mirror of
https://github.com/leejet/stable-diffusion.cpp.git
synced 2026-07-23 11:20:53 -05:00
feat: add ltx2.3 support (#1463)
* add GemmaTokenizer * add basic ltx2.3 support * change vocab file encoding * fix ci * fix ubuntu build * add temporal tiling support * add ltx audio support * update ggml submodule url * fix generate_video * add i2v support * minify bundled Gemma tokenizer vocab sources * pass video fps into temporal rope embeddings * fix av_ca_timestep_scale_multiplier * add LTX2Scheduler support * update docs * fix ci
This commit is contained in:
@@ -68,6 +68,7 @@ enum scheduler_t {
|
||||
KL_OPTIMAL_SCHEDULER,
|
||||
LCM_SCHEDULER,
|
||||
BONG_TANGENT_SCHEDULER,
|
||||
LTX2_SCHEDULER,
|
||||
SCHEDULER_COUNT
|
||||
};
|
||||
|
||||
@@ -151,6 +152,7 @@ enum lora_apply_mode_t {
|
||||
|
||||
typedef struct {
|
||||
bool enabled;
|
||||
bool temporal_tiling;
|
||||
int tile_size_x;
|
||||
int tile_size_y;
|
||||
float target_overlap;
|
||||
@@ -173,7 +175,9 @@ typedef struct {
|
||||
const char* llm_vision_path;
|
||||
const char* diffusion_model_path;
|
||||
const char* high_noise_diffusion_model_path;
|
||||
const char* embeddings_connectors_path;
|
||||
const char* vae_path;
|
||||
const char* audio_vae_path;
|
||||
const char* taesd_path;
|
||||
const char* control_net_path;
|
||||
const sd_embedding_t* embeddings;
|
||||
@@ -210,6 +214,13 @@ typedef struct {
|
||||
const char* params_backend;
|
||||
} sd_ctx_params_t;
|
||||
|
||||
typedef struct {
|
||||
uint32_t sample_rate;
|
||||
uint32_t channels;
|
||||
uint64_t sample_count;
|
||||
float* data;
|
||||
} sd_audio_t;
|
||||
|
||||
typedef struct {
|
||||
uint32_t width;
|
||||
uint32_t height;
|
||||
@@ -365,6 +376,7 @@ typedef struct {
|
||||
float strength;
|
||||
int64_t seed;
|
||||
int video_frames;
|
||||
int fps;
|
||||
float vace_strength;
|
||||
sd_tiling_params_t vae_tiling_params;
|
||||
sd_cache_params_t cache;
|
||||
@@ -409,6 +421,7 @@ SD_API char* sd_ctx_params_to_str(const sd_ctx_params_t* sd_ctx_params);
|
||||
|
||||
SD_API sd_ctx_t* new_sd_ctx(const sd_ctx_params_t* sd_ctx_params);
|
||||
SD_API void free_sd_ctx(sd_ctx_t* sd_ctx);
|
||||
SD_API void free_sd_audio(sd_audio_t* audio);
|
||||
|
||||
SD_API void sd_sample_params_init(sd_sample_params_t* sample_params);
|
||||
SD_API char* sd_sample_params_to_str(const sd_sample_params_t* sample_params);
|
||||
@@ -421,7 +434,11 @@ SD_API char* sd_img_gen_params_to_str(const sd_img_gen_params_t* sd_img_gen_para
|
||||
SD_API sd_image_t* generate_image(sd_ctx_t* sd_ctx, const sd_img_gen_params_t* sd_img_gen_params);
|
||||
|
||||
SD_API void sd_vid_gen_params_init(sd_vid_gen_params_t* sd_vid_gen_params);
|
||||
SD_API sd_image_t* generate_video(sd_ctx_t* sd_ctx, const sd_vid_gen_params_t* sd_vid_gen_params, int* num_frames_out);
|
||||
SD_API bool generate_video(sd_ctx_t* sd_ctx,
|
||||
const sd_vid_gen_params_t* sd_vid_gen_params,
|
||||
sd_image_t** frames_out,
|
||||
int* num_frames_out,
|
||||
sd_audio_t** audio_out);
|
||||
|
||||
typedef struct upscaler_ctx_t upscaler_ctx_t;
|
||||
|
||||
|
||||
Reference in New Issue
Block a user