\n", params.qwen2vl_path.c_str());
printf(" qwen2vl_vision_path: %s\n", params.qwen2vl_vision_path.c_str());
printf(" diffusion_model_path: %s\n", params.diffusion_model_path.c_str());
printf(" high_noise_diffusion_model_path: %s\n", params.high_noise_diffusion_model_path.c_str());
printf(" vae_path: %s\n", params.vae_path.c_str());
@@ -220,6 +222,7 @@ void print_usage(int argc, const char* argv[]) {
printf(" --clip_vision path to the clip-vision encoder\n");
printf(" --t5xxl path to the t5xxl text encoder\n");
printf(" --qwen2vl path to the qwen2vl text encoder\n");
printf(" --qwen2vl_vision path to the qwen2vl vit\n");
printf(" --vae [VAE] path to vae\n");
printf(" --taesd [TAESD_PATH] path to taesd. Using Tiny AutoEncoder for fast decoding (low quality)\n");
printf(" --control-net [CONTROL_PATH] path to control net model\n");
@@ -490,6 +493,7 @@ void parse_args(int argc, const char** argv, SDParams& params) {
{"", "--clip_vision", "", &params.clip_vision_path},
{"", "--t5xxl", "", &params.t5xxl_path},
{"", "--qwen2vl", "", &params.qwen2vl_path},
{"", "--qwen2vl_vision", "", &params.qwen2vl_vision_path},
{"", "--diffusion-model", "", &params.diffusion_model_path},
{"", "--high-noise-diffusion-model", "", &params.high_noise_diffusion_model_path},
{"", "--vae", "", &params.vae_path},
@@ -952,7 +956,7 @@ std::string get_image_params(SDParams params, int64_t seed) {
parameter_string += " " + std::string(sd_schedule_name(params.sample_params.scheduler));
}
parameter_string += ", ";
for (const auto& te : {params.clip_l_path, params.clip_g_path, params.t5xxl_path, params.qwen2vl_path}) {
for (const auto& te : {params.clip_l_path, params.clip_g_path, params.t5xxl_path, params.qwen2vl_path, params.qwen2vl_vision_path}) {
if (!te.empty()) {
parameter_string += "TE: " + sd_basename(te) + ", ";
}
@@ -1336,6 +1340,7 @@ int main(int argc, const char* argv[]) {
params.clip_vision_path.c_str(),
params.t5xxl_path.c_str(),
params.qwen2vl_path.c_str(),
params.qwen2vl_vision_path.c_str(),
params.diffusion_model_path.c_str(),
params.high_noise_diffusion_model_path.c_str(),
params.vae_path.c_str(),