feat: add TAESD implementation - faster autoencoder (#88)

* add taesd implementation

* taesd gpu offloading

* show seed when generating image with -s -1

* less restrictive with larger images

* cuda: im2col speedup x2

* cuda: group norm speedup x90

* quantized models now works in cuda :)

* fix cal mem size

---------

Co-authored-by: leejet <leejet714@gmail.com>

stable-diffusion.h

@@ -38,6 +38,7 @@ private:
 public:
     StableDiffusion(int n_threads                = -1,
                     bool vae_decode_only         = false,
+                    std::string taesd_path       = "",
                     bool free_params_immediately = false,
                     std::string lora_model_dir   = "",
                     RNGType rng_type             = STD_DEFAULT_RNG);