You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
* Adds the models I created for the Super Mario Bros Super Show. Note that the large model is actually a 2x model, but I used a 4x model as the base (apparently that's allowed). Each entry has two resources because there is a live-action and animated model (users are expected to interpolate them for things like the opening sequence).
* Rename large model file to avoid confusion
* Add NES Composite to RGB Model
* Add Digital Pokemon models
* Add "Where on Earth" repair models, updates NES Composite upscale
* Add Mega Man II sample from "The Wizard"
* Update "Where on Earth" deinterlace fix models, add upscaling models, create "Where on Earth" collection
* Minor text/tag fixes
* database fix
Copy file name to clipboardExpand all lines: data/collections.json
+19-8Lines changed: 19 additions & 8 deletions
Original file line number
Diff line number
Diff line change
@@ -28,6 +28,16 @@
28
28
"2x-AnimeSharpV4-Fast-RCAN-PU"
29
29
]
30
30
},
31
+
"c-gameup": {
32
+
"name": "GameUp",
33
+
"description": "GameUp is a set of video upscaling models intended for upscaling and restoring video game footage",
34
+
"models": [
35
+
"2x-GameUpV2-TSCUNet",
36
+
"2x-GameUpV2-TSCUNet-Small",
37
+
"2x-GameUp-TSCUNet"
38
+
],
39
+
"author": "kim2091"
40
+
},
31
41
"c-normal-map-upscaling": {
32
42
"name": "Normal Map Upscaling",
33
43
"description": "This collection contain my RG0 normal map upscaling models.\n\nAll models here are for upscaling *tangent-space* normal maps in RG0 format. RG0 means that the B channel is set to 0. These models will work not correctly if you give them images with non-zero B channel, so you either have to zero the B channel manually or use tool like chaiNNer to do it.\n\n## DDS Compression\n\nI made 3 versions: \n- Normal RG0 is for uncompressed normal map textures. Since it hasn't been trained on compression artifacts, it's highly sensitive to quantization artifacts and noise.\n- Normal RG0 BC1 is for BC1-compressed DDS normal map textures.\n- Normal RG0 BC7 is for BC7-compressed DDS normal map textures. This model sometimes produces images that aren't as sharp. In those cases, you can try the BC1 version to see whether it gives better results.",
@@ -53,14 +63,15 @@
53
63
],
54
64
"author": "kim2091"
55
65
},
56
-
"c-gameup": {
57
-
"name": "GameUp",
58
-
"description": "GameUp is a set of video upscaling models intended for upscaling and restoring video game footage",
66
+
"c-where-on-earth-is-carmen-sandiego-": {
67
+
"name": "Where On Earth Is Carmen Sandiego?",
68
+
"author": "pokepress",
69
+
"description": "Collection of models for use in restoration and upscaling of the TV series \"Where on Earth is Carmen Sandiego?\" from the 1990s. While primarily consisting of cel-based animation, the show also incorporates live-action (including stock footage and scenes involving \"The Player\"), 3D CGI (primarily used for the C5 Corridor), and 2D computer animation. The models are divided into two groups:\n\n* Deinterlace Fix\n* Upscaling\n\nThe deinterlacing fox models are primarily designed for the 2012 Mill Creek release, where a number of episodes have some rather harsh forced deinterlacing, which the models attempt to repair. These models may also be useful for improving picture quality in some scenes (primarily in seasons 3 and 4) that used deinterlacing as part of compositing multiple layers of images, and for improving the results of deinterlacing by QTGMC or other processes.\n\nSpeaking of deinterlacing, for episodes in 480i, I recommend using QTGMC to deinterlace them to 60 (59.97) fps, the frame rate of the live-action and (some) C5 Corridor footage. For the pre-deinterlaced episodes, you're going to be stuck at 30 fps since the other-frame information has already been removed. Despite this series being primarily cel-based animation, I **don't** recommend using 24 fps as it tends to make higher-framerate portions look odd.\n\nThe upscaling models work pretty much how you would expect.\n\nEach model has a small and large variant. The large variants are based on the OmniSR architecture, and tend to produce better results (marginally so in the case of the deinterlacing fix), but are several times slower than the small models, which use the compact architecture.",
Copy file name to clipboardExpand all lines: data/models/1x-WhereOnEarthDeintFixL.json
+21-12Lines changed: 21 additions & 12 deletions
Original file line number
Diff line number
Diff line change
@@ -4,10 +4,11 @@
4
4
"license": "MIT",
5
5
"tags": [
6
6
"cartoon",
7
-
"restoration"
7
+
"restoration",
8
+
"video-frame"
8
9
],
9
-
"description": "The \"Complete Series\" release of \"Where on Earth is Carmen Sandiego?\" by Mill Creek has a number of episodes that suffer from some rather harsh deinterlacing. This model attempts to restore the footage to something closer to a more advanced deinterlacing job.",
10
-
"date": "2025-06-29",
10
+
"description": "The \"Complete Series\" release of \"Where on Earth is Carmen Sandiego?\" by Mill Creek has a number of episodes that suffer from some rather harsh deinterlacing. This model attempts to restore the footage to something closer to a more advanced deinterlacing job. It may also be useful on episodes (primarily found in seasons 3 & 4) that were produced with advanced compositing where certain layers used similar forced deinterlacing techniques, and for cleaning up artifacts left by Yadif, QTGMC, etc.\n\nRevision History:\n* v1.1.0: Added data to improve handing of certain situations, particularly in season 3.\n* v1.0.0: Initial release.",
Copy file name to clipboardExpand all lines: data/models/1x-WhereOnEarthDeintFixS.json
+21-12Lines changed: 21 additions & 12 deletions
Original file line number
Diff line number
Diff line change
@@ -4,9 +4,10 @@
4
4
"license": "MIT",
5
5
"tags": [
6
6
"cartoon",
7
-
"restoration"
7
+
"restoration",
8
+
"video-frame"
8
9
],
9
-
"description": "The \"Complete Series\" release of \"Where on Earth is Carmen Sandiego?\" by Mill Creek has a number of episodes that suffer from some rather harsh deinterlacing. This model attempts to restore the footage to something closer to a more advanced deinterlacing job.",
10
+
"description": "The \"Complete Series\" release of \"Where on Earth is Carmen Sandiego?\" by Mill Creek has a number of episodes that suffer from some rather harsh deinterlacing. This model attempts to restore the footage to something closer to a more advanced deinterlacing job. It may also be useful on episodes (primarily found in seasons 3 & 4) that were produced with advanced compositing where certain layers used similar forced deinterlacing techniques, and for cleaning up artifacts left by Yadif, QTGMC, etc.\n\nRevision History:\n* v1.1.0: Added data to improve handing of certain situations, particularly in season 3.\n* v1.0.0: Initial release.",
"description": "Upscaling model for 1990s cartoon series \"Where on Earth is Carmen Sandiego?\" May also be useful for other shows of that era.\n\nNote: Before using this model, you will need to either:\n* Deinterlace the episodes (I recommend QTGMC on Slower) to 60 fps (I recommend 60 fps because that's the rate of the live-action footage and some other components).\n* Repair the existing deinterlacing via one of the related models for this show.\nWhich method will depend on the episode and release. See the related deinterlacing models for details.\n\nThis show is...complicated. Unlike, say, the Super Mario Bros. Super Show, where live action and animated segments are generally separated into large chunks, Where on Earth is Carmen Sandiego repeatedly switches between live-action, traditional animation, 3D CGI, 2D computer graphics, stock photography, and other sources, sometimes combining them in the same frame. As such, rather than create multiple models for each type, I've created a single model for all footage types.\n\nKnown Weaknesses:\n* The model performs less well on the live-action (Player) and 3D CGI (C5 Corridor) segments due to a scarcity of usable data in those scenes.\n* I don't own the 2025 DVD release, so I can't comment on how well this model works on that footage.",
"description": "Upscaling model for 1990s cartoon series \"Where on Earth is Carmen Sandiego?\" May also be useful for other shows of that era.\n\nNote: Before using this model, you will need to either:\n* Deinterlace the episodes (I recommend QTGMC on Slower) to 60 fps (I recommend 60 fps because that's the rate of the live-action footage and some other components).\n* Repair the existing deinterlacing via one of the related models for this show.\nWhich method will depend on the episode and release. See the related deinterlacing models for details.\n\nThis show is...complicated. Unlike, say, the Super Mario Bros. Super Show, where live action and animated segments are generally separated into large chunks, Where on Earth is Carmen Sandiego repeatedly switches between live-action, traditional animation, 3D CGI, 2D computer graphics, stock photography, and other sources, sometimes combining them in the same frame. As such, rather than create multiple models for each type, I've created a single model for all footage types.\n\nKnown Weaknesses:\n* The model performs less well on the live-action (Player) and 3D CGI (C5 Corridor) segments due to a scarcity of usable data in those scenes.\n* I don't own the 2025 DVD release, so I can't comment on how well this model works on that footage.",
0 commit comments