stable_diffusion

type ContextParams struct {
	ModelPath                   string     // Full model path
	ClipLPath                   string     // CLIP-L text encoder path
	ClipGPath                   string     // CLIP-G text encoder path
	ClipVisionPath              string     // CLIP Vision encoder path
	T5XXLPath                   string     // T5-XXL text encoder path
	LLMPath                     string     // LLM text encoder path (e.g., qwenvl2.5 for qwen-image, mistral-small3.2 for flux2)
	LLMVisionPath               string     // LLM Vision encoder path
	DiffusionModelPath          string     // Standalone diffusion model path
	HighNoiseDiffusionModelPath string     // Standalone high noise diffusion model path
	VAEPath                     string     // VAE model path
	TAESDPath                   string     // TAE-SD model path, uses Tiny AutoEncoder for fast decoding (low quality)
	ControlNetPath              string     // ControlNet model path
	Embeddings                  *Embedding // Embedding information
	EmbeddingCount              uint32     // Number of embeddings
	PhotoMakerPath              string     // PhotoMaker model path
	TensorTypeRules             string     // Weight type rules per tensor pattern (e.g., "^vae\.=f16,model\.=q8_0")
	VAEDecodeOnly               bool       // Process VAE using only decode mode
	FreeParamsImmediately       bool       // Whether to free parameters immediately
	NThreads                    int32      // Number of threads to use for generation
	WType                       string     // Weight type (default: auto-detect from model file)
	RNGType                     string     // Random number generator type (default: "cuda")
	SamplerRNGType              string     // Sampler random number generator type (default: "cuda")
	Prediction                  string     // Prediction type override
	LoraApplyMode               string     // LoRA application mode (default: "auto")
	OffloadParamsToCPU          bool       // Keep weights in RAM to save VRAM, auto-load to VRAM when needed
	EnableMmap                  bool       // Whether to enable memory mapping
	KeepClipOnCPU               bool       // Keep CLIP on CPU (for low VRAM)
	KeepControlNetOnCPU         bool       // Keep ControlNet on CPU (for low VRAM)
	KeepVAEOnCPU                bool       // Keep VAE on CPU (for low VRAM)
	DiffusionFlashAttn          bool       // Use Flash attention in diffusion model (significantly reduces memory usage)
	TAEPreviewOnly              bool       // Prevent decoding final image with taesd (for preview="tae")
	DiffusionConvDirect         bool       // Use Conv2d direct in diffusion model
	VAEConvDirect               bool       // Use Conv2d direct in VAE model (should improve performance)
	CircularX                   bool       // Enable circular padding on X axis
	CircularY                   bool       // Enable circular padding on Y axis
	ForceSDXLVAConvScale        bool       // Force conv scale on SDXL VAE
	ChromaUseDitMask            bool       // Whether Chroma uses DiT mask
	ChromaUseT5Mask             bool       // Whether Chroma uses T5 mask
	ChromaT5MaskPad             int32      // Chroma T5 mask padding size
	QwenImageZeroCondT          bool       // Qwen-image zero condition T parameter
	FlowShift                   float32    // Shift value for Flow models (e.g., SD3.x or WAN)
}

type Embedding struct {
	Name string // Embedding name
	Path string // Embedding file path
}

type ImgGenParams struct {
	Loras              *Lora             // LoRA parameters
	LoraCount          uint32            // Number of LoRAs
	Prompt             string            // Prompt to render
	NegativePrompt     string            // Negative prompt
	ClipSkip           int32             // Skip last layers of CLIP network (1 = no skip, 2 = skip one layer, <=0 = not specified)
	InitImagePath      string            // Initial image path for guidance
	RefImagesPath      []string          // Array of reference image paths for Flux Kontext models
	RefImagesCount     int32             // Number of reference images
	AutoResizeRefImage bool              // Whether to auto-resize reference images
	IncreaseRefIndex   bool              // Whether to auto-increase index based on reference image list order (starting from 1)
	MaskImagePath      string            // Inpainting mask image path
	Width              int32             // Image width (pixels)
	Height             int32             // Image height (pixels)
	CfgScale           float32           // Unconditional guidance scale.
	ImageCfgScale      float32           // Image guidance scale for inpaint or instruct-pix2pix models (default: same as `CfgScale`).
	DistilledGuidance  float32           // Distilled guidance scale for models with guidance input.
	SkipLayers         []int32           // Layers to skip for SLG steps (SLG will be enabled at step int([STEPS]x[START]) and disabled at int([STEPS]x[END])).
	SkipLayerStart     float32           // SLG enabling point.
	SkipLayerEnd       float32           // SLG disabling point.
	SlgScale           float32           // Skip layer guidance (SLG) scale, only for DiT models.
	Scheduler          string            // Denoiser sigma scheduler (default: discrete).
	SampleMethod       string            // Sampling method (default: euler for Flux/SD3/Wan, euler_a otherwise).
	SampleSteps        int32             // Number of sample steps.
	Eta                float32           // Eta in DDIM, only for DDIM and TCD.
	ShiftedTimestep    int32             // Shift timestep for NitroFusion models, default: 0, recommended N for NitroSD-Realism around 250 and 500 for NitroSD-Vibrant.
	CustomSigmas       []float32         // Custom sigma values for the sampler, comma-separated (e.g. "14.61,7.8,3.5,0.0").
	Strength           float32           // Noise/denoise strength (range [0.0, 1.0])
	Seed               int64             // RNG seed (< 0 for random seed)
	BatchCount         int32             // Number of images to generate
	ControlImagePath   string            // Control condition image path for ControlNet
	ControlStrength    float32           // Strength to apply ControlNet
	PMParams           *PMParams         // PhotoMaker parameters
	VAETilingParams    sd.SDTilingParams // VAE tiling parameters for reducing memory usage
	CacheParams        sd.SDCacheParams  // Cache parameters for DiT models
}

type Lora struct {
	IsHighNoise bool    // Whether it's a high noise LoRA
	Multiplier  float32 // LoRA multiplier
	Path        string  // LoRA file path
}

type PMParams struct {
	IDImages      *sd.SDImage // ID images pointer
	IDImagesCount int32       // Number of ID images
	IDEmbedPath   string      // PhotoMaker v2 ID embedding path
	StyleStrength float32     // Strength to keep PhotoMaker input identity
}

type StableDiffusion struct {
	// contains filtered or unexported fields
}

type Upscaler struct {
	// contains filtered or unexported fields
}

type UpscalerParams struct {
	EsrganPath         string // ESRGAN model path
	OffloadParamsToCPU bool   // Whether to save parameters to CPU
	Direct             bool   // Whether to use direct mode
	NThreads           int    // Number of threads to use
	TileSize           int    // Tile size
}

type VidGenParams struct {
	Loras             *Lora    // LoRA parameters
	LoraCount         uint32   // Number of LoRAs
	Prompt            string   // Prompt to render
	NegativePrompt    string   // Negative prompt
	ClipSkip          int32    // Skip last layers of CLIP network (1 = no skip, 2 = skip one layer, <=0 = not specified)
	InitImagePath     string   // Initial image path for starting generation
	EndImagePath      string   // End image path for ending generation (required for flf2v)
	ControlFramesPath []string // Array of control frame image paths for video
	ControlFramesSize int32    // Control frame size
	Width             int32    // Video width (pixels)
	Height            int32    // Video height (pixels)

	CfgScale          float32   // Unconditional guidance scale.
	ImageCfgScale     float32   // Image guidance scale for inpaint or instruct-pix2pix models (default: same as `CfgScale`).
	DistilledGuidance float32   // Distilled guidance scale for models with guidance input.
	SkipLayers        []int32   // Layers to skip for SLG steps (SLG will be enabled at step int([STEPS]x[START]) and disabled at int([STEPS]x[END])).
	SkipLayerStart    float32   // SLG enabling point.
	SkipLayerEnd      float32   // SLG disabling point.
	SlgScale          float32   // Skip layer guidance (SLG) scale, only for DiT models.
	Scheduler         string    // Denoiser sigma scheduler (default: discrete).
	SampleMethod      string    // Sampling method (default: euler for Flux/SD3/Wan, euler_a otherwise).
	SampleSteps       int32     // Number of sample steps.
	Eta               float32   // Eta in DDIM, only for DDIM and TCD.
	ShiftedTimestep   int32     // Shift timestep for NitroFusion models, default: 0, recommended N for NitroSD-Realism around 250 and 500 for NitroSD-Vibrant.
	CustomSigmas      []float32 // Custom sigma values for the sampler, comma-separated (e.g. "14.61,7.8,3.5,0.0").

	HighNoiseCfgScale          float32   // High noise diffusion model equivalent of `cfg_scale`.
	HighNoiseImageCfgScale     float32   // High noise diffusion model equivalent of `image_cfg_scale`.
	HighNoiseDistilledGuidance float32   // High noise diffusion model equivalent of `guidance`.
	HighNoiseSkipLayers        []int32   // High noise diffusion model equivalent of `skip_layers`.
	HighNoiseSkipLayerStart    float32   // High noise diffusion model equivalent of `skip_layer_start`.
	HighNoiseSkipLayerEnd      float32   // High noise diffusion model equivalent of `skip_layer_end`.
	HighNoiseSlgScale          float32   // High noise diffusion model equivalent of `slg_scale`.
	HighNoiseScheduler         string    // High noise diffusion model equivalent of `scheduler`.
	HighNoiseSampleMethod      string    // High noise diffusion model equivalent of `sample_method`.
	HighNoiseSampleSteps       int32     // High noise diffusion model equivalent of `sample_steps` (default: -1 = auto).
	HighNoiseEta               float32   // High noise diffusion model equivalent of `eta`.
	HighNoiseShiftedTimestep   int32     // Shift timestep for NitroFusion models, default: 0, recommended N for NitroSD-Realism around 250 and 500 for NitroSD-Vibrant.
	HighNoiseCustomSigmas      []float32 // Custom sigma values for the sampler, comma-separated (e.g. "14.61,7.8,3.5,0.0").

	MOEBoundary  float32          // Timestep boundary for Wan2.2 MoE models
	Strength     float32          // Noise/denoise strength (range [0.0, 1.0])
	Seed         int64            // RNG seed (< 0 for random seed)
	VideoFrames  int32            // Number of video frames to generate
	VaceStrength float32          // Wan VACE strength
	CacheParams  sd.SDCacheParams // Cache parameters for DiT models
}