add crt-guest shaders and presets and LUTify two presets

2024-11-23 08:19:54 +00:00 · 2019-01-08 16:21:34 -06:00 · 2019-01-08 16:21:34 -06:00 · 488bcf4038
commit 488bcf4038
parent b54b0b29df
10 changed files with 1064 additions and 83 deletions
--- a/crt/crt-guest-dr-venom.slangp
+++ b/crt/crt-guest-dr-venom.slangp
@ -0,0 +1,48 @@
+shaders = 8
+
+shader0 = shaders/guest/afterglow.slang
+filter_linear0 = false
+scale_type0 = source
+scale0 = 1.0
+
+shader1 = shaders/guest/d65-d50.slang
+filter_linear1 = false
+scale_type1 = source
+scale1 = 1.0
+alias1 = temp_pass
+
+shader2 = shaders/guest/avg-lum.slang
+filter_linear2 = false
+scale_type2 = source
+scale2 = 0.0625
+mipmap_input2 = true
+alias2 = lum_pass
+
+shader3 = ../stock.slang
+filter_linear3 = false
+scale_type3 = source
+scale3 = 16.0
+
+shader4 = shaders/guest/linearize.slang
+filter_linear4 = false
+scale_type4 = source
+scale4 = 1.0
+float_framebuffer4 = true
+alias4 = linearize_pass
+
+shader5 = shaders/guest/blur_horiz.slang
+filter_linear5 = false
+scale_type5 = source
+scale5 = 1.0
+float_framebuffer5 = true
+
+shader6 = shaders/guest/blur_vert.slang
+filter_linear6 = false
+scale_type6 = source
+scale6 = 1.0
+float_framebuffer6 = true
+
+shader7 = shaders/guest/crt-guest-dr-venom.slang
+filter_linear7 = true
+scale_type7 = viewport
+scale7 = 1.0
--- a/crt/shaders/guest/afterglow.slang
+++ b/crt/shaders/guest/afterglow.slang
@ -0,0 +1,104 @@
+#version 450
+
+/*
+   Phosphor Afterglow Shader
+   
+   Copyright (C) 2018 guest(r) - guest.r@gmail.com
+
+   This program is free software; you can redistribute it and/or
+   modify it under the terms of the GNU General Public License
+   as published by the Free Software Foundation; either version 2
+   of the License, or (at your option) any later version.
+
+   This program is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+   GNU General Public License for more details.
+
+   You should have received a copy of the GNU General Public License
+   along with this program; if not, write to the Free Software
+   Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
+   
+*/
+
+layout(push_constant) uniform Push
+{
+	vec4 SourceSize;
+	vec4 OriginalSize;
+	vec4 OutputSize;
+	uint FrameCount;
+	float SW;
+	float AR;
+	float PR;
+	float AG;
+	float PG;
+	float AB;
+	float PB;
+	float sat;
+	float GTH;
+} params;
+
+#pragma parameter SW "Afterglow switch ON/OFF" 1.0 0.0 1.0 1.0
+#pragma parameter AR "Afterglow Red (more is more)" 0.07 0.0 1.0 0.01
+#pragma parameter PR "Persistence Red (more is less)" 0.05 0.0 1.0 0.01
+#pragma parameter AG "Afterglow Green" 0.07 0.0 1.0 0.01
+#pragma parameter PG "Persistence Green"  0.05 0.0 1.0 0.01
+#pragma parameter AB "Afterglow Blue" 0.07 0.0 1.0 0.01
+#pragma parameter PB "Persistence Blue"  0.05 0.0 1.0 0.01
+#pragma parameter sat "Afterglow saturation" 0.10 0.0 1.0 0.01
+#pragma parameter GTH "Afterglow threshold" 5.0 0.0 255.0 1.0
+
+layout(std140, set = 0, binding = 0) uniform UBO
+{
+	mat4 MVP;
+} global;
+
+#pragma stage vertex
+layout(location = 0) in vec4 Position;
+layout(location = 1) in vec2 TexCoord;
+layout(location = 0) out vec2 vTexCoord;
+
+void main()
+{
+   gl_Position = global.MVP * Position;
+   vTexCoord = TexCoord;
+}
+
+#pragma stage fragment
+layout(location = 0) in vec2 vTexCoord;
+layout(location = 0) out vec4 FragColor;
+layout(set = 0, binding = 2) uniform sampler2D Source;
+layout(set = 0, binding = 3) uniform sampler2D OriginalHistory1;
+layout(set = 0, binding = 4) uniform sampler2D OriginalHistory2;
+layout(set = 0, binding = 5) uniform sampler2D OriginalHistory3;
+layout(set = 0, binding = 6) uniform sampler2D OriginalHistory4;
+layout(set = 0, binding = 7) uniform sampler2D OriginalHistory5;
+layout(set = 0, binding = 8) uniform sampler2D OriginalHistory6;
+
+#define eps 1e-4
+
+vec3 afterglow(float number)
+{
+	return vec3(params.AR, params.AG, params.AB)*exp2(-vec3(params.PR, params.PG, params.PB)*vec3(number*number));
+}
+
+void main()
+{
+	vec3 color = texture(Source, vTexCoord.xy).rgb;
+	vec3 color1 = texture(OriginalHistory1, vTexCoord.xy).rgb * afterglow(1.0);
+	vec3 color2 = texture(OriginalHistory2, vTexCoord.xy).rgb * afterglow(2.0);
+	vec3 color3 = texture(OriginalHistory3, vTexCoord.xy).rgb * afterglow(3.0);
+	vec3 color4 = texture(OriginalHistory4, vTexCoord.xy).rgb * afterglow(4.0);
+	vec3 color5 = texture(OriginalHistory5, vTexCoord.xy).rgb * afterglow(5.0);
+	vec3 color6 = texture(OriginalHistory6, vTexCoord.xy).rgb * afterglow(6.0);
+
+	vec3 glow = color1 + color2 + color3 + color4 + color5 + color6;
+	
+	float l = length(glow);
+	glow = normalize(pow(glow + vec3(eps), vec3(params.sat)))*l;		
+	
+	float w = 1.0;
+	if ((color.r + color.g + color.b) > params.GTH/255.0) w = 0.0;
+	
+	FragColor = vec4(color + params.SW*w*glow,1.0);
+}
--- a/crt/shaders/guest/avg-lum.slang
+++ b/crt/shaders/guest/avg-lum.slang
@ -0,0 +1,64 @@
+#version 450
+
+/*
+   Average Luminance Shader
+   
+   Copyright (C) 2018 guest(r) - guest.r@gmail.com
+
+   This program is free software; you can redistribute it and/or
+   modify it under the terms of the GNU General Public License
+   as published by the Free Software Foundation; either version 2
+   of the License, or (at your option) any later version.
+
+   This program is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+   GNU General Public License for more details.
+
+   You should have received a copy of the GNU General Public License
+   along with this program; if not, write to the Free Software
+   Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
+   
+   Thanks to HunterK for the mipmap hint. :D
+*/
+
+layout(push_constant) uniform Push
+{
+	vec4 SourceSize;
+	vec4 OriginalSize;
+	vec4 OutputSize;
+	uint FrameCount;
+	float grade;
+} params;
+
+#pragma parameter grade "Blooming grade" 0.70 0.10 1.0 0.05 
+
+layout(std140, set = 0, binding = 0) uniform UBO
+{
+	mat4 MVP;
+} global;
+
+#pragma stage vertex
+layout(location = 0) in vec4 Position;
+layout(location = 1) in vec2 TexCoord;
+layout(location = 0) out vec2 vTexCoord;
+
+void main()
+{
+   gl_Position = global.MVP * Position;
+   vTexCoord = TexCoord;
+}
+
+#pragma stage fragment
+layout(location = 0) in vec2 vTexCoord;
+layout(location = 0) out vec4 FragColor;
+layout(set = 0, binding = 2) uniform sampler2D Source;
+
+void main()
+{
+	float mip_level = max(log2(params.SourceSize.x), log2(params.SourceSize.y));
+	float black_compensation = (params.SourceSize.x*params.SourceSize.y)/(params.SourceSize.x*params.SourceSize.y);
+	float lum = length(textureLod(Source, vTexCoord.xy, mip_level).rgb * black_compensation);
+	lum = lum * inversesqrt(3.0);
+	FragColor = vec4(pow(lum, params.grade));
+}
--- a/crt/shaders/guest/blur_horiz.slang
+++ b/crt/shaders/guest/blur_horiz.slang
@ -0,0 +1,55 @@
+#version 450
+
+// Higher value, more centered glow.
+// Lower values might need more taps.
+
+layout(push_constant) uniform Push
+{
+	vec4 SourceSize;
+	vec4 OriginalSize;
+	vec4 OutputSize;
+	uint FrameCount;
+	float TAPSH;
+	float GLOW_FALLOFF_H;
+} params;
+
+#pragma parameter TAPSH "H. Glow Radius" 4.0 1.0 6.0 1.0 
+#pragma parameter GLOW_FALLOFF_H "GLOW_FALLOFF H" 0.30 0.10 1.0 0.01 
+
+layout(std140, set = 0, binding = 0) uniform UBO
+{
+	mat4 MVP;
+} global;
+
+#pragma stage vertex
+layout(location = 0) in vec4 Position;
+layout(location = 1) in vec2 TexCoord;
+layout(location = 0) out vec2 vTexCoord;
+
+void main()
+{
+   gl_Position = global.MVP * Position;
+   vTexCoord = TexCoord;
+}
+
+#pragma stage fragment
+layout(location = 0) in vec2 vTexCoord;
+layout(location = 0) out vec4 FragColor;
+layout(set = 0, binding = 2) uniform sampler2D Source;
+
+#define kernel(x) exp(-params.GLOW_FALLOFF_H * (x) * (x))
+
+void main()
+{
+	vec3 col = vec3(0.0);
+	float dx = params.SourceSize.z;
+
+	float k_total = 0.;
+	for (float i = -params.TAPSH; i <= params.TAPSH; i++)
+		{
+		float k = kernel(i);
+		k_total += k;
+		col += k * texture(Source, vTexCoord + vec2(float(i) * dx, 0.0)).rgb;
+		}
+   FragColor = vec4(col / k_total, 1.0);
+}
--- a/crt/shaders/guest/blur_vert.slang
+++ b/crt/shaders/guest/blur_vert.slang
@ -0,0 +1,55 @@
+#version 450
+
+// Higher value, more centered glow.
+// Lower values might need more taps.
+
+layout(push_constant) uniform Push
+{
+	vec4 SourceSize;
+	vec4 OriginalSize;
+	vec4 OutputSize;
+	uint FrameCount;
+	float TAPSV;
+	float GLOW_FALLOFF_V;
+} params;
+
+#pragma parameter TAPSV "V. Glow Radius" 4.0 1.0 6.0 1.0 
+#pragma parameter GLOW_FALLOFF_V "GLOW_FALLOFF_V" 0.30 0.10 1.0 0.01 
+
+layout(std140, set = 0, binding = 0) uniform UBO
+{
+	mat4 MVP;
+} global;
+
+#pragma stage vertex
+layout(location = 0) in vec4 Position;
+layout(location = 1) in vec2 TexCoord;
+layout(location = 0) out vec2 vTexCoord;
+
+void main()
+{
+   gl_Position = global.MVP * Position;
+   vTexCoord = TexCoord;
+}
+
+#pragma stage fragment
+layout(location = 0) in vec2 vTexCoord;
+layout(location = 0) out vec4 FragColor;
+layout(set = 0, binding = 2) uniform sampler2D Source;
+
+#define kernel(x) exp(-params.GLOW_FALLOFF_V * (x) * (x))
+
+void main()
+{
+	vec3 col = vec3(0.0);
+	float dy = params.SourceSize.w;
+
+	float k_total = 0.;
+	for (float i = -params.TAPSV; i <= params.TAPSV; i++)
+		{
+		float k = kernel(i);
+		k_total += k;
+		col += k * texture(Source, vTexCoord + vec2(0.0, float(i) * dy)).rgb;
+		}
+   FragColor = vec4(col / k_total, 1.0);
+}
--- a/crt/shaders/guest/crt-guest-dr-venom.slang
+++ b/crt/shaders/guest/crt-guest-dr-venom.slang
@ -0,0 +1,300 @@
+#version 450
+
+/*
+   CRT - Guest - Dr. Venom
+   
+   Copyright (C) 2018 guest(r) - guest.r@gmail.com
+
+   This program is free software; you can redistribute it and/or
+   modify it under the terms of the GNU General Public License
+   as published by the Free Software Foundation; either version 2
+   of the License, or (at your option) any later version.
+
+   This program is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+   GNU General Public License for more details.
+
+   You should have received a copy of the GNU General Public License
+   along with this program; if not, write to the Free Software
+   Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
+   
+*/
+
+layout(push_constant) uniform Push
+{
+	vec4 SourceSize;
+	vec4 OutputSize;
+	float OS;
+	float BLOOM;
+	float brightboost;
+	float saturation;
+	float scanline;
+	float beam_min;
+	float beam_max;
+	float h_sharp;
+	float l_sharp;
+	float gamma_out;
+	float warpX;
+	float warpY;
+	float glow;
+	float shadowMask;
+	float maskDark;
+	float maskLight;
+	float CGWG;
+	float GTW;
+} params;
+
+#pragma parameter OS "Do Overscan" 1.0 0.0 2.0 1.0
+#define OS params.OS
+#pragma parameter BLOOM "Bloom percentage" 5.0 0.0 20.0 1.0
+#define BLOOM params.BLOOM
+#pragma parameter brightboost "Bright boost" 1.10 0.50 2.00 0.01
+#define brightboost params.brightboost
+#pragma parameter saturation "Saturation adjustment" 1.0 0.1 2.0 0.05
+#define saturation params.saturation
+#pragma parameter scanline "Scanline adjust" 8.0 1.0 12.0 1.0
+#define scanline params.scanline
+#pragma parameter beam_min "Scanline dark" 1.40 0.5 2.0 0.05
+#define beam_min params.beam_min
+#pragma parameter beam_max "Scanline bright" 0.80 0.5 2.0 0.05
+#define beam_max params.beam_max
+#pragma parameter h_sharp "Horizontal sharpness" 5.0 1.5 20.0 0.25
+#define h_sharp params.h_sharp
+#pragma parameter l_sharp "Substractive sharpness" 0.0 0.0 0.30 0.01
+#define l_sharp params.l_sharp
+#pragma parameter gamma_out "Gamma out" 2.4 1.0 3.0 0.05
+#define gamma_out params.gamma_out
+#pragma parameter warpX "warpX" 0.031 0.0 0.125 0.01
+#define warpX params.warpX
+#pragma parameter warpY "warpY" 0.041 0.0 0.125 0.01
+#define warpY params.warpY
+#pragma parameter glow "Glow Strength" 0.06 0.0 0.5 0.01
+#define glow params.glow
+#pragma parameter shadowMask "Mask Style (0 = CGWG)" 0.0 0.0 4.0 1.0
+#pragma parameter maskDark "Lottes maskDark" 0.5 0.0 2.0 0.1
+#define maskDark params.maskDark
+#pragma parameter maskLight "Lottes maskLight" 1.5 0.0 2.0 0.1
+#define maskLight params.maskLight
+#pragma parameter CGWG "CGWG Mask Str." 0.4 0.0 1.0 0.1
+#define CGWG params.CGWG
+#pragma parameter GTW "Gamma Tweak" 1.10 0.5 1.5 0.01
+#define GTW params.GTW
+
+layout(std140, set = 0, binding = 0) uniform UBO
+{
+	mat4 MVP;
+} global;
+
+#pragma stage vertex
+layout(location = 0) in vec4 Position;
+layout(location = 1) in vec2 TexCoord;
+layout(location = 0) out vec2 vTexCoord;
+
+void main()
+{
+   gl_Position = global.MVP * Position;
+   vTexCoord = TexCoord * 1.0001;
+}
+
+#pragma stage fragment
+layout(location = 0) in vec2 vTexCoord;
+layout(location = 0) out vec4 FragColor;
+layout(set = 0, binding = 2) uniform sampler2D Source;
+layout(set = 0, binding = 3) uniform sampler2D lum_pass;
+layout(set = 0, binding = 4) uniform sampler2D linearize_pass;
+
+#define eps 1e-10
+
+vec3 sw(float x, vec3 color)
+{
+	vec3 tmp = mix(vec3(beam_min),vec3(beam_max), color);
+	vec3 ex = vec3(x)*tmp;
+	return exp2(-scanline*ex*ex);
+} 
+
+// Shadow mask (mostly from PD Lottes shader).
+vec3 Mask(vec2 pos)
+{
+   vec3 mask = vec3(maskDark, maskDark, maskDark);
+
+   // Phosphor.
+   if (params.shadowMask == 0.0)
+   {
+      float mf = floor(mod(pos.x,2.0));
+      float mc = 1.0 - CGWG;	
+      if (mf == 0.0) { mask.r = 1.0; mask.g = mc; mask.b = 1.0; }
+      else { mask.r = mc; mask.g = 1.0; mask.b = mc; };
+   }    
+   
+   
+   // Very compressed TV style shadow mask.
+   else if (params.shadowMask == 1.0)
+   {
+      float line = maskLight;
+      float odd  = 0.0;
+
+      if (fract(pos.x/6.0) < 0.5)
+         odd = 1.0;
+      if (fract((pos.y + odd)/2.0) < 0.5)
+         line = maskDark;
+
+      pos.x = fract(pos.x/3.0);
+    
+      if      (pos.x < 0.333) mask.r = maskLight;
+      else if (pos.x < 0.666) mask.g = maskLight;
+      else                    mask.b = maskLight;
+      mask*=line;  
+   } 
+
+   // Aperture-grille.
+   else if (params.shadowMask == 2.0)
+   {
+      pos.x = fract(pos.x/3.0);
+
+      if      (pos.x < 0.333) mask.r = maskLight;
+      else if (pos.x < 0.666) mask.g = maskLight;
+      else                    mask.b = maskLight;
+   } 
+
+   // Stretched VGA style shadow mask (same as prior shaders).
+   else if (params.shadowMask == 3.0)
+   {
+      pos.x += pos.y*3.0;
+      pos.x  = fract(pos.x/6.0);
+
+      if      (pos.x < 0.333) mask.r = maskLight;
+      else if (pos.x < 0.666) mask.g = maskLight;
+      else                    mask.b = maskLight;
+   }
+
+   // VGA style shadow mask.
+   else if (params.shadowMask == 4.0)
+   {
+      pos.xy = floor(pos.xy*vec2(1.0, 0.5));
+      pos.x += pos.y*3.0;
+      pos.x  = fract(pos.x/6.0);
+
+      if      (pos.x < 0.333) mask.r = maskLight;
+      else if (pos.x < 0.666) mask.g = maskLight;
+      else                    mask.b = maskLight;
+   }
+
+   return mask;
+} 
+
+// Distortion of scanlines, and end of screen alpha (PD Lottes Curvature)
+vec2 Warp(vec2 pos)
+{
+    pos  = pos*2.0-1.0;    
+    pos *= vec2(1.0 + (pos.y*pos.y)*warpX, 1.0 + (pos.x*pos.x)*warpY);
+    return pos*0.5 + 0.5;
+} 
+
+vec2 Overscan(vec2 pos, float dx, float dy){
+  pos=pos*2.0-1.0;    
+  pos*=vec2(dx,dy);
+  return pos*0.5+0.5;
+} 
+
+// Borrowed from cgwg's crt-geom, under GPL
+
+float corner(vec2 coord)
+{
+                coord *= params.SourceSize.xy / params.SourceSize.xy;
+                coord = (coord - vec2(0.5)) * 1.0 + vec2(0.5);
+                coord = min(coord, vec2(1.0)-coord) * vec2(1.0, params.SourceSize.y/params.SourceSize.x);
+                vec2 cdist = vec2(0.003);
+                coord = (cdist - min(coord,cdist));
+                float dist = sqrt(dot(coord,coord));
+                return clamp((cdist.x-dist)*600.0,0.0, 1.0);
+}  
+
+const float sqrt3     = 1.732050807568877;
+
+vec3 gamma_correct(vec3 color, vec3 tmp)
+{
+	float l = length(color)/sqrt3;
+	float g = mix(1.0/GTW, 1.0, max(max(tmp.r,tmp.g),tmp.b));
+	l = pow(l,g)*sqrt3;
+	return l*normalize(color + vec3(eps));
+}
+
+void main()
+{
+	vec3 lum = texture(lum_pass, vec2(0.1,0.1)).xyz;
+
+	float factor  = 1.00 + (1.0-0.5*OS)*BLOOM/100.0 - lum.x*BLOOM/100.0;
+	vec2 texcoord  = Overscan(vTexCoord.xy*(params.SourceSize.xy/params.SourceSize.xy), factor, factor)*(params.SourceSize.xy/params.SourceSize.xy);
+	vec2 pos  = Warp(texcoord);
+	vec2 pos0 = Warp(texcoord);
+	
+	vec2 ps = params.SourceSize.zw;
+	vec2 OGL2Pos = pos * params.SourceSize.xy - vec2(0.0,0.5);
+	vec2 fp = fract(OGL2Pos);
+	vec2 dx = vec2(ps.x,0.0);
+	vec2 dy = vec2(0.0, ps.y);
+
+	vec2 pC4 = floor(OGL2Pos) * ps + 0.5*ps;	
+	
+	// Reading the texels
+	vec2 x2 = 2.0*dx;
+	
+	float wl  = exp2(-h_sharp*0.36)*l_sharp;
+
+	float wl2 = 1.5 + fp.x; wl2*=wl2; wl2 = exp2(-h_sharp*wl2); wl2 = max(wl2 - wl, -wl2);
+	float wl1 = 0.5 + fp.x; wl1*=wl1; wl1 = exp2(-h_sharp*wl1); wl1 = max(wl1 - wl, -0.25);
+	float wct = 0.5 - fp.x; wct*=wct; wct = exp2(-h_sharp*wct);
+	float wr1 = 1.5 - fp.x; wr1*=wr1; wr1 = exp2(-h_sharp*wr1); wr1 = max(wr1 - wl, -0.25);
+	float wr2 = 2.5 - fp.x; wr2*=wr2; wr2 = exp2(-h_sharp*wr2); wr2 = max(wr2 - wl, -wr2);
+
+	float wt = 1.0/(wl2+wl1+wct+wr1+wr2);
+	
+	vec3 l2 = texture(linearize_pass, pC4 -x2).xyz;
+	vec3 l1 = texture(linearize_pass, pC4 -dx).xyz;
+	vec3 ct = texture(linearize_pass, pC4    ).xyz;	
+	vec3 r1 = texture(linearize_pass, pC4 +dx).xyz;
+	vec3 r2 = texture(linearize_pass, pC4 +x2).xyz;
+
+	vec3 color1 = (l2*wl2 + l1*wl1 + ct*wct + r1*wr1 + r2*wr2)*wt;
+	if (l_sharp > 0.0) color1 = clamp(color1, 0.8*min(min(l1,r1),ct), 1.2*max(max(l1,r1),ct)); 
+	
+	l2 = texture(linearize_pass, pC4 -x2 +dy).xyz;
+	l1 = texture(linearize_pass, pC4 -dx +dy).xyz;
+	ct = texture(linearize_pass, pC4     +dy).xyz;	
+	r1 = texture(linearize_pass, pC4 +dx +dy).xyz;
+	r2 = texture(linearize_pass, pC4 +x2 +dy).xyz;
+
+	vec3 color2 = (l2*wl2 + l1*wl1 + ct*wct + r1*wr1 + r2*wr2)*wt;
+	if (l_sharp > 0.0) color2 = clamp(color2, 0.8*min(min(l1,r1),ct), 1.2*max(max(l1,r1),ct)); 
+	
+// calculating scanlines
+	
+	float f = fp.y;
+	
+	vec3 w1 = sw(f,color1);
+	vec3 w2 = sw(1.0-f,color2); 
+	
+	vec3 color = color1*w1 + color2*w2;
+	vec3 ctmp  = color/(w1+w2);
+	
+	color = pow(color, vec3(1.0/gamma_out));
+	float l = length(color);
+	color = normalize(pow(color + vec3(eps), vec3(saturation,saturation,saturation)))*l;	
+	color*=brightboost;	
+	color = gamma_correct(color,ctmp);
+	color = pow(color, vec3(gamma_out));	
+	color = min(color, 1.0);	
+	
+// Apply Mask
+
+	color = color*Mask(vTexCoord * params.OutputSize.xy);
+	
+	vec3 Bloom = texture(Source, pos).xyz;
+	
+	color+=glow*Bloom;
+	color = min(color, 1.0);
+	
+	color = pow(color, vec3(1.0/gamma_out));
+    FragColor = vec4(color*corner(pos0), 1.0);
+}
--- a/crt/shaders/guest/d65-d50.slang
+++ b/crt/shaders/guest/d65-d50.slang
@ -0,0 +1,57 @@
+#version 450
+
+layout(push_constant) uniform Push
+{
+	vec4 SourceSize;
+	vec4 OriginalSize;
+	vec4 OutputSize;
+	uint FrameCount;
+	float WP;
+} params;
+
+#pragma parameter WP "D65 to D50 strength %" 0.0 -100.0 100.0 10.0 
+
+layout(std140, set = 0, binding = 0) uniform UBO
+{
+	mat4 MVP;
+} global;
+
+#pragma stage vertex
+layout(location = 0) in vec4 Position;
+layout(location = 1) in vec2 TexCoord;
+layout(location = 0) out vec2 vTexCoord;
+
+void main()
+{
+   gl_Position = global.MVP * Position;
+   vTexCoord = TexCoord;
+}
+
+#pragma stage fragment
+layout(location = 0) in vec2 vTexCoord;
+layout(location = 0) out vec4 FragColor;
+layout(set = 0, binding = 2) uniform sampler2D Source;
+
+const mat3 D65 = mat3 (
+           0.5767309,  0.2973769,  0.0270343,
+           0.1855540,  0.6273491,  0.0706872,
+           0.1881852,  0.0752741,  0.9911085);
+
+const mat3 D50 = mat3 (
+           1.7552599, -0.5441336,  0.0063467,
+          -0.4836786,  1.5068789, -0.0175761,
+          -0.2530000,  0.0215528,  1.2256959);
+
+void main()
+{
+	vec3 color = texture(Source, vTexCoord.xy).rgb;
+	
+	vec3 c65 = D65*color;
+	vec3 c50 = D50*c65;
+	
+	float m = params.WP/100.0;
+	
+	color = (1.0-m)*color + m*c50;
+	
+	FragColor = vec4(color,1.0);
+}
--- a/crt/shaders/guest/linearize.slang
+++ b/crt/shaders/guest/linearize.slang
@ -0,0 +1,38 @@
+#version 450
+
+layout(push_constant) uniform Push
+{
+	vec4 SourceSize;
+	vec4 OriginalSize;
+	vec4 OutputSize;
+	uint FrameCount;
+	float GAMMA_INPUT;
+} params;
+
+#pragma parameter GAMMA_INPUT "Gamma Input" 2.4 0.1 5.0 0.01
+
+layout(std140, set = 0, binding = 0) uniform UBO
+{
+	mat4 MVP;
+} global;
+
+#pragma stage vertex
+layout(location = 0) in vec4 Position;
+layout(location = 1) in vec2 TexCoord;
+layout(location = 0) out vec2 vTexCoord;
+
+void main()
+{
+   gl_Position = global.MVP * Position;
+   vTexCoord = TexCoord;
+}
+
+#pragma stage fragment
+layout(location = 0) in vec2 vTexCoord;
+layout(location = 0) out vec4 FragColor;
+layout(set = 0, binding = 2) uniform sampler2D temp_pass;
+
+void main()
+{
+   FragColor = pow(vec4(texture(temp_pass, vTexCoord)), vec4(params.GAMMA_INPUT));
+}
--- a/presets/crt-royale-sony_bvm.slangp
+++ b/presets/crt-royale-sony_bvm.slangp
@ -0,0 +1,256 @@
+# IMPORTANT:
+# Shader passes need to know details about the image in the mask_texture LUT
+# files, so set the following constants in user-cgp-constants.h accordingly:
+# 1.) mask_triads_per_tile = (number of horizontal triads in mask texture LUT's)
+# 2.) mask_texture_small_size = (texture size of mask*texture_small LUT's)
+# 3.) mask_texture_large_size = (texture size of mask*texture_large LUT's)
+# 4.) mask_grille_avg_color = (avg. brightness of mask_grille_texture* LUT's, in [0, 1])
+# 5.) mask_slot_avg_color = (avg. brightness of mask_slot_texture* LUT's, in [0, 1])
+# 6.) mask_shadow_avg_color = (avg. brightness of mask_shadow_texture* LUT's, in [0, 1])
+# Shader passes also need to know certain scales set in this .slangp, but their
+# compilation model doesn't currently allow the .slangp file to tell them.  Make
+# sure to set the following constants in user-cgp-constants.h accordingly too:
+# 1.) bloom_approx_scale_x = scale_x2
+# 2.) mask_resize_viewport_scale = float2(scale_x6, scale_y5)
+# Finally, shader passes need to know the value of geom_max_aspect_ratio used to
+# calculate scale_y6 (among other values):
+# 1.) geom_max_aspect_ratio = (geom_max_aspect_ratio used to calculate scale_y5)
+
+shaders = "13"
+
+# Set an identifier, filename, and sampling traits for the phosphor mask texture.
+# Load an aperture grille, slot mask, and an EDP shadow mask, and load a small
+# non-mipmapped version and a large mipmapped version.
+# TODO: Test masks in other directories.
+textures = "mask_grille_texture_small;mask_grille_texture_large;mask_slot_texture_small;mask_slot_texture_large;mask_shadow_texture_small;mask_shadow_texture_large;SamplerLUT"
+mask_grille_texture_small = "../crt/shaders/crt-royale/TileableLinearApertureGrille15Wide8And5d5SpacingResizeTo64.png"
+mask_grille_texture_large = "../crt/shaders/crt-royale/TileableLinearApertureGrille15Wide8And5d5Spacing.png"
+mask_slot_texture_small = "../crt/shaders/crt-royale/TileableLinearSlotMaskTall15Wide9And4d5Horizontal9d14VerticalSpacingResizeTo64.png"
+mask_slot_texture_large = "../crt/shaders/crt-royale/TileableLinearSlotMaskTall15Wide9And4d5Horizontal9d14VerticalSpacing.png"
+mask_shadow_texture_small = "../crt/shaders/crt-royale/TileableLinearShadowMaskEDPResizeTo64.png"
+mask_shadow_texture_large = "../crt/shaders/crt-royale/TileableLinearShadowMaskEDP.png"
+mask_grille_texture_small_wrap_mode = "repeat"
+mask_grille_texture_large_wrap_mode = "repeat"
+mask_slot_texture_small_wrap_mode = "repeat"
+mask_slot_texture_large_wrap_mode = "repeat"
+mask_shadow_texture_small_wrap_mode = "repeat"
+mask_shadow_texture_large_wrap_mode = "repeat"
+mask_grille_texture_small_linear = "true"
+mask_grille_texture_large_linear = "true"
+mask_slot_texture_small_linear = "true"
+mask_slot_texture_large_linear = "true"
+mask_shadow_texture_small_linear = "true"
+mask_shadow_texture_large_linear = "true"
+mask_grille_texture_small_mipmap = "false"  # Mipmapping causes artifacts with manually resized masks without tex2Dlod
+mask_grille_texture_large_mipmap = "true"   # Essential for hardware-resized masks
+mask_slot_texture_small_mipmap = "false"    # Mipmapping causes artifacts with manually resized masks without tex2Dlod
+mask_slot_texture_large_mipmap = "true"     # Essential for hardware-resized masks
+mask_shadow_texture_small_mipmap = "false"  # Mipmapping causes artifacts with manually resized masks without tex2Dlod
+mask_shadow_texture_large_mipmap = "true"   # Essential for hardware-resized masks
+SamplerLUT = "../reshade/shaders/LUT/Sony_Trinitron_Std_50_no_gamma.png"
+SamplerLUT_linear = true
+
+shader0 = "../reshade/shaders/LUT/LUT.slang"
+
+# Pass0: Linearize the input based on CRT gamma and bob interlaced fields.
+# (Bobbing ensures we can immediately blur without getting artifacts.)
+shader1 = "../crt/shaders/crt-royale/src/crt-royale-first-pass-linearize-crt-gamma-bob-fields.slang"
+alias1 = "ORIG_LINEARIZED"
+filter_linear1 = "false"
+scale_type1 = "source"
+scale1 = "1.0"
+srgb_framebuffer1 = "true"
+
+# Pass1: Resample interlaced (and misconverged) scanlines vertically.
+# Separating vertical/horizontal scanline sampling is faster: It lets us
+# consider more scanlines while calculating weights for fewer pixels, and
+# it reduces our samples from vertical*horizontal to vertical+horizontal.
+# This has to come right after ORIG_LINEARIZED, because there's no
+# "original_source" scale_type we can use later.
+shader2 = "../crt/shaders/crt-royale/src/crt-royale-scanlines-vertical-interlacing.slang"
+alias2 = "VERTICAL_SCANLINES"
+filter_linear2 = "true"
+scale_type_x2 = "source"
+scale_x2 = "1.0"
+scale_type_y2 = "viewport"
+scale_y2 = "1.0"
+#float_framebuffer2 = "true"
+srgb_framebuffer2 = "true"
+
+# Pass2: Do a small resize blur of ORIG_LINEARIZED at an absolute size, and
+# account for convergence offsets.  We want to blur a predictable portion of the
+# screen to match the phosphor bloom, and absolute scale works best for
+# reliable results with a fixed-size bloom.  Picking a scale is tricky:
+# a.) 400x300 is a good compromise for the "fake-bloom" version: It's low enough
+#     to blur high-res/interlaced sources but high enough that resampling
+#     doesn't smear low-res sources too much.
+# b.) 320x240 works well for the "real bloom" version: It's 1-1.5% faster, and
+#     the only noticeable visual difference is a larger halation spread (which
+#     may be a good thing for people who like to crank it up).
+# Note the 4:4 aspect ratio assumes the input has cropped geom_overscan (so it's
+# *intended* for an ~4:4 aspect ratio).
+shader3 = "../crt/shaders/crt-royale/src/crt-royale-bloom-approx.slang"
+alias3 = "BLOOM_APPROX"
+filter_linear3 = "true"
+scale_type3 = "absolute"
+scale_x3 = "320"
+scale_y3 = "240"
+srgb_framebuffer3 = "true"
+
+# Pass3: Vertically blur the input for halation and refractive diffusion.
+# Base this on BLOOM_APPROX: This blur should be small and fast, and blurring
+# a constant portion of the screen is probably physically correct if the
+# viewport resolution is proportional to the simulated CRT size.
+shader4 = "../blurs/blur5fast-vertical.slang"
+filter_linear4 = "true"
+scale_type4 = "source"
+scale4 = "1.0"
+srgb_framebuffer4 = "true"
+
+# Pass4: Horizontally blur the input for halation and refractive diffusion.
+# Note: Using a one-pass 9x10 blur is about 1% slower.
+shader5 = "../blurs/blur5fast-horizontal.slang"
+alias5 = "HALATION_BLUR"
+filter_linear5 = "true"
+scale_type5 = "source"
+scale5 = "1.0"
+srgb_framebuffer5 = "true"
+
+# Pass5: Lanczos-resize the phosphor mask vertically.  Set the absolute
+# scale_x6 == mask_texture_small_size.x (see IMPORTANT above).  Larger scales
+# will blur, and smaller scales could get nasty.  The vertical size must be
+# based on the viewport size and calculated carefully to avoid artifacts later.
+# First calculate the minimum number of mask tiles we need to draw.
+# Since curvature is computed after the scanline masking pass:
+#   num_resized_mask_tiles = 2.0;
+# If curvature were computed in the scanline masking pass (it's not):
+#   max_mask_texel_border = ~3.0 * (1/3.0 + 4.0*sqrt(2.0) + 0.6 + 1.0);
+#   max_mask_tile_border = max_mask_texel_border/
+#       (min_resized_phosphor_triad_size * mask_triads_per_tile);
+#   num_resized_mask_tiles = max(2.0, 1.0 + max_mask_tile_border * 2.0);
+#   At typical values (triad_size >= 2.0, mask_triads_per_tile == 8):
+#       num_resized_mask_tiles = ~3.8
+# Triad sizes are given in horizontal terms, so we need geom_max_aspect_ratio
+# to relate them to vertical resolution.  The widest we expect is:
+#   geom_max_aspect_ratio = 4.0/3.0  # Note: Shader passes need to know this!
+# The fewer triads we tile across the screen, the larger each triad will be as a
+# fraction of the viewport size, and the larger scale_y6 must be to draw a full
+# num_resized_mask_tiles.  Therefore, we must decide the smallest number of
+# triads we'll guarantee can be displayed on screen.  We'll set this according
+# to 3-pixel triads at 768p resolution (the lowest anyone's likely to use):
+#   min_allowed_viewport_triads = 768.0*geom_max_aspect_ratio / 3.0 = 341.333333
+# Now calculate the viewport scale that ensures we can draw resized_mask_tiles:
+#   min_scale_x = resized_mask_tiles * mask_triads_per_tile /
+#       min_allowed_viewport_triads
+#   scale_y6 = geom_max_aspect_ratio * min_scale_x
+#   # Some code might depend on equal scales:
+#   scale_x7 = scale_y5
+# Given our default geom_max_aspect_ratio and min_allowed_viewport_triads:
+#   scale_y6 = 4.0/3.0 * 2.0/(341.33334 / 8.0) = 0.0625
+# IMPORTANT: The scales MUST be calculated in this way.  If you wish to change
+# geom_max_aspect_ratio, update that constant in user-cgp-constants.h!
+shader6 = "../crt/shaders/crt-royale/src/crt-royale-mask-resize-vertical.slang"
+filter_linear6 = "true"
+scale_type_x6 = "absolute"
+scale_x6 = "64"
+scale_type_y6 = "viewport"
+scale_y6 = "0.0625" # Safe for >= 341.334 horizontal triads at viewport size
+#srgb_framebuffer6 = "false" # mask_texture is already assumed linear
+
+# Pass6: Lanczos-resize the phosphor mask horizontally.  scale_x7 = scale_y5.
+# TODO: Check again if the shaders actually require equal scales.
+shader7 = "../crt/shaders/crt-royale/src/crt-royale-mask-resize-horizontal.slang"
+alias7 = "MASK_RESIZE"
+filter_linear7 = "false"
+scale_type_x7 = "viewport"
+scale_x7 = "0.0625"
+scale_type_y7 = "source"
+scale_y7 = "1.0"
+#srgb_framebuffer7 = "false" # mask_texture is already assumed linear
+
+# Pass7: Resample (misconverged) scanlines horizontally, apply halation, and
+# apply the phosphor mask.
+shader8 = "../crt/shaders/crt-royale/src/crt-royale-scanlines-horizontal-apply-mask.slang"
+alias8 = "MASKED_SCANLINES"
+filter_linear8 = "true" # This could just as easily be nearest neighbor.
+scale_type8 = "viewport"
+scale8 = "1.0"
+#float_framebuffer8 = "true"
+srgb_framebuffer8 = "true"
+
+# Pass 8: Compute a brightpass.  This will require reading the final mask.
+shader9 = "../crt/shaders/crt-royale/src/crt-royale-brightpass.slang"
+alias9 = "BRIGHTPASS"
+filter_linear9 = "true" # This could just as easily be nearest neighbor.
+scale_type9 = "viewport"
+scale9 = "1.0"
+srgb_framebuffer9 = "true"
+
+# Pass 9: Blur the brightpass vertically
+shader10 = "../crt/shaders/crt-royale/src/crt-royale-bloom-vertical.slang"
+filter_linear10 = "true" # This could just as easily be nearest neighbor.
+scale_type10 = "source"
+scale10 = "1.0"
+srgb_framebuffer10 = "true"
+
+# Pass 10: Blur the brightpass horizontally and combine it with the dimpass:
+shader11 = "../crt/shaders/crt-royale/src/crt-royale-bloom-horizontal-reconstitute.slang"
+filter_linear11 = "true"
+scale_type11 = "source"
+scale11 = "1.0"
+srgb_framebuffer11 = "true"
+
+# Pass 11: Compute curvature/AA:
+shader12 = "../crt/shaders/crt-royale/src/crt-royale-last-pass-no-geom.slang"
+filter_linear12 = "true"
+scale_type12 = "viewport"
+mipmap_input12 = "true"
+texture_wrap_mode12 = "clamp_to_edge"
+
+parameters = "crt_gamma;lcd_gamma;levels_contrast;halation_weight;diffusion_weight;bloom_underestimate_levels;bloom_excess;beam_min_sigma;beam_max_sigma;beam_spot_power;beam_min_shape;beam_max_shape;beam_shape_power;beam_horiz_filter;beam_horiz_sigma;beam_horiz_linear_rgb_weight;convergence_offset_x_r;convergence_offset_x_g;convergence_offset_x_b;convergence_offset_y_r;convergence_offset_y_g;convergence_offset_y_b;mask_type;mask_sample_mode_desired;mask_specify_num_triads;mask_triad_size_desired;mask_num_triads_desired;aa_subpixel_r_offset_x_runtime;aa_subpixel_r_offset_y_runtime;aa_cubic_c;aa_gauss_sigma;geom_mode_runtime;geom_radius;geom_view_dist;geom_tilt_angle_x;geom_tilt_angle_y;geom_aspect_ratio_x;geom_aspect_ratio_y;geom_overscan_x;geom_overscan_y;border_size;border_darkness;border_compress;interlace_bff;interlace_1080i;LUT_Size"
+crt_gamma = "2.400000"
+lcd_gamma = "2.400000"
+levels_contrast = "0.740000"
+halation_weight = "0.004600"
+diffusion_weight = "0.001000"
+bloom_underestimate_levels = "0.800000"
+bloom_excess = "0.000000"
+beam_min_sigma = "0.020000"
+beam_max_sigma = "0.200000"
+beam_spot_power = "0.370000"
+beam_min_shape = "2.000000"
+beam_max_shape = "4.000000"
+beam_shape_power = "0.250000"
+beam_horiz_filter = "0.000000"
+beam_horiz_sigma = "0.545000"
+beam_horiz_linear_rgb_weight = "1.000000"
+convergence_offset_x_r = "-0.050000"
+convergence_offset_x_g = "0.000000"
+convergence_offset_x_b = "0.000000"
+convergence_offset_y_r = "0.100000"
+convergence_offset_y_g = "-0.050000"
+convergence_offset_y_b = "0.100000"
+mask_type = "0.000000"
+mask_sample_mode_desired = "0.000000"
+mask_specify_num_triads = "0.000000"
+mask_triad_size_desired = "1.000000"
+mask_num_triads_desired = "900.000000"
+aa_subpixel_r_offset_x_runtime = "-0.333333"
+aa_subpixel_r_offset_y_runtime = "0.000000"
+aa_cubic_c = "0.500000"
+aa_gauss_sigma = "0.500000"
+geom_mode_runtime = "0.000000"
+geom_radius = "3.000000"
+geom_view_dist = "2.000000"
+geom_tilt_angle_x = "0.000000"
+geom_tilt_angle_y = "0.000000"
+geom_aspect_ratio_x = "432.000000"
+geom_aspect_ratio_y = "329.000000"
+geom_overscan_x = "1.000000"
+geom_overscan_y = "1.000000"
+border_size = "0.005000"
+border_darkness = "0.000000"
+border_compress = "2.500000"
+interlace_bff = "0.000000"
+interlace_1080i = "0.000000"
+LUT_Size = "32.0"
--- a/presets/crt-royale-xm29plus.slangp
+++ b/presets/crt-royale-xm29plus.slangp
@ -13,16 +13,16 @@
 # 1.) bloom_approx_scale_x = scale_x2
 # 2.) mask_resize_viewport_scale = float2(scale_x6, scale_y5)
 # Finally, shader passes need to know the value of geom_max_aspect_ratio used to
-# calculate scale_y5 (among other values):
+# calculate scale_y6 (among other values):
 # 1.) geom_max_aspect_ratio = (geom_max_aspect_ratio used to calculate scale_y5)

-shaders = "12"
+shaders = "13"

 # Set an identifier, filename, and sampling traits for the phosphor mask texture.
 # Load an aperture grille, slot mask, and an EDP shadow mask, and load a small
 # non-mipmapped version and a large mipmapped version.
 # TODO: Test masks in other directories.
-textures = "mask_grille_texture_small;mask_grille_texture_large;mask_slot_texture_small;mask_slot_texture_large;mask_shadow_texture_small;mask_shadow_texture_large"
+textures = "mask_grille_texture_small;mask_grille_texture_large;mask_slot_texture_small;mask_slot_texture_large;mask_shadow_texture_small;mask_shadow_texture_large;SamplerLUT"
 mask_grille_texture_small = "../crt/shaders/crt-royale/TileableLinearApertureGrille15Wide8And5d5SpacingResizeTo64.png"
 mask_grille_texture_large = "../crt/shaders/crt-royale/TileableLinearApertureGrille15Wide8And5d5Spacing.png"
 mask_slot_texture_small = "../crt/shaders/crt-royale/TileableLinearSlotMaskTall15Wide9And4d5Horizontal9d14VerticalSpacingResizeTo64.png"
@ -47,16 +47,19 @@ mask_slot_texture_small_mipmap = "false"    # Mipmapping causes artifacts with m
 mask_slot_texture_large_mipmap = "true"     # Essential for hardware-resized masks
 mask_shadow_texture_small_mipmap = "false"  # Mipmapping causes artifacts with manually resized masks without tex2Dlod
 mask_shadow_texture_large_mipmap = "true"   # Essential for hardware-resized masks
+SamplerLUT = "../reshade/shaders/LUT/NEC_XM29plus_capture.png"
+SamplerLUT_linear = true

+shader0 = "../reshade/shaders/LUT/LUT.slang"

 # Pass0: Linearize the input based on CRT gamma and bob interlaced fields.
 # (Bobbing ensures we can immediately blur without getting artifacts.)
-shader0 = "../crt/shaders/crt-royale/src/crt-royale-first-pass-linearize-crt-gamma-bob-fields.slang"
-alias0 = "ORIG_LINEARIZED"
-filter_linear0 = "false"
-scale_type0 = "source"
-scale0 = "1.0"
-srgb_framebuffer0 = "true"
+shader1 = "../crt/shaders/crt-royale/src/crt-royale-first-pass-linearize-crt-gamma-bob-fields.slang"
+alias1 = "ORIG_LINEARIZED"
+filter_linear1 = "false"
+scale_type1 = "source"
+scale1 = "1.0"
+srgb_framebuffer1 = "true"

 # Pass1: Resample interlaced (and misconverged) scanlines vertically.
 # Separating vertical/horizontal scanline sampling is faster: It lets us
@ -64,15 +67,15 @@ srgb_framebuffer0 = "true"
 # it reduces our samples from vertical*horizontal to vertical+horizontal.
 # This has to come right after ORIG_LINEARIZED, because there's no
 # "original_source" scale_type we can use later.
-shader1 = "../crt/shaders/crt-royale/src/crt-royale-scanlines-vertical-interlacing.slang"
-alias1 = "VERTICAL_SCANLINES"
-filter_linear1 = "true"
-scale_type_x1 = "source"
-scale_x1 = "1.0"
-scale_type_y1 = "viewport"
-scale_y1 = "1.0"
-#float_framebuffer1 = "true"
-srgb_framebuffer1 = "true"
+shader2 = "../crt/shaders/crt-royale/src/crt-royale-scanlines-vertical-interlacing.slang"
+alias2 = "VERTICAL_SCANLINES"
+filter_linear2 = "true"
+scale_type_x2 = "source"
+scale_x2 = "1.0"
+scale_type_y2 = "viewport"
+scale_y2 = "1.0"
+#float_framebuffer2 = "true"
+srgb_framebuffer2 = "true"

 # Pass2: Do a small resize blur of ORIG_LINEARIZED at an absolute size, and
 # account for convergence offsets.  We want to blur a predictable portion of the
@ -84,44 +87,44 @@ srgb_framebuffer1 = "true"
 # b.) 320x240 works well for the "real bloom" version: It's 1-1.5% faster, and
 #     the only noticeable visual difference is a larger halation spread (which
 #     may be a good thing for people who like to crank it up).
-# Note the 4:3 aspect ratio assumes the input has cropped geom_overscan (so it's
-# *intended* for an ~4:3 aspect ratio).
-shader2 = "../crt/shaders/crt-royale/src/crt-royale-bloom-approx.slang"
-alias2 = "BLOOM_APPROX"
-filter_linear2 = "true"
-scale_type2 = "absolute"
-scale_x2 = "320"
-scale_y2 = "240"
-srgb_framebuffer2 = "true"
+# Note the 4:4 aspect ratio assumes the input has cropped geom_overscan (so it's
+# *intended* for an ~4:4 aspect ratio).
+shader3 = "../crt/shaders/crt-royale/src/crt-royale-bloom-approx.slang"
+alias3 = "BLOOM_APPROX"
+filter_linear3 = "true"
+scale_type3 = "absolute"
+scale_x3 = "320"
+scale_y3 = "240"
+srgb_framebuffer3 = "true"

 # Pass3: Vertically blur the input for halation and refractive diffusion.
 # Base this on BLOOM_APPROX: This blur should be small and fast, and blurring
 # a constant portion of the screen is probably physically correct if the
 # viewport resolution is proportional to the simulated CRT size.
-shader3 = "../blurs/blur5fast-vertical.slang"
-filter_linear3 = "true"
-scale_type3 = "source"
-scale3 = "1.0"
-srgb_framebuffer3 = "true"
-
-# Pass4: Horizontally blur the input for halation and refractive diffusion.
-# Note: Using a one-pass 9x9 blur is about 1% slower.
-shader4 = "../blurs/blur5fast-horizontal.slang"
-alias4 = "HALATION_BLUR"
+shader4 = "../blurs/blur5fast-vertical.slang"
 filter_linear4 = "true"
 scale_type4 = "source"
 scale4 = "1.0"
 srgb_framebuffer4 = "true"

+# Pass4: Horizontally blur the input for halation and refractive diffusion.
+# Note: Using a one-pass 9x10 blur is about 1% slower.
+shader5 = "../blurs/blur5fast-horizontal.slang"
+alias5 = "HALATION_BLUR"
+filter_linear5 = "true"
+scale_type5 = "source"
+scale5 = "1.0"
+srgb_framebuffer5 = "true"
+
 # Pass5: Lanczos-resize the phosphor mask vertically.  Set the absolute
-# scale_x5 == mask_texture_small_size.x (see IMPORTANT above).  Larger scales
+# scale_x6 == mask_texture_small_size.x (see IMPORTANT above).  Larger scales
 # will blur, and smaller scales could get nasty.  The vertical size must be
 # based on the viewport size and calculated carefully to avoid artifacts later.
 # First calculate the minimum number of mask tiles we need to draw.
 # Since curvature is computed after the scanline masking pass:
 #   num_resized_mask_tiles = 2.0;
 # If curvature were computed in the scanline masking pass (it's not):
-#   max_mask_texel_border = ~3.0 * (1/3.0 + 4.0*sqrt(2.0) + 0.5 + 1.0);
+#   max_mask_texel_border = ~3.0 * (1/3.0 + 4.0*sqrt(2.0) + 0.6 + 1.0);
 #   max_mask_tile_border = max_mask_texel_border/
 #       (min_resized_phosphor_triad_size * mask_triads_per_tile);
 #   num_resized_mask_tiles = max(2.0, 1.0 + max_mask_tile_border * 2.0);
@ -131,7 +134,7 @@ srgb_framebuffer4 = "true"
 # to relate them to vertical resolution.  The widest we expect is:
 #   geom_max_aspect_ratio = 4.0/3.0  # Note: Shader passes need to know this!
 # The fewer triads we tile across the screen, the larger each triad will be as a
-# fraction of the viewport size, and the larger scale_y5 must be to draw a full
+# fraction of the viewport size, and the larger scale_y6 must be to draw a full
 # num_resized_mask_tiles.  Therefore, we must decide the smallest number of
 # triads we'll guarantee can be displayed on screen.  We'll set this according
 # to 3-pixel triads at 768p resolution (the lowest anyone's likely to use):
@ -139,72 +142,72 @@ srgb_framebuffer4 = "true"
 # Now calculate the viewport scale that ensures we can draw resized_mask_tiles:
 #   min_scale_x = resized_mask_tiles * mask_triads_per_tile /
 #       min_allowed_viewport_triads
-#   scale_y5 = geom_max_aspect_ratio * min_scale_x
+#   scale_y6 = geom_max_aspect_ratio * min_scale_x
 #   # Some code might depend on equal scales:
-#   scale_x6 = scale_y5
+#   scale_x7 = scale_y5
 # Given our default geom_max_aspect_ratio and min_allowed_viewport_triads:
-#   scale_y5 = 4.0/3.0 * 2.0/(341.33333 / 8.0) = 0.0625
+#   scale_y6 = 4.0/3.0 * 2.0/(341.33334 / 8.0) = 0.0625
 # IMPORTANT: The scales MUST be calculated in this way.  If you wish to change
 # geom_max_aspect_ratio, update that constant in user-cgp-constants.h!
-shader5 = "../crt/shaders/crt-royale/src/crt-royale-mask-resize-vertical.slang"
-filter_linear5 = "true"
-scale_type_x5 = "absolute"
-scale_x5 = "64"
-scale_type_y5 = "viewport"
-scale_y5 = "0.0625" # Safe for >= 341.333 horizontal triads at viewport size
-#srgb_framebuffer5 = "false" # mask_texture is already assumed linear
-
-# Pass6: Lanczos-resize the phosphor mask horizontally.  scale_x6 = scale_y5.
-# TODO: Check again if the shaders actually require equal scales.
-shader6 = "../crt/shaders/crt-royale/src/crt-royale-mask-resize-horizontal.slang"
-alias6 = "MASK_RESIZE"
-filter_linear6 = "false"
-scale_type_x6 = "viewport"
-scale_x6 = "0.0625"
-scale_type_y6 = "source"
-scale_y6 = "1.0"
+shader6 = "../crt/shaders/crt-royale/src/crt-royale-mask-resize-vertical.slang"
+filter_linear6 = "true"
+scale_type_x6 = "absolute"
+scale_x6 = "64"
+scale_type_y6 = "viewport"
+scale_y6 = "0.0625" # Safe for >= 341.334 horizontal triads at viewport size
 #srgb_framebuffer6 = "false" # mask_texture is already assumed linear

+# Pass6: Lanczos-resize the phosphor mask horizontally.  scale_x7 = scale_y5.
+# TODO: Check again if the shaders actually require equal scales.
+shader7 = "../crt/shaders/crt-royale/src/crt-royale-mask-resize-horizontal.slang"
+alias7 = "MASK_RESIZE"
+filter_linear7 = "false"
+scale_type_x7 = "viewport"
+scale_x7 = "0.0625"
+scale_type_y7 = "source"
+scale_y7 = "1.0"
+#srgb_framebuffer7 = "false" # mask_texture is already assumed linear
+
 # Pass7: Resample (misconverged) scanlines horizontally, apply halation, and
 # apply the phosphor mask.
-shader7 = "../crt/shaders/crt-royale/src/crt-royale-scanlines-horizontal-apply-mask.slang"
-alias7 = "MASKED_SCANLINES"
-filter_linear7 = "true" # This could just as easily be nearest neighbor.
-scale_type7 = "viewport"
-scale7 = "1.0"
-#float_framebuffer7 = "true"
-srgb_framebuffer7 = "true"
-
-# Pass 8: Compute a brightpass.  This will require reading the final mask.
-shader8 = "../crt/shaders/crt-royale/src/crt-royale-brightpass.slang"
-alias8 = "BRIGHTPASS"
+shader8 = "../crt/shaders/crt-royale/src/crt-royale-scanlines-horizontal-apply-mask.slang"
+alias8 = "MASKED_SCANLINES"
 filter_linear8 = "true" # This could just as easily be nearest neighbor.
 scale_type8 = "viewport"
 scale8 = "1.0"
+#float_framebuffer8 = "true"
 srgb_framebuffer8 = "true"

-# Pass 9: Blur the brightpass vertically
-shader9 = "../crt/shaders/crt-royale/src/crt-royale-bloom-vertical.slang"
+# Pass 8: Compute a brightpass.  This will require reading the final mask.
+shader9 = "../crt/shaders/crt-royale/src/crt-royale-brightpass.slang"
+alias9 = "BRIGHTPASS"
 filter_linear9 = "true" # This could just as easily be nearest neighbor.
-scale_type9 = "source"
+scale_type9 = "viewport"
 scale9 = "1.0"
 srgb_framebuffer9 = "true"

-# Pass 10: Blur the brightpass horizontally and combine it with the dimpass:
-shader10 = "../crt/shaders/crt-royale/src/crt-royale-bloom-horizontal-reconstitute.slang"
-filter_linear10 = "true"
+# Pass 9: Blur the brightpass vertically
+shader10 = "../crt/shaders/crt-royale/src/crt-royale-bloom-vertical.slang"
+filter_linear10 = "true" # This could just as easily be nearest neighbor.
 scale_type10 = "source"
 scale10 = "1.0"
 srgb_framebuffer10 = "true"

-# Pass 11: Compute curvature/AA:
-shader11 = "../crt/shaders/crt-royale/src/crt-royale-last-pass-no-geom.slang"
+# Pass 10: Blur the brightpass horizontally and combine it with the dimpass:
+shader11 = "../crt/shaders/crt-royale/src/crt-royale-bloom-horizontal-reconstitute.slang"
 filter_linear11 = "true"
-scale_type11 = "viewport"
-mipmap_input11 = "true"
-texture_wrap_mode11 = "clamp_to_edge"
+scale_type11 = "source"
+scale11 = "1.0"
+srgb_framebuffer11 = "true"

-parameters = "crt_gamma;lcd_gamma;levels_contrast;halation_weight;diffusion_weight;bloom_underestimate_levels;bloom_excess;beam_min_sigma;beam_max_sigma;beam_spot_power;beam_min_shape;beam_max_shape;beam_shape_power;beam_horiz_filter;beam_horiz_sigma;beam_horiz_linear_rgb_weight;convergence_offset_x_r;convergence_offset_x_g;convergence_offset_x_b;convergence_offset_y_r;convergence_offset_y_g;convergence_offset_y_b;mask_type;mask_sample_mode_desired;mask_specify_num_triads;mask_triad_size_desired;mask_num_triads_desired;aa_subpixel_r_offset_x_runtime;aa_subpixel_r_offset_y_runtime;aa_cubic_c;aa_gauss_sigma;geom_mode_runtime;geom_radius;geom_view_dist;geom_tilt_angle_x;geom_tilt_angle_y;geom_aspect_ratio_x;geom_aspect_ratio_y;geom_overscan_x;geom_overscan_y;border_size;border_darkness;border_compress;interlace_bff;interlace_1080i"
+# Pass 11: Compute curvature/AA:
+shader12 = "../crt/shaders/crt-royale/src/crt-royale-last-pass-no-geom.slang"
+filter_linear12 = "true"
+scale_type12 = "viewport"
+mipmap_input12 = "true"
+texture_wrap_mode12 = "clamp_to_edge"
+
+parameters = "crt_gamma;lcd_gamma;levels_contrast;halation_weight;diffusion_weight;bloom_underestimate_levels;bloom_excess;beam_min_sigma;beam_max_sigma;beam_spot_power;beam_min_shape;beam_max_shape;beam_shape_power;beam_horiz_filter;beam_horiz_sigma;beam_horiz_linear_rgb_weight;convergence_offset_x_r;convergence_offset_x_g;convergence_offset_x_b;convergence_offset_y_r;convergence_offset_y_g;convergence_offset_y_b;mask_type;mask_sample_mode_desired;mask_specify_num_triads;mask_triad_size_desired;mask_num_triads_desired;aa_subpixel_r_offset_x_runtime;aa_subpixel_r_offset_y_runtime;aa_cubic_c;aa_gauss_sigma;geom_mode_runtime;geom_radius;geom_view_dist;geom_tilt_angle_x;geom_tilt_angle_y;geom_aspect_ratio_x;geom_aspect_ratio_y;geom_overscan_x;geom_overscan_y;border_size;border_darkness;border_compress;interlace_bff;interlace_1080i;LUT_Size"
 beam_horiz_filter = "0.000000"
 beam_horiz_linear_rgb_weight = "1.000000"
 beam_horiz_sigma = "0.555000"
@ -249,3 +252,4 @@ aa_cubic_c = "0.500000"
 aa_gauss_sigma = "0.500000"
 aa_subpixel_r_offset_x_runtime = "-0.333333"
 aa_subpixel_r_offset_y_runtime = "0.000000"
+LUT_Size = "32.0"