diff --git a/GPU/Directx9/DepalettizeShaderDX9.cpp b/GPU/Directx9/DepalettizeShaderDX9.cpp
index 8cfc8cb7de..a85f6282db 100644
--- a/GPU/Directx9/DepalettizeShaderDX9.cpp
+++ b/GPU/Directx9/DepalettizeShaderDX9.cpp
@@ -20,7 +20,6 @@
 #include "base/logging.h"
 #include "Common/Log.h"
 #include "Core/Reporting.h"
-#include "GPU/GPUState.h"
 #include "GPU/Directx9/TextureCacheDX9.h"
 #include "GPU/Directx9/DepalettizeShaderDX9.h"
 #include "GPU/Common/DepalettizeShaderCommon.h"
@@ -64,13 +63,12 @@ DepalShaderCacheDX9::~DepalShaderCacheDX9() {
 	}
 }
 
-u32 DepalShaderCacheDX9::GenerateShaderID(GEBufferFormat pixelFormat) {
-	return (gstate.clutformat & 0xFFFFFF) | (pixelFormat << 24);
+u32 DepalShaderCacheDX9::GenerateShaderID(GEPaletteFormat clutFormat, GEBufferFormat pixelFormat) {
+	return (clutFormat & 0xFFFFFF) | (pixelFormat << 24);
 }
 
-LPDIRECT3DTEXTURE9 DepalShaderCacheDX9::GetClutTexture(const u32 clutID, u32 *rawClut) {
-	GEPaletteFormat palFormat = gstate.getClutPaletteFormat();
-	const u32 realClutID = clutID ^ palFormat;
+LPDIRECT3DTEXTURE9 DepalShaderCacheDX9::GetClutTexture(GEPaletteFormat clutFormat, const u32 clutID, u32 *rawClut) {
+	const u32 realClutID = clutID ^ clutFormat;
 
 	auto oldtex = texCache_.find(realClutID);
 	if (oldtex != texCache_.end()) {
@@ -78,8 +76,8 @@ LPDIRECT3DTEXTURE9 DepalShaderCacheDX9::GetClutTexture(const u32 clutID, u32 *ra
 		return oldtex->second->texture;
 	}
 
-	D3DFORMAT dstFmt = DX9::getClutDestFormat(palFormat);
-	int texturePixels = palFormat == GE_CMODE_32BIT_ABGR8888 ? 256 : 512;
+	D3DFORMAT dstFmt = DX9::getClutDestFormat(clutFormat);
+	int texturePixels = clutFormat == GE_CMODE_32BIT_ABGR8888 ? 256 : 512;
 
 	DepalTextureDX9 *tex = new DepalTextureDX9();
 
@@ -144,8 +142,8 @@ void DepalShaderCacheDX9::Decimate() {
 	}
 }
 
-LPDIRECT3DPIXELSHADER9 DepalShaderCacheDX9::GetDepalettizePixelShader(GEBufferFormat pixelFormat) {
-	u32 id = GenerateShaderID(pixelFormat);
+LPDIRECT3DPIXELSHADER9 DepalShaderCacheDX9::GetDepalettizePixelShader(GEPaletteFormat clutFormat, GEBufferFormat pixelFormat) {
+	u32 id = GenerateShaderID(clutFormat, pixelFormat);
 
 	auto shader = cache_.find(id);
 	if (shader != cache_.end()) {
diff --git a/GPU/Directx9/DepalettizeShaderDX9.h b/GPU/Directx9/DepalettizeShaderDX9.h
index 55a4ae7911..7cdcb9413f 100644
--- a/GPU/Directx9/DepalettizeShaderDX9.h
+++ b/GPU/Directx9/DepalettizeShaderDX9.h
@@ -42,14 +42,14 @@ public:
 	~DepalShaderCacheDX9();
 
 	// This also uploads the palette and binds the correct texture.
-	LPDIRECT3DPIXELSHADER9 GetDepalettizePixelShader(GEBufferFormat pixelFormat);
+	LPDIRECT3DPIXELSHADER9 GetDepalettizePixelShader(GEPaletteFormat clutFormat, GEBufferFormat pixelFormat);
 	LPDIRECT3DVERTEXSHADER9 GetDepalettizeVertexShader() { return vertexShader_; }
-	LPDIRECT3DTEXTURE9 GetClutTexture(const u32 clutHash, u32 *rawClut);
+	LPDIRECT3DTEXTURE9 GetClutTexture(GEPaletteFormat clutFormat, const u32 clutHash, u32 *rawClut);
 	void Clear();
 	void Decimate();
 
 private:
-	u32 GenerateShaderID(GEBufferFormat pixelFormat);
+	u32 GenerateShaderID(GEPaletteFormat clutFormat, GEBufferFormat pixelFormat);
 
 	LPDIRECT3DVERTEXSHADER9 vertexShader_;
 	std::map<u32, DepalShaderDX9 *> cache_;
diff --git a/GPU/Directx9/TextureCacheDX9.cpp b/GPU/Directx9/TextureCacheDX9.cpp
index 0d3e2f1b6f..5c74e097a2 100644
--- a/GPU/Directx9/TextureCacheDX9.cpp
+++ b/GPU/Directx9/TextureCacheDX9.cpp
@@ -911,13 +911,15 @@ void TextureCacheDX9::SetTextureFramebuffer(TexCacheEntry *entry, VirtualFramebu
 	framebuffer->usageFlags |= FB_USAGE_TEXTURE;
 	bool useBufferedRendering = g_Config.iRenderingMode != FB_NON_BUFFERED_MODE;
 	if (useBufferedRendering) {
+		const GEPaletteFormat clutFormat = gstate.getClutPaletteFormat();
+
 		LPDIRECT3DPIXELSHADER9 pshader = nullptr;
 		if ((entry->status & TexCacheEntry::STATUS_DEPALETTIZE) && !g_Config.bDisableSlowFramebufEffects) {
-			pshader = depalShaderCache_->GetDepalettizePixelShader(framebuffer->drawnFormat);
+			pshader = depalShaderCache_->GetDepalettizePixelShader(clutFormat, framebuffer->drawnFormat);
 		}
 
 		if (pshader) {
-			LPDIRECT3DTEXTURE9 clutTexture = depalShaderCache_->GetClutTexture(clutHash_, clutBuf_);
+			LPDIRECT3DTEXTURE9 clutTexture = depalShaderCache_->GetClutTexture(clutFormat, clutHash_, clutBuf_);
 
 			FBO *depalFBO = framebufferManager_->GetTempFBO(framebuffer->renderWidth, framebuffer->renderHeight, FBO_8888);
 			fbo_bind_as_render_target(depalFBO);
@@ -974,11 +976,10 @@ void TextureCacheDX9::SetTextureFramebuffer(TexCacheEntry *entry, VirtualFramebu
 			dxstate.Restore();
 			dxstate.viewport.restore();
 
-			const GEPaletteFormat clutFormat = gstate.getClutPaletteFormat();
 			const u32 bytesPerColor = clutFormat == GE_CMODE_32BIT_ABGR8888 ? sizeof(u32) : sizeof(u16);
 			const u32 clutTotalColors = clutMaxBytes_ / bytesPerColor;
 
-			TexCacheEntry::Status alphaStatus = CheckAlpha(clutBuf_, getClutDestFormat(gstate.getClutPaletteFormat()), clutTotalColors, clutTotalColors, 1);
+			TexCacheEntry::Status alphaStatus = CheckAlpha(clutBuf_, getClutDestFormat(clutFormat), clutTotalColors, clutTotalColors, 1);
 			gstate_c.textureFullAlpha = alphaStatus == TexCacheEntry::STATUS_ALPHA_FULL;
 			gstate_c.textureSimpleAlpha = alphaStatus == TexCacheEntry::STATUS_ALPHA_SIMPLE;
 		} else {
diff --git a/GPU/GLES/DepalettizeShader.cpp b/GPU/GLES/DepalettizeShader.cpp
index 111a7a06bf..1a2859aa2c 100644
--- a/GPU/GLES/DepalettizeShader.cpp
+++ b/GPU/GLES/DepalettizeShader.cpp
@@ -21,7 +21,6 @@
 #include "Common/Log.h"
 #include "Core/Reporting.h"
 #include "DepalettizeShader.h"
-#include "GPU/GPUState.h"
 #include "GPU/GLES/TextureCache.h"
 #include "GPU/Common/DepalettizeShaderCommon.h"
 
@@ -121,13 +120,12 @@ bool DepalShaderCache::CreateVertexShader() {
 	return !vertexShaderFailed_;
 }
 
-u32 DepalShaderCache::GenerateShaderID(GEBufferFormat pixelFormat) {
+u32 DepalShaderCache::GenerateShaderID(GEPaletteFormat clutFormat, GEBufferFormat pixelFormat) {
 	return (gstate.clutformat & 0xFFFFFF) | (pixelFormat << 24);
 }
 
-GLuint DepalShaderCache::GetClutTexture(const u32 clutID, u32 *rawClut) {
-	GEPaletteFormat palFormat = gstate.getClutPaletteFormat();
-	const u32 realClutID = clutID ^ palFormat;
+GLuint DepalShaderCache::GetClutTexture(GEPaletteFormat clutFormat, const u32 clutID, u32 *rawClut) {
+	const u32 realClutID = clutID ^ clutFormat;
 
 	auto oldtex = texCache_.find(realClutID);
 	if (oldtex != texCache_.end()) {
@@ -135,8 +133,8 @@ GLuint DepalShaderCache::GetClutTexture(const u32 clutID, u32 *rawClut) {
 		return oldtex->second->texture;
 	}
 
-	GLuint dstFmt = getClutDestFormat(palFormat);
-	int texturePixels = palFormat == GE_CMODE_32BIT_ABGR8888 ? 256 : 512;
+	GLuint dstFmt = getClutDestFormat(clutFormat);
+	int texturePixels = clutFormat == GE_CMODE_32BIT_ABGR8888 ? 256 : 512;
 
 	bool useBGRA = UseBGRA8888() && dstFmt == GL_UNSIGNED_BYTE;
 
@@ -194,8 +192,8 @@ void DepalShaderCache::Decimate() {
 	}
 }
 
-DepalShader *DepalShaderCache::GetDepalettizeShader(GEBufferFormat pixelFormat) {
-	u32 id = GenerateShaderID(pixelFormat);
+DepalShader *DepalShaderCache::GetDepalettizeShader(GEPaletteFormat clutFormat, GEBufferFormat pixelFormat) {
+	u32 id = GenerateShaderID(clutFormat, pixelFormat);
 
 	auto shader = cache_.find(id);
 	if (shader != cache_.end()) {
diff --git a/GPU/GLES/DepalettizeShader.h b/GPU/GLES/DepalettizeShader.h
index 60a80fdf59..82479b8cff 100644
--- a/GPU/GLES/DepalettizeShader.h
+++ b/GPU/GLES/DepalettizeShader.h
@@ -42,13 +42,13 @@ public:
 	~DepalShaderCache();
 
 	// This also uploads the palette and binds the correct texture.
-	DepalShader *GetDepalettizeShader(GEBufferFormat pixelFormat);
-	GLuint GetClutTexture(const u32 clutHash, u32 *rawClut);
+	DepalShader *GetDepalettizeShader(GEPaletteFormat clutFormat, GEBufferFormat pixelFormat);
+	GLuint GetClutTexture(GEPaletteFormat clutFormat, const u32 clutHash, u32 *rawClut);
 	void Clear();
 	void Decimate();
 
 private:
-	u32 GenerateShaderID(GEBufferFormat pixelFormat);
+	u32 GenerateShaderID(GEPaletteFormat clutFormat, GEBufferFormat pixelFormat);
 	bool CreateVertexShader();
 
 	bool useGL3_;
diff --git a/GPU/GLES/TextureCache.cpp b/GPU/GLES/TextureCache.cpp
index 6c32f3eb34..7d4bb76130 100644
--- a/GPU/GLES/TextureCache.cpp
+++ b/GPU/GLES/TextureCache.cpp
@@ -980,12 +980,13 @@ void TextureCache::SetTextureFramebuffer(TexCacheEntry *entry, VirtualFramebuffe
 	framebuffer->usageFlags |= FB_USAGE_TEXTURE;
 	bool useBufferedRendering = g_Config.iRenderingMode != FB_NON_BUFFERED_MODE;
 	if (useBufferedRendering) {
+		const GEPaletteFormat clutFormat = gstate.getClutPaletteFormat();
 		DepalShader *depal = nullptr;
 		if ((entry->status & TexCacheEntry::STATUS_DEPALETTIZE) && !g_Config.bDisableSlowFramebufEffects) {
-			depal = depalShaderCache_->GetDepalettizeShader(framebuffer->drawnFormat);
+			depal = depalShaderCache_->GetDepalettizeShader(clutFormat, framebuffer->drawnFormat);
 		}
 		if (depal) {
-			GLuint clutTexture = depalShaderCache_->GetClutTexture(clutHash_, clutBuf_);
+			GLuint clutTexture = depalShaderCache_->GetClutTexture(clutFormat, clutHash_, clutBuf_);
 			FBO *depalFBO = framebufferManager_->GetTempFBO(framebuffer->renderWidth, framebuffer->renderHeight, FBO_8888);
 			fbo_bind_as_render_target(depalFBO);
 			static const float pos[12] = {
@@ -1040,11 +1041,10 @@ void TextureCache::SetTextureFramebuffer(TexCacheEntry *entry, VirtualFramebuffe
 			glstate.Restore();
 			framebufferManager_->RebindFramebuffer();
 
-			const GEPaletteFormat clutFormat = gstate.getClutPaletteFormat();
 			const u32 bytesPerColor = clutFormat == GE_CMODE_32BIT_ABGR8888 ? sizeof(u32) : sizeof(u16);
 			const u32 clutTotalColors = clutMaxBytes_ / bytesPerColor;
 
-			TexCacheEntry::Status alphaStatus = CheckAlpha(clutBuf_, getClutDestFormat(gstate.getClutPaletteFormat()), clutTotalColors, clutTotalColors, 1);
+			TexCacheEntry::Status alphaStatus = CheckAlpha(clutBuf_, getClutDestFormat(clutFormat), clutTotalColors, clutTotalColors, 1);
 			gstate_c.textureFullAlpha = alphaStatus == TexCacheEntry::STATUS_ALPHA_FULL;
 			gstate_c.textureSimpleAlpha = alphaStatus == TexCacheEntry::STATUS_ALPHA_SIMPLE;
 		} else {