voice_audio_multi/include/engine/community_models/soulx_flashhead/pipeline.h
Fabio c36510c21e
Some checks failed
Linux Build / Linux cpu (push) Has been cancelled
Linux Build / Linux cpu-clang (push) Has been cancelled
Linux Build / Linux vulkan (push) Has been cancelled
mac-build / macOS CPU (push) Has been cancelled
Nix Build / Nix (cpu) (push) Has been cancelled
Nix Build / Nix (vulkan) (push) Has been cancelled
windows-build / Windows CPU (push) Has been cancelled
Initial import: audio.cpp with Orange Pi documentation
2026-11-04 19:05:22 +01:00

29 lines
945 B
C++

#pragma once
#include "engine/community_models/soulx_flashhead/assets.h"
#include "engine/framework/core/execution_context.h"
#include <cstddef>
namespace engine::community_models::soulx_flashhead {
struct GenerateOptions {
std::filesystem::path reference_image;
int64_t height = 512, width = 512, steps = 4;
uint64_t seed = 42;
float color_strength = 1, audio_guidance_scale = 3;
};
struct VideoChunk {
int64_t height = 0, width = 0, frames = 0, index = 0;
std::vector<std::byte> rgb;
};
class Pipeline {
public:
Pipeline(core::ExecutionContext & execution, std::shared_ptr<const Assets> assets, bool cuda_cudnn = false);
~Pipeline();
void begin(const GenerateOptions & options);
std::vector<VideoChunk> push(const std::vector<float> & mono16k, bool final);
void reset();
private:
struct State;
std::unique_ptr<State> state_;
};
} // namespace engine::community_models::soulx_flashhead