![]() ![]() ![]() ![]() Missing Apple Core ML files, affects 1x and 4x scale mode, missing one block size file for 1x and one for 4x, library should still functionĪrtemis LQ 6, 7, and 8 are mostly the same. ![]() Missing Open Neural Network Exchange Single Float (fp32) files, breaks 1x scale mode Missing OpenVINO files, breaks entire library Missing entire library files for Apple Core ML, breaks entire library Missing OpenVINO files, breaks entire libraries Models with missing / incomplete model files on the download server: Models visually indistinguishable from one another: Produces results visually indistinguishable from regular resize (spline, lanczos, etc.) Here’s my personal notes that I’ve taken regarding the published (i.e., live on the public server) models so far: Here’s a copy/paste of a post I made in the beta forum with some additional details: It’s probably not noticeable in final live video. In my testing, they are slightly sharper than the “beta” model files. According to developers, the “release” Artemis v9 model files have had an additional week of training. The “beta” Artemis v9 model files are no longer available as the “release” ones overwrote the “beta” ones on the download server, since they have the same file names. The following models files are missing / not available from the download server: Missing model files for download: These OpenVINO files are missing for the. VEAI will download the model files it needs automatically. Now Artemis-LQ v8 will appear in addition to Artemis-LQ v9 in VEAI. So for example, open artemis-lq-9.json, then change "version": "9", to "version": "8", and save the file as artemis-lq-8.json. BE CAREFUL not to overwrite your original JSON’s. Change the number in line 3 "version": "X", to the version you want, then save the JSON as a new file, nameing it to the corresponsing version. Your current JSON files should be located in C:\Users\Admin\AppData\Roaming\Topaz Labs LLC\Video Enhance AI\models. Then, open your current JSON file in a text editor (i.e., Notepad). To get these files, first, make sure VEAI is closed. Here are all of the current live models that may or may not work for you (try them and see) for VEAI 1.8.0: (Some users have asked Topaz to switch to Vulkan instead of DX12 which would work on Win7.) The new engine also requires DirectX 12, which means no more ability to run on Windows 7. I believe this is because 1.6.1 and earlier versions used TensorFlow, and 1.7.x is a new engine that uses Open Neural Network Exchange. The older models (1.6.1 etc) will not work in VEAI version 1.7.x and up. So my hope for such an option would simply be a less irritated AI but still having deinterlacing or even repair bad deinterlacing, since this is one problem that you definitely won’t solve afterwards.Devs : Could you make all versions of models avaiable for download ?Īnd maybe label them as v4.0, 4.1, 4.2 aso ?įor example artremis v9.0 and artremis v9.1 ( the beta and the released one ) But since I aim for at least 200% or even 400%, I found that I better use VEAI on the raw files, even if they are in pretty bad condition and do the necessary work afterwards. I indeed got pretty descent results if only used the 100% option + external filters, even with Gaia, while its the model that is the easiest to irritate. But just like I said before in this thread, I think the AIs, regardless if its Gaia or Artemis, do suffer from any interference from external tools.As you described your goal of just cleaning SD footage without much upscaling, I guess we just have very different requirements. I think QTGMC is on its own absolutely fine. The reason why I would like to combine Dione with other models, is not that I think we actually need a newer better deinterlacing method. Ok maybe I misspoke on this one I don’t want it to be the standard option for every AI in VEAI but just an option like the grain is now.īTW. But if the AI version is actually superior, since it can correct things, no matter if interlacing was done correctly in the first place, I would guess it makes sense to combine Dione with every other model? For example if you like the Gaia look, the only way to get that is to use separated deinterlacing. I was also wondering why Dione is actually a separate model, instead of a combination of things. I think it would be nice to have one model specifically for this task, so even the slight studders would not be visible anymore. But overall I would say it was able to repair and even smooth things out a bit. The only thing that could be improved is some light studder manifesting in different parts of the video. (edges are still slightly interlaced) Initially I thought with DioneTV and DV the outcome must be awful, since its not dedicated for this specific problem. I just made some tests with Dione and badly deinterlaced sources. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |