DarthAffe/stable-diffusion.cpp
1
0 Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-11-14 12:56:33 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: add MiniMax-H3-Image support (#2324)

Browse Source
This commit is contained in:
leejet authored and GitHub committed 2026-11-11 01:24:25 +08:00
1 parent f8417d02e1
commit 32d516c019
15 files changed
+436 -118
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

src/pipeline/diffusion_engine.cpp
+8 -2
View File
@@ -41,6 +41,7 @@
#include "model/audio/wav2vec2.hpp"
#include "model/diffusion/animatediff.hpp"
#include "model/diffusion/control.hpp"
#include "model/diffusion/minimax_h3.hpp"
#include "model/diffusion/model.hpp"
#include "model/diffusion/z_image.hpp"
#include "model/vae/audio_vae.hpp"
@@ -1492,6 +1493,11 @@ bool StableDiffusionGGML::build_denoiser() {
break;
}
case H3_AV_FLOW_PRED: {
if (version == VERSION_MINIMAX_H3_IMAGE) {
LOG_INFO("running in MiniMax H3 Image FLOW mode");
denoiser = std::make_shared<MiniMaxH3ImageDenoiser>(MiniMaxH3::pdd_sigmas);
break;
}
LOG_INFO("running in MiniMax H3 AV FLOW mode");
denoiser = std::make_shared<H3AVFlowDenoiser>(default_flow_shift, version == VERSION_P_H3_IMAGE ? 1.f : 3.f, get_latent_channel());
break;
@@ -2615,7 +2621,7 @@ sd::Tensor<float> StableDiffusionGGML::sample(const std::shared_ptr<DiffusionMod
condition.c_position_ids.empty() ? nullptr : &condition.c_position_ids,
condition.c_ref_audios.empty() ? nullptr : &condition.c_ref_audios,
condition.c_reference_blocks.empty() ? nullptr : &condition.c_reference_blocks,
version == VERSION_P_H3_IMAGE ? 2 : audio_length,
version == VERSION_MINIMAX_H3_IMAGE ? 0 : (version == VERSION_P_H3_IMAGE ? 2 : audio_length),
std::isfinite(active_flow_shift) ? active_flow_shift : 12.f,
version == VERSION_P_H3_IMAGE ? 1.f : 3.f,
target_index > 0 && target_index < sigmas.size() ? sigmas[target_index] : NAN};
@@ -3054,7 +3060,7 @@ sd::Tensor<float> StableDiffusionGGML::decode_first_stage(const sd::Tensor<float
return {};
}
auto decoded = first_stage_model->decode(n_threads, latents, tiling_params, decode_video, circular_x, circular_y);
if (version == VERSION_P_H3_IMAGE && !decoded.empty() && decoded.dim() == 5) {
if (sd_version_is_minimax_h3_image(version) && !decoded.empty() && decoded.dim() == 5) {
decoded = decoded.squeeze(2);
}
if (!decoded.empty() ||