diff --git a/stable-diffusion.cpp b/stable-diffusion.cpp
index 074290d84..1add767b0 100644
--- a/stable-diffusion.cpp
+++ b/stable-diffusion.cpp
@@ -2076,8 +2076,9 @@ class StableDiffusionGGML {
     ggml_tensor* vae_encode(ggml_context* work_ctx, ggml_tensor* x, bool encode_video = false) {
         int64_t t0          = ggml_time_ms();
         ggml_tensor* result = nullptr;
-        int W               = x->ne[0] / get_vae_scale_factor();
-        int H               = x->ne[1] / get_vae_scale_factor();
+        const int vae_scale_factor = get_vae_scale_factor();
+        int W                      = x->ne[0] / vae_scale_factor;
+        int H                      = x->ne[1] / vae_scale_factor;
         int C               = get_latent_channel();
         if (vae_tiling_params.enabled && !encode_video) {
             // TODO wan2.2 vae support?
@@ -2113,7 +2114,7 @@ class StableDiffusionGGML {
                 auto on_tiling = [&](ggml_tensor* in, ggml_tensor* out, bool init) {
                     first_stage_model->compute(n_threads, in, false, &out, work_ctx);
                 };
-                sd_tiling_non_square(x, result, 8, tile_size_x, tile_size_y, tile_overlap, on_tiling);
+                sd_tiling_non_square(x, result, vae_scale_factor, tile_size_x, tile_size_y, tile_overlap, on_tiling);
             } else {
                 first_stage_model->compute(n_threads, x, false, &result, work_ctx);
             }
@@ -2124,7 +2125,7 @@ class StableDiffusionGGML {
                 auto on_tiling = [&](ggml_tensor* in, ggml_tensor* out, bool init) {
                     tae_first_stage->compute(n_threads, in, false, &out, nullptr);
                 };
-                sd_tiling(x, result, 8, 64, 0.5f, on_tiling);
+                sd_tiling(x, result, vae_scale_factor, 64, 0.5f, on_tiling);
             } else {
                 tae_first_stage->compute(n_threads, x, false, &result, work_ctx);
             }
@@ -2200,8 +2201,9 @@ class StableDiffusionGGML {
     }
 
     ggml_tensor* decode_first_stage(ggml_context* work_ctx, ggml_tensor* x, bool decode_video = false) {
-        int64_t W           = x->ne[0] * get_vae_scale_factor();
-        int64_t H           = x->ne[1] * get_vae_scale_factor();
+        const int vae_scale_factor = get_vae_scale_factor();
+        int64_t W                  = x->ne[0] * vae_scale_factor;
+        int64_t H                  = x->ne[1] * vae_scale_factor;
         int64_t C           = 3;
         ggml_tensor* result = nullptr;
         if (decode_video) {
@@ -2241,7 +2243,7 @@ class StableDiffusionGGML {
                 auto on_tiling = [&](ggml_tensor* in, ggml_tensor* out, bool init) {
                     first_stage_model->compute(n_threads, in, true, &out, nullptr);
                 };
-                sd_tiling_non_square(x, result, 8, tile_size_x, tile_size_y, tile_overlap, on_tiling);
+                sd_tiling_non_square(x, result, vae_scale_factor, tile_size_x, tile_size_y, tile_overlap, on_tiling);
             } else {
                 first_stage_model->compute(n_threads, x, true, &result, work_ctx);
             }
@@ -2253,7 +2255,7 @@ class StableDiffusionGGML {
                 auto on_tiling = [&](ggml_tensor* in, ggml_tensor* out, bool init) {
                     tae_first_stage->compute(n_threads, in, true, &out);
                 };
-                sd_tiling(x, result, 8, 64, 0.5f, on_tiling);
+                sd_tiling(x, result, vae_scale_factor, 64, 0.5f, on_tiling);
             } else {
                 tae_first_stage->compute(n_threads, x, true, &result);
             }