feat: add Z-Image L2P support (#2075)

This commit is contained in:
Aleksei Pakhomov authored and GitHub committed 2026-10-06 17:23:21 +08:00
1 parent b6947b8bdc
commit bbdcad48dd
10 files changed
+304 -6

No files matched your search

+7 -1
View File
@@ -107,6 +107,7 @@ const char* model_version_to_str[] = {
"ESRGAN",
"PixArt",
"Ming-Image",
"Z-Image L2P",
};
static_assert(VERSION_COUNT == sizeof(model_version_to_str) / sizeof(model_version_to_str[0]),
@@ -1376,6 +1377,7 @@ bool StableDiffusionGGML::build_denoiser() {
sd_version_is_anima(version) ||
sd_version_is_ernie_image(version) ||
sd_version_is_z_image(version) ||
sd_version_is_z_image_l2p(version) ||
version == VERSION_MING_IMAGE ||
sd_version_is_llada_image(version) ||
sd_version_is_boogu_image(version) ||
@@ -2172,7 +2174,7 @@ std::vector<float> StableDiffusionGGML::prepare_sample_timesteps(float sigma,
if (version == VERSION_HIDREAM_O1) {
return std::vector<float>{1.0f - (t / static_cast<float>(TIMESTEPS))};
}
if (sd_version_is_z_image(version) || sd_version_is_ideogram4(version) || version == VERSION_MING_IMAGE) {
if (sd_version_is_z_image(version) || sd_version_is_z_image_l2p(version) || sd_version_is_ideogram4(version) || version == VERSION_MING_IMAGE) {
return std::vector<float>{1000.f - t};
}
return std::vector<float>{t};
@@ -2762,6 +2764,8 @@ 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 (sd_version_is_z_image_l2p(version)) {
down_factor = 16;
} else if (version == VERSION_QWEN_IMAGE_2_1 || version == VERSION_MING_IMAGE || 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 {
@@ -2792,6 +2796,8 @@ int StableDiffusionGGML::get_latent_channel() {
latent_channel = 3;
} else if (sd_version_is_sensenova_u1(version)) {
latent_channel = 3;
} else if (sd_version_is_z_image_l2p(version)) {
latent_channel = 3;
} else if (sd_version_is_pid(version)) {
latent_channel = 3;
} else if (sd_version_is_sefi_image(version)) {
+14 -1
View File
@@ -37,6 +37,7 @@
#include "model/diffusion/unet.hpp"
#include "model/diffusion/wan.hpp"
#include "model/diffusion/z_image.hpp"
#include "model/diffusion/z_image_l2p.hpp"
#include "model/vae/auto_encoder_kl.hpp"
#include "model/vae/hunyuan_vae.hpp"
#include "model/vae/ltx_audio_vae.hpp"
@@ -393,6 +394,18 @@ namespace sd::model_builders {
"model.diffusion_model",
version,
weight_manager);
} else if (sd_version_is_z_image_l2p(version)) {
result.conditioner = std::make_shared<LLMEmbedder>(ctx.backends.runtime_backend(SDBackendModule::TE),
tensor_storage_map,
version,
"",
false,
weight_manager,
tokenizers);
result.diffusion = std::make_shared<ZImageL2P::ZImageL2PRunner>(ctx.backends.runtime_backend(SDBackendModule::DIFFUSION),
tensor_storage_map,
"model.diffusion_model",
weight_manager);
} else if (sd_version_is_llada_image(version)) {
result.conditioner = std::make_shared<LLaDAImageEmbedder>(ctx.backends.runtime_backend(SDBackendModule::TE),
tensor_storage_map,
@@ -613,7 +626,7 @@ namespace sd::model_builders {
}
};
if (version == VERSION_CHROMA_RADIANCE || version == VERSION_HIDREAM_O1 || sd_version_is_minit2i(version) || sd_version_is_sensenova_u1(version)) {
if (version == VERSION_CHROMA_RADIANCE || version == VERSION_HIDREAM_O1 || sd_version_is_minit2i(version) || sd_version_is_sensenova_u1(version) || sd_version_is_z_image_l2p(version)) {
LOG_INFO("using FakeVAE");
result.vae = std::make_shared<FakeVAE>(version,
ctx.backends.runtime_backend(SDBackendModule::VAE),