DarthAffe/stable-diffusion.cpp
1
0 Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-11-11 11:26:34 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: add PixArt model family support (#2047)

Browse Source
This commit is contained in:
losewayy authored and GitHub committed 2026-09-25 18:18:55 +08:00
1 parent 4c3cf7543d
commit 39ada0863b
10 files changed
+512 -5
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

src/pipeline/model_builders.cpp
+32
View File
@@ -1,5 +1,6 @@
#include "model_builders.h"
#include <cmath>
#include <cstring>
#include <utility>
@@ -28,6 +29,7 @@
#include "model/diffusion/mmdit.hpp"
#include "model/diffusion/model.hpp"
#include "model/diffusion/pid.hpp"
#include "model/diffusion/pixart.hpp"
#include "model/diffusion/qwen_image.hpp"
#include "model/diffusion/qwen_image_2_1.hpp"
#include "model/diffusion/sensenova_u1.h"
@@ -301,6 +303,19 @@ namespace sd::model_builders {
weight_manager,
sd_ctx_params->model_args);
}
} else if (version == VERSION_PIXART) {
result.conditioner = std::make_shared<T5CLIPEmbedder>(ctx.backends.runtime_backend(SDBackendModule::TE),
tensor_storage_map,
true,
0,
false,
weight_manager,
sd_ctx_params->model_args);
result.diffusion = std::make_shared<PixArt::PixArtRunner>(ctx.backends.runtime_backend(SDBackendModule::DIFFUSION),
tensor_storage_map,
"model.diffusion_model",
weight_manager,
sd_ctx_params->model_args);
} else if (sd_version_is_mage_flow(version)) {
result.conditioner = std::make_shared<LLMEmbedder>(ctx.backends.runtime_backend(SDBackendModule::TE),
tensor_storage_map,
@@ -562,6 +577,23 @@ namespace sd::model_builders {
false,
vae_version,
weight_manager);
if (sd_version_is_pixart(version)) {
// Alpha-512 and Sigma share tensor layouts; Alpha-512 needs an explicit scale override.
if (tensor_storage_map.count("model.diffusion_model.adaln_single.emb.resolution_embedder.linear_1.weight") != 0) {
model->scale_factor = 0.18215f;
}
for (const auto& [key, value] : parse_key_value_args(sd_ctx_params->model_args, "model arg")) {
if (key == "pixart_vae_scale_factor") {
float parsed = 0.f;
if (parse_strict_float(value, parsed) && std::isfinite(parsed) && parsed > 0.f) {
model->scale_factor = parsed;
} else {
LOG_WARN("ignoring invalid PixArt model arg '%s=%s'", key.c_str(), value.c_str());
}
}
}
LOG_VERBOSE("pixart: VAE scale factor = %.5f", model->scale_factor);
}
if (sd_version_is_sdxl(version) &&
(strlen(SAFE_STR(sd_ctx_params->vae_path)) == 0 || sd_ctx_params->force_sdxl_vae_conv_scale || options.external_vae_is_invalid)) {
float vae_conv_2d_scale = 1.f / 32.f;