diff --git a/pcsx2/GS/Renderers/Common/GSRenderer.cpp b/pcsx2/GS/Renderers/Common/GSRenderer.cpp
index 971a842e3f..f44201ed6a 100644
--- a/pcsx2/GS/Renderers/Common/GSRenderer.cpp
+++ b/pcsx2/GS/Renderers/Common/GSRenderer.cpp
@@ -147,7 +147,8 @@ bool GSRenderer::Merge(int field)
 
 	s_n++;
 
-	if (samesrc && fr[0].bottom == fr[1].bottom && !feedback_merge && fr[0].right == fr[1].right)
+	// Only need to check the right/bottom on software renderer, hardware always gets the full texture then cuts a bit out later.
+	if (samesrc && !feedback_merge && (GSConfig.UseHardwareRenderer() || (fr[0].right == fr[1].right && fr[0].bottom == fr[1].bottom)))
 	{
 		tex[0] = GetOutput(0, y_offset[0]);
 		tex[1] = tex[0]; // saves one texture fetch
@@ -200,11 +201,14 @@ bool GSRenderer::Merge(int field)
 		GSVector2i display_diff(display_offsets[i].x - display_baseline.x, display_offsets[i].y - display_baseline.y);
 		GSVector2i frame_diff(fr[i].left - frame_baseline.x, fr[i].top - frame_baseline.y);
 
-		// Clear any frame offsets, we don't need them now.
-		fr[i].right -= fr[i].left;
-		fr[i].left = 0;
-		fr[i].bottom -= fr[i].top;
-		fr[i].top = 0;
+		if (!GSConfig.UseHardwareRenderer())
+		{
+			// Clear any frame offsets, we don't need them now.
+			fr[i].right -= fr[i].left;
+			fr[i].left = 0;
+			fr[i].bottom -= fr[i].top;
+			fr[i].top = 0;
+		}
 
 		// If using scanmsk we have to keep the single line offset, regardless of upscale
 		// so we handle this separately after the rect calculations.
@@ -239,11 +243,15 @@ bool GSRenderer::Merge(int field)
 					if (display_diff.y < 4)
 						off.y -= display_diff.y;
 
-					// Offset by DISPFB setting
-					if (abs(frame_diff.x) < 4)
-						off.x += frame_diff.x;
-					if (abs(frame_diff.y) < 4)
-						off.y += frame_diff.y;
+					// Only functional in HW mode, software clips/positions the framebuffer on read.
+					if (GSConfig.UseHardwareRenderer())
+					{
+						// Offset by DISPFB setting
+						if (abs(frame_diff.x) < 4)
+							off.x += frame_diff.x;
+						if (abs(frame_diff.y) < 4)
+							off.y += frame_diff.y;
+					}
 				}
 			}
 		}
@@ -289,7 +297,8 @@ bool GSRenderer::Merge(int field)
 						off.y += display_baseline.y;
 
 					// Anti-Blur stuff
-					if (GSConfig.PCRTCAntiBlur)
+					// Only functional in HW mode, software clips/positions the framebuffer on read.
+					if (GSConfig.PCRTCAntiBlur && GSConfig.UseHardwareRenderer())
 					{
 						// Offset by DISPFB setting
 						if (abs(frame_diff.x) < 4)
diff --git a/pcsx2/GS/Renderers/SW/GSRendererSW.cpp b/pcsx2/GS/Renderers/SW/GSRendererSW.cpp
index a8bc4255f1..6a2c9adf13 100644
--- a/pcsx2/GS/Renderers/SW/GSRendererSW.cpp
+++ b/pcsx2/GS/Renderers/SW/GSRendererSW.cpp
@@ -35,7 +35,6 @@ GSRendererSW::GSRendererSW(int threads)
 	m_tc = std::make_unique<GSTextureCacheSW>();
 	m_rl = GSRasterizerList::Create<GSDrawScanline>(threads);
 
-	// Max framebuffer size can be 1024x2048 (it will loop at 2048).
 	m_output = (u8*)_aligned_malloc(1024 * 1024 * sizeof(u32), 32);
 
 	std::fill(std::begin(m_fzb_pages), std::end(m_fzb_pages), 0);
@@ -146,46 +145,52 @@ GSTexture* GSRendererSW::GetOutput(int i, int& y_offset)
 		constexpr int pitch = 1024 * 4;
 		const int off_x = DISPFB.DBX & 0x7ff;
 		const int off_y = DISPFB.DBY & 0x7ff;
-		bool part2_h = false;
-		bool part2_w = false;
+		const GSVector4i out_r(0, 0, w, h);
 		GSVector4i r(off_x, off_y, w + off_x, h + off_y);
 		GSVector4i rh(off_x, off_y, w + off_x, (h + off_y) & 0x7FF);
 		GSVector4i rw(off_x, off_y, (w + off_x) & 0x7FF, h + off_y);
-		GSVector4i out_r(0, 0, w, h);
+		bool h_wrap = false;
+		bool w_wrap = false;
 
 		// Need to read it in 2 parts, since you can't do a split rect.
 		if (r.bottom >= 2048)
 		{
 			r.bottom = 2048;
 			rw.bottom = 2048;
-			part2_h = true;
 			rh.top = 0;
+			h_wrap = true;
 		}
 
 		if (r.right >= 2048)
 		{
 			r.right = 2048;
 			rh.right = 2048;
-			part2_w = true;
 			rw.left = 0;
-			
+			w_wrap = true;
 		}
+
 		const GSLocalMemory::psm_t& psm = GSLocalMemory::m_psm[DISPFB.PSM];
 
+		// Top left rect
 		(m_mem.*psm.rtx)(m_mem.GetOffset(DISPFB.Block(), DISPFB.FBW, DISPFB.PSM), r.ralign<Align_Outside>(psm.bs), m_output, pitch, m_env.TEXA);
 
-		int top = (part2_h) ? ((r.bottom - r.top) * pitch) : 0;
-		int left = (part2_w) ? (r.right - r.left) * (GSLocalMemory::m_psm[DISPFB.PSM].bpp / 8) : 0;
+		int top = (h_wrap) ? ((r.bottom - r.top) * pitch) : 0;
+		int left = (w_wrap) ? (r.right - r.left) * (GSLocalMemory::m_psm[DISPFB.PSM].bpp / 8) : 0;
 
-		if (part2_w)
+		// The following only happen if the DBX/DBY wrap around at 2048.
+
+		// Top right rect
+		if (w_wrap)
 			(m_mem.*psm.rtx)(m_mem.GetOffset(DISPFB.Block(), DISPFB.FBW, DISPFB.PSM), rw.ralign<Align_Outside>(psm.bs), &m_output[left], pitch, m_env.TEXA);
 
-		if (part2_h)
+		// Bottom left rect
+		if (h_wrap)
 			(m_mem.*psm.rtx)(m_mem.GetOffset(DISPFB.Block(), DISPFB.FBW, DISPFB.PSM), rh.ralign<Align_Outside>(psm.bs), &m_output[top], pitch, m_env.TEXA);
 
-		if (part2_h && part2_w)
+		// Bottom right rect
+		if (h_wrap && w_wrap)
 		{
-			// needs also rw with the start/end height of rh, fills in the bottom right rect which will be missing if both overflow.
+			// Needs also rw with the start/end height of rh, fills in the bottom right rect which will be missing if both overflow.
 			const GSVector4i rwh(rw.left, rh.top, rw.right, rh.bottom);
 			(m_mem.*psm.rtx)(m_mem.GetOffset(DISPFB.Block(), DISPFB.FBW, DISPFB.PSM), rwh.ralign<Align_Outside>(psm.bs), &m_output[top + left], pitch, m_env.TEXA);
 		}