diff --git a/examples/gpu/source/main.c b/examples/gpu/source/main.c
index c42849e..4e1bb86 100644
--- a/examples/gpu/source/main.c
+++ b/examples/gpu/source/main.c
@@ -24,6 +24,12 @@
 
 #define RGBA8(r,g,b,a) ((((r)&0xFF)<<24) | (((g)&0xFF)<<16) | (((b)&0xFF)<<8) | (((a)&0xFF)<<0))
 
+//transfer from GPU output buffer to actual framebuffer flags
+#define DISPLAY_TRANSFER_FLAGS \
+	(GX_TRANSFER_FLIP_VERT(0) | GX_TRANSFER_OUT_TILED(0) | GX_TRANSFER_RAW_COPY(0) | \
+	 GX_TRANSFER_IN_FORMAT(GX_TRANSFER_FMT_RGBA8) | GX_TRANSFER_OUT_FORMAT(GX_TRANSFER_FMT_RGB8) | \
+	 GX_TRANSFER_SCALING(GX_TRANSFER_SCALE_X))
+
 //shader structure
 DVLB_s* dvlb;
 shaderProgram_s shader;
@@ -159,10 +165,28 @@ void renderFrame()
 	GPU_SetDummyTexEnv(5);
 
 	//texturing stuff
-		GPU_SetTexture(GPU_TEXUNIT0, (u32*)osConvertVirtToPhys((u32)texData),128,128,GPU_TEXTURE_MAG_FILTER(GPU_NEAREST)|GPU_TEXTURE_MIN_FILTER(GPU_NEAREST),GPU_RGBA8);
-		GPU_SetAttributeBuffers(3, (u32*)osConvertVirtToPhys((u32)texData),
-			GPU_ATTRIBFMT(0, 3, GPU_FLOAT)|GPU_ATTRIBFMT(1, 2, GPU_FLOAT)|GPU_ATTRIBFMT(2, 3, GPU_FLOAT),
-			0xFFC, 0x210, 1, (u32[]){0x00000000}, (u64[]){0x210}, (u8[]){3});
+		GPU_SetTexture(
+			GPU_TEXUNIT0, //texture unit
+			(u32*)osConvertVirtToPhys((u32)texData), //data buffer
+			128, //texture width
+			128, //texture height
+			GPU_TEXTURE_MAG_FILTER(GPU_NEAREST) | GPU_TEXTURE_MIN_FILTER(GPU_NEAREST), //texture params
+			GPU_RGBA8 //texture pixel format
+		);
+
+		GPU_SetAttributeBuffers(
+			3, //3 attributes: vertices, texcoords, and normals
+			(u32*)osConvertVirtToPhys((u32)texData), //mesh buffer
+			GPU_ATTRIBFMT(0, 3, GPU_FLOAT) | // GPU Input attribute register 0 (v0): 3 floats (position)
+			GPU_ATTRIBFMT(1, 2, GPU_FLOAT) | // GPU Input attribute register 1 (v1): 2 floats (texcoord)
+			GPU_ATTRIBFMT(2, 3, GPU_FLOAT),  // GPU Input attribute register 2 (v2): 3 floats (normal)
+			0xFFC,
+			0x210,
+			1,
+			(u32[]){0x00000000},
+			(u64[]){0x210},
+			(u8[]){3}
+		);
 
 	//setup lighting (this is specific to our shader)
 		vect3Df_s lightDir=vnormf(vect3Df(cos(lightAngle), -1.0f, sin(lightAngle)));
@@ -286,7 +310,7 @@ int main(int argc, char** argv)
 
 			//we wait for the left buffer to finish drawing
 			gspWaitForP3D();
-			GX_SetDisplayTransfer(NULL, (u32*)gpuOut, 0x019001E0, (u32*)gfxGetFramebuffer(GFX_TOP, GFX_LEFT, NULL, NULL), 0x019001E0, 0x01001000);
+			GX_SetDisplayTransfer(NULL, (u32*)gpuOut, GX_BUFFER_DIM(240*2, 400), (u32*)gfxGetFramebuffer(GFX_TOP, GFX_LEFT, NULL, NULL), GX_BUFFER_DIM(240*2, 400), DISPLAY_TRANSFER_FLAGS);
 			gspWaitForPPF();
 
 			//we draw the right buffer, wait for it to finish and then switch back to left one
@@ -299,7 +323,7 @@ int main(int argc, char** argv)
 			gspWaitForP3D();
 
 			//transfer from GPU output buffer to actual framebuffer
-			GX_SetDisplayTransfer(NULL, (u32*)gpuOut, 0x019001E0, (u32*)gfxGetFramebuffer(GFX_TOP, GFX_RIGHT, NULL, NULL), 0x019001E0, 0x01001000);
+			GX_SetDisplayTransfer(NULL, (u32*)gpuOut, GX_BUFFER_DIM(240*2, 400), (u32*)gfxGetFramebuffer(GFX_TOP, GFX_RIGHT, NULL, NULL), GX_BUFFER_DIM(240*2, 400), DISPLAY_TRANSFER_FLAGS);
 			gspWaitForPPF();
 			GPUCMD_SetBuffer(gpuCmd, gpuCmdSize, 0);
 		}else{
@@ -310,7 +334,7 @@ int main(int argc, char** argv)
 			gspWaitForP3D();
 
 			//clear the screen
-			GX_SetDisplayTransfer(NULL, (u32*)gpuOut, 0x019001E0, (u32*)gfxGetFramebuffer(GFX_TOP, GFX_LEFT, NULL, NULL), 0x019001E0, 0x01001000);
+			GX_SetDisplayTransfer(NULL, (u32*)gpuOut, GX_BUFFER_DIM(240*2, 400), (u32*)gfxGetFramebuffer(GFX_TOP, GFX_LEFT, NULL, NULL), GX_BUFFER_DIM(240*2, 400), DISPLAY_TRANSFER_FLAGS);
 			gspWaitForPPF();
 		}
 
diff --git a/libctru/include/3ds/gpu/gx.h b/libctru/include/3ds/gpu/gx.h
index 396a752..f4aa3e5 100644
--- a/libctru/include/3ds/gpu/gx.h
+++ b/libctru/include/3ds/gpu/gx.h
@@ -2,6 +2,29 @@
 
 #define GX_BUFFER_DIM(w, h) (((h)<<16)|((w)&0xFFFF))
 
+typedef enum
+{
+	GX_TRANSFER_FMT_RGBA8  = 0,
+	GX_TRANSFER_FMT_RGB8   = 1,
+	GX_TRANSFER_FMT_RGB565 = 2,
+	GX_TRANSFER_FMT_RGB5A1 = 3,
+	GX_TRANSFER_FMT_RGBA4  = 4
+} GX_TRANSFER_FORMAT;
+
+typedef enum
+{
+	GX_TRANSFER_SCALE_NO = 0,
+	GX_TRANSFER_SCALE_X  = 1,
+	GX_TRANSFER_SCALE_Y  = 2
+} GX_TRANSFER_SCALE;
+
+#define GX_TRANSFER_FLIP_VERT(x)  ((x)<<0)
+#define GX_TRANSFER_OUT_TILED(x)  ((x)<<1)
+#define GX_TRANSFER_RAW_COPY(x)   ((x)<<3)
+#define GX_TRANSFER_IN_FORMAT(x)  ((x)<<8)
+#define GX_TRANSFER_OUT_FORMAT(x) ((x)<<12)
+#define GX_TRANSFER_SCALING(x)    ((x)<<24)
+
 Result GX_RequestDma(u32* gxbuf, u32* src, u32* dst, u32 length);
 Result GX_SetCommandList_Last(u32* gxbuf, u32* buf0a, u32 buf0s, u8 flags);
 Result GX_SetMemoryFill(u32* gxbuf, u32* buf0a, u32 buf0v, u32* buf0e, u16 width0, u32* buf1a, u32 buf1v, u32* buf1e, u16 width1);
diff --git a/libctru/source/gpu/gpu.c b/libctru/source/gpu/gpu.c
index 5d8d8da..326da5c 100644
--- a/libctru/source/gpu/gpu.c
+++ b/libctru/source/gpu/gpu.c
@@ -377,21 +377,21 @@ void GPU_SetTexture(GPU_TEXUNIT unit, u32* data, u16 width, u16 height, u32 para
 	case GPU_TEXUNIT0:
 		GPUCMD_AddWrite(GPUREG_TEXUNIT0_TYPE, colorType);
 		GPUCMD_AddWrite(GPUREG_TEXUNIT0_LOC, ((u32)data)>>3);
-		GPUCMD_AddWrite(GPUREG_TEXUNIT0_DIM, (width)|(height<<16));
+		GPUCMD_AddWrite(GPUREG_TEXUNIT0_DIM, (width<<16)|height);
 		GPUCMD_AddWrite(GPUREG_TEXUNIT0_PARAM, param);
 		break;
 		
 	case GPU_TEXUNIT1:
 		GPUCMD_AddWrite(GPUREG_TEXUNIT1_TYPE, colorType);
 		GPUCMD_AddWrite(GPUREG_TEXUNIT1_LOC, ((u32)data)>>3);
-		GPUCMD_AddWrite(GPUREG_TEXUNIT1_DIM, (width)|(height<<16));
+		GPUCMD_AddWrite(GPUREG_TEXUNIT1_DIM, (width<<16)|height);
 		GPUCMD_AddWrite(GPUREG_TEXUNIT1_PARAM, param);
 		break;
 		
 	case GPU_TEXUNIT2:
 		GPUCMD_AddWrite(GPUREG_TEXUNIT2_TYPE, colorType);
 		GPUCMD_AddWrite(GPUREG_TEXUNIT2_LOC, ((u32)data)>>3);
-		GPUCMD_AddWrite(GPUREG_TEXUNIT2_DIM, (width)|(height<<16));
+		GPUCMD_AddWrite(GPUREG_TEXUNIT2_DIM, (width<<16)|height);
 		GPUCMD_AddWrite(GPUREG_TEXUNIT2_PARAM, param);
 		break;
 	}