DarthAffe/stable-diffusion.cpp
1
0
Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-09-24 20:20:37 +00:00
Code Issues Packages Projects Releases Wiki Activity

chore: format code

Browse Source
This commit is contained in:
leejet 2026-08-19 23:06:07 +08:00
parent 16304cc3fd
commit 97d2990807
6 changed files with 17 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
examples/common/common.cpp
View File

@ -1556,14 +1556,12 @@ ArgOptions SDGenerationParams::get_options() {
};
std::string sample_methods = sample_method_to_str[0];
for (int i = 1; i < SAMPLE_METHOD_COUNT; i++)
{
for (int i = 1; i < SAMPLE_METHOD_COUNT; i++) {
sample_methods += ", " + std::string(sample_method_to_str[i]);
}
std::string schedulers = scheduler_to_str[0];
for (int i = 1; i < SCHEDULER_COUNT; i++)
{
for (int i = 1; i < SCHEDULER_COUNT; i++) {
schedulers += ", " + std::string(scheduler_to_str[i]);
}
@ -1575,17 +1573,17 @@ ArgOptions SDGenerationParams::get_options() {
{"",
"--sampling-method",
"sampling method, one of [" + sample_methods + "], "
"default: euler for Flux/SD3/Wan, euler_a otherwise",
"default: euler for Flux/SD3/Wan, euler_a otherwise",
on_sample_method_arg},
{"",
"--high-noise-sampling-method",
"(high noise) sampling method, one of [" + sample_methods + "], "
"default: euler for Flux/SD3/Wan, euler_a otherwise",
"default: euler for Flux/SD3/Wan, euler_a otherwise",
on_high_noise_sample_method_arg},
{"",
"--scheduler",
"denoiser sigma scheduler, one of [" + schedulers + "], "
"alias: normal=discrete, default: model-specific",
"alias: normal=discrete, default: model-specific",
on_scheduler_arg},
{"",
"--sigmas",

6
scripts/merge_safetensors.py
View File

@ -23,16 +23,16 @@ from typing import BinaryIO
# Configuration
# -----------------------------------------------------------------------------
OUTPUT_PATH = Path(r"..\models\diffusion_models\minimax_h3_ref2va_pruned_bf16.safetensors")
OUTPUT_PATH = Path(r".minimax_h3_fl2va_pruned_bf16.safetensors")
SOURCE_RULES = [
{
"path": Path(r"..\models\diffusion_models\minimax_h3_ref2va_bf16.safetensors"),
"path": Path(r".minimax_h3_fl2va_bf16.safetensors"),
"include": [r".*"],
"exclude": [r".*adaln_proj\.linear.*", r"time_embedder.*"],
},
{
"path": Path(r"..\models\diffusion_models\minimax_h3_ref2va_pruned_int8_convrot.safetensors"),
"path": Path(r".minimax_h3_fl2va_pruned_int8_convrot.safetensors"),
"include": [r"^.*adaln_proj\.linear.*", "adaln_t_table"],
"exclude": [],
},

2
src/core/ggml_graph_cut.cpp
View File

@ -454,7 +454,7 @@ namespace sd::ggml_graph_cut {
return false;
}
return starts_with(tensor->name, GGML_RUNNER_CUT_PREFIX) &&
ends_with(tensor->name, GGML_RUNNER_CUT_SUFFIX);
ends_with(tensor->name, GGML_RUNNER_CUT_SUFFIX);
}
std::string make_graph_cut_name(const std::string& group, const std::string& output) {

2
src/model/vae/tae.hpp
View File

@ -429,7 +429,7 @@ class TinyVideoDecoder : public UnaryBlock {
bool is_wide = false;
public:
int t_upscale = 1;
int t_upscale = 1;
TinyVideoDecoder(int z_channels = 4, int patch_size = 1, std::vector<bool> time_upscale = {false, true, true}, bool is_wide = false)
: z_channels(z_channels), patch_size(patch_size), is_wide(is_wide) {
t_upscale = 1;

8
src/runtime/denoiser.hpp
View File

@ -2586,7 +2586,7 @@ static sd::Tensor<float> sample_lms(denoise_cb_t model,
// modified with "history shift" value, which seemingly needs less steps
int divisions = 1000;
int max_order = 4;
int shift = 1; // 4, 0 - original; 4, 1 - PR #1843; 3, 1 - smoother image
int shift = 1; // 4, 0 - original; 4, 1 - PR #1843; 3, 1 - smoother image
for (const auto& [key, value] : extra_sample_args) {
int parsed = 0;
if (key == "lms_max_order") {
@ -2624,7 +2624,7 @@ static sd::Tensor<float> sample_lms(denoise_cb_t model,
auto linear_multistep_coeff = [=](const int order, const int m, const int j) -> float {
if (!divisions)
return sigmas[m + 1] - sigmas[m]; // delta / 0 * 0
#define LMS_PRECISION float // when divisions > 30 millions, the double precision fixes noise
#define LMS_PRECISION float // when divisions > 30 millions, the double precision fixes noise
const LMS_PRECISION a = sigmas[m], dx = (sigmas[m + 1] - a) / divisions, s = sigmas[m - j];
const LMS_PRECISION b0 = a + 0.5f * dx; // using Riemann middle integral
LMS_PRECISION sum = 0.0f;
@ -2672,8 +2672,8 @@ static sd::Tensor<float> sample_lms(denoise_cb_t model,
int hist_max = hist.size() - 1;
for (int c = 2; c <= order; c++)
x += hist[std::min(hist_max, hist_size_p1 - c + shift)] * lms_coeff[c - 1];
// max_order == 4 => hist[] index = 2, 1, 0
// shift == 1 => hist[] index = 2, 2, 1
// max_order == 4 => hist[] index = 2, 1, 0
// shift == 1 => hist[] index = 2, 2, 1
}
if (hist_size_p1 == max_order) {
hist.erase(hist.begin());

2
src/stable-diffusion.cpp
View File

@ -2315,7 +2315,7 @@ public:
return;
}
} else if (channels == 24) {
if(sd_version_is_minimax_h3(version)){
if (sd_version_is_minimax_h3(version)) {
latent_rgb_proj = minimax_latent_rgb_proj;
latent_rgb_bias = minimax_latent_rgb_bias;
} else {