trending/stable-diffusion.cpp
1
0
Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-10-29 07:33:29 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: add FLUX.3 Image Klein and Klein Base support (#2143)

Browse Source
This commit is contained in:
leejet
2026-10-16 02:42:07 +08:00
committed by GitHub
parent e47426c044
commit 8cd731e7b4
15 changed files with 413 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/pipeline/diffusion_engine.cpp
+20 -1
View File
@@ -111,6 +111,7 @@ const char* model_version_to_str[] = {
"Ming-Image",
"Z-Image L2P",
"Iris-3B",
"Flux.3 Image Klein",
};
static_assert(VERSION_COUNT == sizeof(model_version_to_str) / sizeof(model_version_to_str[0]),
@@ -1514,6 +1515,9 @@ bool StableDiffusionGGML::build_denoiser() {
} else {
default_flow_shift = 3.f;
}
} else if (sd_version_is_flux3(version)) {
pred_type = FLUX_FLOW_PRED;
default_flow_shift = 6.93f;
} else if (sd_version_is_flux(version) ||
sd_version_is_flux2(version) ||
sd_version_is_longcat(version) ||
@@ -1579,7 +1583,11 @@ bool StableDiffusionGGML::build_denoiser() {
}
case FLUX_FLOW_PRED: {
LOG_INFO("running in Flux FLOW mode");
denoiser = std::make_shared<FluxFlowDenoiser>();
if (sd_version_is_flux3(version)) {
denoiser = std::make_shared<Flux3FlowDenoiser>();
} else {
denoiser = std::make_shared<FluxFlowDenoiser>();
}
break;
}
case SEFI_FLOW_PRED: {
@@ -2558,6 +2566,13 @@ sd::Tensor<float> StableDiffusionGGML::sample(const std::shared_ptr<DiffusionMod
if (sd_version_is_hunyuan_video(version) && step + 1 < sigmas.size()) {
hunyuan_timestep_r_tensor = sd::Tensor<float>::from_vector({sigmas[step + 1]});
}
sd::Tensor<float> flux3_target_timestep;
if (version == VERSION_FLUX3) {
// The sign marks intermediate evaluations; the magnitude is the one-based step.
const size_t target_index = static_cast<size_t>(std::abs(step));
GGML_ASSERT(target_index > 0 && target_index < sigmas.size());
flux3_target_timestep = sd::Tensor<float>::from_vector({sigmas[target_index]});
}
sd::Tensor<float> noised_input = x * c_in;
if (apply_denoise_mask && (version == VERSION_WAN2_2_TI2V || sd_version_is_ltxav(version) || sd_version_is_lingbot_video(version))) {
noised_input = noised_input * denoise_mask + sampling_init_latent * (1.0f - denoise_mask);
@@ -2634,6 +2649,8 @@ sd::Tensor<float> StableDiffusionGGML::sample(const std::shared_ptr<DiffusionMod
} else if (sd_version_is_flux(version) || sd_version_is_flux2(version) || sd_version_is_longcat(version) || sd_version_is_sefi_image(version)) {
diffusion_params.extra = FluxDiffusionExtra{&guidance_tensor,
local_skip_layers};
} else if (sd_version_is_flux3(version)) {
diffusion_params.extra = Flux3DiffusionExtra{flux3_target_timestep.empty() ? nullptr : &flux3_target_timestep};
} else if (version == VERSION_QWEN_IMAGE_2_1) {
diffusion_params.extra = QwenImage21DiffusionExtra{&condition.c_token_types};
} else if (sd_version_is_anima(version)) {
@@ -3180,6 +3197,8 @@ std::string StableDiffusionGGML::get_default_ref_image_preset(SDVersion version)
return "longcat";
} else if (sd_version_is_flux(version)) {
return "flux_kontext";
} else if (sd_version_is_flux3(version)) {
return "flux2";
} else if (sd_version_is_flux2(version) || sd_version_is_sefi_image(version)) {
return "flux2";
} else if (version == VERSION_QWEN_IMAGE_LAYERED) {