DarthAffe/stable-diffusion.cpp
1
0 Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-11-10 19:06:33 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: add SeedVR2 image and video upscaling (#2300)

Browse Source
This commit is contained in:
leejet authored and GitHub committed 2026-11-09 01:13:57 +08:00
1 parent abc6718455
commit cd5594e9f9
14 files changed
+1035 -89
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

examples/cli/main.cpp
+49 -23
View File
@@ -35,12 +35,13 @@ std::regex format_specifier_regex("(?:[^%]|^)(?:%%)*(%\\d{0,3}d)");
struct SDCliParams {
std::string input_frames;
int video_upscale_factor = 0;
int vsr_window_size = 16;
SDMode mode = IMG_GEN;
std::string output_path = "output.png";
int output_begin_idx = -1;
int compression_quality = 90;
int video_upscale_factor = 0;
int vsr_window_size = 16;
int vsr_temporal_chunk_size = 5;
SDMode mode = IMG_GEN;
std::string output_path = "output.png";
int output_begin_idx = -1;
int compression_quality = 90;
std::string image_path;
std::string metadata_format = "text";
@@ -66,7 +67,7 @@ struct SDCliParams {
ArgOptions options;
options.string_options = {
{"", "--input-frames", "directory of ordered RGB frames for vid_upscale", 0, &input_frames},
{"", "--input-frames", "directory of ordered RGB frames for vid_upscale (use -i for a single image)", 0, &input_frames},
{"-o",
"--output",
"path to write result image to. you can use printf-style %d format specifiers for image sequences (default: ./output.png) (eg. output_%03d.png). Single-file video outputs support .avi, .webm, and animated .webp",
@@ -95,8 +96,9 @@ struct SDCliParams {
};
options.int_options = {
{"", "--upscale-factor", "required video upscale factor (RelayVSR: 2 or 4)", &video_upscale_factor},
{"", "--upscale-factor", "required positive video upscale factor (RelayVSR: 2 or 4; SeedVR2: integer)", &video_upscale_factor},
{"", "--vsr-window-size", "RelayVSR window including both endpoints (default: 16)", &vsr_window_size},
{"", "--vsr-temporal-chunk-size", "SeedVR2 input frames per independent chunk: 1 or 4n+1 (default: 5)", &vsr_temporal_chunk_size},
{"",
"--preview-interval",
"preview interval: in each sampling pass, positive N updates every Nth denoiser step and -N previews only completed logical step N; 0 previews the final completed step of the first pass (base-resolution or high-noise). Default: 1",
@@ -227,8 +229,8 @@ struct SDCliParams {
}
bool validate() {
if (mode == VID_UPSCALE && (input_frames.empty() || video_upscale_factor <= 0 || vsr_window_size < 2)) {
LOG_ERROR("vid_upscale requires --input-frames, positive --upscale-factor, and --vsr-window-size >= 2");
if (mode == VID_UPSCALE && video_upscale_factor <= 0) {
LOG_ERROR("vid_upscale requires a positive --upscale-factor");
return false;
}
if (mode != METADATA) {
@@ -540,7 +542,9 @@ bool save_results(const SDCliParams& cli_params,
return sucessful_reults != 0;
}
if ((cli_params.mode == VID_GEN && num_results > 1) || cli_params.mode == VID_UPSCALE) {
const bool video_upscale_output = cli_params.mode == VID_UPSCALE &&
(gen_params.init_image_path.empty() || ext_lower == ".avi" || ext_lower == ".webm");
if ((cli_params.mode == VID_GEN && num_results > 1) || video_upscale_output) {
if (ext_lower != ".avi" && ext_lower != ".webp" && ext_lower != ".webm")
ext = ".avi";
std::string params = gen_params.embed_image_metadata
@@ -676,12 +680,23 @@ int main(int argc, const char* argv[]) {
}
if (cli_params.mode == VID_UPSCALE) {
if (cli_params.input_frames.empty() == gen_params.init_image_path.empty()) {
LOG_ERROR("vid_upscale requires exactly one input: -i/--init-img or --input-frames");
return 1;
}
ctx_params.prepare_backend_assignments();
if (ctx_params.diffusion_model_path.empty() || ctx_params.vae_path.empty() || gen_params.fps <= 0) {
LOG_ERROR("vid_upscale requires --diffusion-model, --vae and positive --fps");
return 1;
}
std::vector<SDImageOwner> owned_frames;
if (!load_images_from_dir(cli_params.input_frames, owned_frames) || owned_frames.empty()) {
if (!gen_params.init_image_path.empty()) {
owned_frames.emplace_back();
if (!load_sd_image_from_file(owned_frames.back().put(), gen_params.init_image_path.c_str(), 0, 0, 3)) {
LOG_ERROR("load image from '%s' failed", gen_params.init_image_path.c_str());
return 1;
}
} else if (!load_images_from_dir(cli_params.input_frames, owned_frames) || owned_frames.empty()) {
LOG_ERROR("vid_upscale input contains no readable frames");
return 1;
}
@@ -692,12 +707,22 @@ int main(int argc, const char* argv[]) {
frames.push_back(frame.get());
sd_video_upscaler_ctx_params_t params;
sd_video_upscaler_ctx_params_init(&params);
params.diffusion_model_path = ctx_params.diffusion_model_path.c_str();
params.vae_path = ctx_params.vae_path.c_str();
params.upscale_factor = cli_params.video_upscale_factor;
params.n_threads = ctx_params.n_threads;
params.backend = ctx_params.effective_backend.c_str();
params.params_backend = ctx_params.effective_params_backend.c_str();
params.diffusion_model_path = ctx_params.diffusion_model_path.c_str();
params.vae_path = ctx_params.vae_path.c_str();
params.upscale_factor = cli_params.video_upscale_factor;
params.n_threads = ctx_params.n_threads;
params.backend = ctx_params.effective_backend.c_str();
params.params_backend = ctx_params.effective_params_backend.c_str();
params.flash_attn_mode = ctx_params.flash_attn_mode.c_str();
std::string conv_direct_mode = ctx_params.conv_direct_mode;
if (conv_direct_mode.empty()) {
conv_direct_mode = "auto";
if (ctx_params.diffusion_conv_direct)
conv_direct_mode += ",diffusion=on";
if (ctx_params.vae_conv_direct)
conv_direct_mode += ",vae=on";
}
params.conv_direct_mode = conv_direct_mode.c_str();
std::unique_ptr<video_upscaler_ctx_t, decltype(&free_video_upscaler_ctx)> upscaler(
new_video_upscaler_ctx(&params),
free_video_upscaler_ctx);
@@ -706,11 +731,12 @@ int main(int argc, const char* argv[]) {
sd_video_generation_result_t* output = nullptr;
sd_video_upscale_params_t upscale_params;
sd_video_upscale_params_init(&upscale_params);
upscale_params.frames = frames.data();
upscale_params.frame_count = int(frames.size());
upscale_params.fps = gen_params.fps;
upscale_params.window_size = cli_params.vsr_window_size;
upscale_params.seed = gen_params.seed;
upscale_params.frames = frames.data();
upscale_params.frame_count = int(frames.size());
upscale_params.fps = gen_params.fps;
upscale_params.window_size = cli_params.vsr_window_size;
upscale_params.temporal_chunk_size = cli_params.vsr_temporal_chunk_size;
upscale_params.seed = gen_params.seed;
if (!upscale_video(upscaler.get(), &upscale_params, &output))
return 1;
std::string video_info = output->generation_info;
examples/common/common.cpp
+1 -1
View File
@@ -1136,7 +1136,7 @@ ArgOptions SDGenerationParams::get_options() {
&extra_ad_args},
{"-i",
"--init-img",
"path to the init image",
"path to the init image, or a single input image for vid_upscale",
0,
&init_image_path},
{"",