fix: use static implementation of stb_image_resize

* Support png image and resize image with 64 pixels in img2img mode

* update the error information

---------

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

README.md

@@ -306,14 +306,14 @@ sd -m ../models/v1-5-pruned-emaonly.safetensors -p "a lovely cat" --upscale-mode
 
 #### Using PhotoMaker to personalize image generation
 
-You can use [PhotoMaker](https://github.com/TencentARC/PhotoMaker) to personalize generated images with your own ID. 
+You can use [PhotoMaker](https://github.com/TencentARC/PhotoMaker) to personalize generated images with your own ID.
 
 **NOTE**, currently PhotoMaker **ONLY** works with **SDXL** (any SDXL model files will work).
 
 Download PhotoMaker model file (in safetensor format) [here](https://huggingface.co/bssrdf/PhotoMaker). The official release of the model file (in .bin format) does not work with ```stablediffusion.cpp```.
 
-- Specify the PhotoMaker model path using the `--stacked-id-embd-dir PATH` parameter. 
-- Specify the input images path using the `--input-id-images-dir PATH` parameter. 
+- Specify the PhotoMaker model path using the `--stacked-id-embd-dir PATH` parameter.
+- Specify the input images path using the `--input-id-images-dir PATH` parameter.
   - input images **must** have the same width and height for preprocessing (to be improved)
 
 In prompt, make sure you have a class word followed by the trigger word ```"img"``` (hard-coded for now). The class word could be one of ```"man, woman, girl, boy"```. If input ID images contain asian faces, add ```Asian``` before the class
@@ -367,6 +367,12 @@ These projects wrap `stable-diffusion.cpp` for easier use in other languages/fra
 * Golang: [seasonjs/stable-diffusion](https://github.com/seasonjs/stable-diffusion)
 * C#: [DarthAffe/StableDiffusion.NET](https://github.com/DarthAffe/StableDiffusion.NET)
 
+## UIs
+
+These projects use `stable-diffusion.cpp` as a backend for their image generation.
+
+- [Jellybox](https://jellybox.com)
+
 ## Contributors
 
 Thank you to all the people who have already contributed to stable-diffusion.cpp!

examples/cli/main.cpp

@@ -17,6 +17,10 @@
 #define STB_IMAGE_WRITE_STATIC
 #include "stb_image_write.h"
 
+#define STB_IMAGE_RESIZE_IMPLEMENTATION
+#define STB_IMAGE_RESIZE_STATIC
+#include "stb_image_resize.h"
+
 const char* rng_type_to_str[] = {
     "std_default",
     "cuda",
@@ -663,21 +667,47 @@ int main(int argc, const char* argv[]) {
             fprintf(stderr, "load image from '%s' failed\n", params.input_path.c_str());
             return 1;
         }
-        if (c != 3) {
-            fprintf(stderr, "input image must be a 3 channels RGB image, but got %d channels\n", c);
+        if (c < 3) {
+            fprintf(stderr, "the number of channels for the input image must be >= 3, but got %d channels\n", c);
             free(input_image_buffer);
             return 1;
         }
-        if (params.width <= 0 || params.width % 64 != 0) {
-            fprintf(stderr, "error: the width of image must be a multiple of 64\n");
+        if (params.width <= 0) {
+            fprintf(stderr, "error: the width of image must be greater than 0\n");
             free(input_image_buffer);
             return 1;
         }
-        if (params.height <= 0 || params.height % 64 != 0) {
-            fprintf(stderr, "error: the height of image must be a multiple of 64\n");
+        if (params.height <= 0) {
+            fprintf(stderr, "error: the height of image must be greater than 0\n");
             free(input_image_buffer);
             return 1;
         }
+
+        // Resize input image ...
+        if (params.height % 64 != 0 || params.width % 64 != 0) {
+            int resized_height = params.height + (64 - params.height % 64);
+            int resized_width = params.width + (64 - params.width % 64);
+
+            uint8_t *resized_image_buffer = (uint8_t *)malloc(resized_height * resized_width * 3);
+            if (resized_image_buffer == NULL) {
+                fprintf(stderr, "error: allocate memory for resize input image\n");
+                free(input_image_buffer);
+                return 1;
+            }
+            stbir_resize(input_image_buffer, params.width, params.height, 0, 
+                resized_image_buffer, resized_width, resized_height, 0, STBIR_TYPE_UINT8, 
+                3 /*RGB channel*/, STBIR_ALPHA_CHANNEL_NONE, 0,
+                STBIR_EDGE_CLAMP, STBIR_EDGE_CLAMP,
+                STBIR_FILTER_BOX, STBIR_FILTER_BOX,
+                STBIR_COLORSPACE_SRGB, nullptr
+            );
+
+            // Save resized result
+            free(input_image_buffer);
+            input_image_buffer = resized_image_buffer;
+            params.height = resized_height;
+            params.width = resized_width;
+        }
     }
 
     sd_ctx_t* sd_ctx = new_sd_ctx(params.model_path.c_str(),