Recent content by yano2mch

Currently plugged in Klein in and... getting mostly decent results, having it scan json files and making an image to represent the character/intent. Mind you these are cards that had their image removed for some reason? So generated replacement images is kinda what this is for. I'll look over...

Mhmm. Well Z-image fits on my video card (Q4 and Q6), i might be able to do on another computer that has 16GB VRam but i don't want to boot it up and then have it idle most of the time. I'll try other models, depending on what gives the best result for the project. Tried Minmax H3 as well...

You can also do it via Notepad++, well if you use it already like me. Use Mac or Linux? Open a terminal and use the following: (Paste text, enter followed by Ctrl+D) cat | base64 -d #one pass cat | base64 -d | base64 -d #two passes Omni might be the only style worth using. Wish they left...

Currently experimenting with Z-Image Turbo (or ZIT). Working on a commandline that will in theory take a character card without an image, extract the text needed and make an image cover, then create the image and save it. Course generating 1024x1024 images are fairly slow, while doing a...

A few months ago Gemma4 model came out. I wrote it off as not being useful for OCR work, but recently found that it was a pipeline of uploading an image to be badly compressed so the OCR results were useless at that time. But sending the unmodified jpeg resulted in very decent work. As such an...

In search doesn't look like it's allowed; Part of a collection? Yes you can. Though with collections pushing 500+ books and 'function undefined' making you reload the whole thing ~40 books at a time is annoying to get back to where you were.

The file's complete, since the zip TOC is at the end otherwise you couldn't even open it. The book's contents are incomplete. It's a technical difference. Looked in my classic folder and found it too, but the chapter is 8k (The raw text of other books tends to be ~100k). Scanning what i have i...

Well i suppose the advantage of Rar format, is it's aware of jpeg and some audio/video codecs so it can squeeze a little more from those; though that was more important pre-2010. 7zip i almost exclusively use the right-click context menu to compress or extract archives, and use the little...

Hmmm interesting. Bet a little optimization could have reduced several hundred megs, or more. Bit of a pain every post is over a gig. edit: A lot of PDF's that could have optimization or be unoptimized and let lzma do a better job; jpegs that could be optimized and then leaving uncompressed in...

Another option is to concatenate them to a single file. A LOT easier if you use MinGW/CygWin or Linux. #Linux/Unix cat Archive* > Archive.7z #windows, i think this was how you do it copy /B Archive.zip.001+Archive.zip.002+Archive.zip.003 Archive.zip But i would certainly rely on 7zip first.

I wrote a script to do the same thing for epubs, stripping formatting and unneeded blocks, and do each paragraph separately. Compresses to about 200Mb per book. Unfortunately it's not consistent person output, which you can get around or not. If i find a way to make it consistent i'd be more...

I see several models that are promising, though using specific wording and Lora would help keep consistency; but only if it's already trained. Inpainting and other may work and just re-rolling until outfits or workable scenes may work too. I need to test, but i think you might be better using...

Could. Though i'd downloaded from Anne's Archive on stuff and found OceanOfPDF instances. So not sure. Honestly it's not the worst possible injection, but it is annoying when it breaks sentences or paragraphs and is on every page. This i also wrote like 2 years ago, but converted to make it...

Bonsai put out a 4B/8B 1bit model some months back. It was.... okay.... as an experiment and proof of concept i wasn't that thrilled. However they've recently put out a 27B 1bit model, which is just under 4Gb, along with a webui you can have a LLM on a DVD (Though the 20 minutes to copy to RAM...

If you were using 7zip, just 7z -x "MrDouble 2.zip.001" should have worked. you could also unzip it with the unzip command once concatenated. the test in it showed no errors when i ran it, thus it should extract just fine without 7zip at that point. Still long as it works it doesn't matter...