trending/stable-diffusion.cpp
1
0
Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-10-27 07:14:04 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: add PixArt model family support (#2047)

Browse Source
This commit is contained in:
losewayy
2026-09-25 18:18:55 +08:00
committed by GitHub
parent 4c3cf7543d
commit 39ada0863b
10 changed files with 512 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/pipeline/diffusion_engine.cpp
+20 -1
View File
@@ -105,6 +105,7 @@ const char* model_version_to_str[] = {
"SenseNova U1.5",
"LLaDA-Image",
"ESRGAN",
"PixArt",
};
static_assert(VERSION_COUNT == sizeof(model_version_to_str) / sizeof(model_version_to_str[0]),
@@ -125,6 +126,18 @@ void calculate_alphas_cumprod(float* alphas_cumprod,
}
}
void calculate_alphas_cumprod_linear_beta(float* alphas_cumprod,
float beta_start,
float beta_end,
int timesteps = TIMESTEPS) {
float product = 1.0f;
for (int i = 0; i < timesteps; i++) {
float beta = beta_start + (beta_end - beta_start) * ((float)i / (timesteps - 1));
product *= 1.0f - beta;
alphas_cumprod[i] = product;
}
}
template <typename T, typename = void>
struct has_set_runtime_backends : std::false_type {};
template <typename T>
@@ -666,6 +679,10 @@ void StableDiffusionGGML::refresh_compvis_denoiser_sigmas() {
std::vector<float> alphas_cumprod(TIMESTEPS);
if (file_alphas_cumprod.size() == TIMESTEPS) {
alphas_cumprod = file_alphas_cumprod;
} else if (sd_version_is_pixart(version)) {
// PixArt checkpoints train with a linear beta schedule (0.0001 -> 0.02)
// instead of the scaled_linear schedule used by SD1.x/SDXL.
calculate_alphas_cumprod_linear_beta(alphas_cumprod.data(), 0.0001f, 0.02f);
} else {
calculate_alphas_cumprod(alphas_cumprod.data());
}
@@ -2731,7 +2748,7 @@ int StableDiffusionGGML::get_diffusion_model_down_factor() {
if (sd_version_is_dit(version)) {
if (sd_version_is_sensenova_u1(version)) {
down_factor = 32;
} else if (version == VERSION_QWEN_IMAGE_2_1 || sd_version_is_wan(version) || sd_version_is_lingbot_video(version) || sd_version_is_minimax_h3(version)) {
} else if (version == VERSION_QWEN_IMAGE_2_1 || sd_version_is_wan(version) || sd_version_is_lingbot_video(version) || sd_version_is_minimax_h3(version) || sd_version_is_pixart(version)) {
down_factor = 2;
} else {
down_factor = 1;
@@ -2769,6 +2786,8 @@ int StableDiffusionGGML::get_latent_channel() {
latent_channel = 128;
} else if (sd_version_is_mage_flow(version)) {
latent_channel = 128;
} else if (sd_version_is_pixart(version)) {
latent_channel = 4;
} else {
latent_channel = 16;
}