keer
Active Member
- Jun 20, 2017
- 794
- 1,688
- 389
Please, which is the file that has the suggested names we can be called and call other people, and how I edit it?
I'm interested in trying the GenAI mod, and I think I've downloaded the five .py files and one .rpy file from his Git. (I just select each file and download it, yes? Then create a folder for it called GenAI, and drop that in the Game/mods folder.)
But the Git also contains a Stable Diffusion guide, and I can't get it to open properly in a browser. I see a couple links, but none of them works. If I open the file in a text editor, or look at it directly on the Git, I can kinda read it, but I'm afraid I'm going to miss a step. Am I misunderstanding how to view this HTML file? Or can anyone repost the steps for setting up Stable Diffusion to work with this mod here?
Edit: I did manage to get Stable Diffusion running, and I seem to have successfully installed a model -- I can generate images of a woman. When I add the command-line arguments indicated by the mod's Stable Diffusion guide, the SD WebUI no longer opens, but the game did seem to communicate with SD, for a bit. It made a couple not-great images. But then I tried clicking on the GenAI Config link at the bottom of the game page, and the game crashed, and now I can't get SD to work in it. Not sure what to do.
Also, should I use GenAI with the modpack version of the game, or the basic Reformulate version?
But the Git also contains a Stable Diffusion guide, and I can't get it to open properly in a browser. I see a couple links, but none of them works. If I open the file in a text editor, or look at it directly on the Git, I can kinda read it, but I'm afraid I'm going to miss a step. Am I misunderstanding how to view this HTML file? Or can anyone repost the steps for setting up Stable Diffusion to work with this mod here?
Edit: I did manage to get Stable Diffusion running, and I seem to have successfully installed a model -- I can generate images of a woman. When I add the command-line arguments indicated by the mod's Stable Diffusion guide, the SD WebUI no longer opens, but the game did seem to communicate with SD, for a bit. It made a couple not-great images. But then I tried clicking on the GenAI Config link at the bottom of the game page, and the game crashed, and now I can't get SD to work in it. Not sure what to do.
Also, should I use GenAI with the modpack version of the game, or the basic Reformulate version?
Last edited:
Magister Crudi
Member
- May 23, 2023
- 267
- 185
- 119
Did she just steal my dick's soul?
Maybe I should count their fingers before going home with them.
Maybe I should count their fingers before going home with them.
AccidentalGadgeteer
Active Member
- Oct 8, 2020
- 834
- 1,192
- 267
Magister Crudi
Member
- May 23, 2023
- 267
- 185
- 119
You mean that's not from the LEDs on all the nanobots in her bloodstream?
Must be hard on her kidneys filtering out all those little buggers, but where would we be if we let petty considerations like that stand in the way of Science?
Is there cum oozing from her belly button?
I've finally been able to get the GenAI mod to work with LR2's modpack. My main question: I don't fully understand how to override a prompt in the GenAI Config screen. When I click override, I get a confusing little popup that is impossible to edit. I can "append" to the prompt, but I'm not sure that is doing much. I often get images that don't quite match the scene, so editing the prompt is important. How is the 'override prompt' option supposed to work?
Edit: Initially I was getting a RenPy rollback crash if I clicked the link to configure GenAI. But reinstalling and playing vanilla Reformulate has fixed that for now. (Does the GenAI mod work with the modpack version of the game too?) I'm now having some success using hibakuxa's recommended model checkpoint.
Edit: Initially I was getting a RenPy rollback crash if I clicked the link to configure GenAI. But reinstalling and playing vanilla Reformulate has fixed that for now. (Does the GenAI mod work with the modpack version of the game too?) I'm now having some success using hibakuxa's recommended model checkpoint.
Last edited:
I'm a bit of an AI noob. I have a Geforce RTX 5060 and it appears like the version of Forge won't work with my card. Is there an alternative installation I can do? I was able to install it correctly and launch it, it just can't generate any images and I noticed it said it's incompatible with my version of PyTorch on the startup. I have been able to use ComfyUI with ease up to this point, but decided I'd try getting this game to work with the GenAI mod. Any help would be greatly appreciated.
I am an AI newb too. As I understand it, Forge is a fork of Stable Diffusion, not quite the same thing. I think GenAI requires Stable Diffusion itself. If you download GenAI from its Git (or find it from posts in this thread), you'll find an .html file that explains how to set up Stable Diffusion and then the game itself. Essentially, you install SD; download a model and install that; revise the SD .bat file with command line parameters designed to link it to LR2; run LR2; and click on the GenAI link at the bottom of LR2 to set it up.
Incidentally, I dimly recall reading somewhere that 50-series GPUs might require an additional step for some AI generation? I don't know.
NaughtyAnon
Newbie
- Apr 2, 2020
- 44
- 36
- 152
So between both SD Forge and AUTOMATIC1111 SD WebUI there are issues with the NVidia Blackwell architecture (all 50XX cards) that are still being fixed. On both core repositories there are a lot of steps to try and fix things but it is still technically a dev branch.
Magister Crudi
Member
- May 23, 2023
- 267
- 185
- 119
Okay this is super helpful. I will go back to the drawing board since it appears from the other reply that Forge might not be compatible with the 50 series yet (or rather without complex alterations that I don't know if I'm skilled enough to do). I think if I can change my port to the right one on ComfyUI and add in some of the other alterations I might be able to get it to work. I'll update this if I'm able to get anywhere with this.
Okay, got it all working. First I was able to get Forge working by updating the CUDA 12.9 using this link, plus ChatGPT to help me uninstall and install:
You must be registered to see the links
Second, I had the API issue. I had put in everything correctly, but I didn't get rid of the "rem" which was a comment out. Once I got rid of that, it worked flawlessly. Thank you all for the help from previous pages!
Congrats! Glad to hear you got it working.
Now, is there a way to alter the size or placement of the images in LR2? The folks on Discord tell me to alter the GenAI code to do this, but I am not skilled enough coder to do this, and I don't see a way to do it using the GenAI configuration menu in-game.
Guys, the GenAI mod only works with AUTOMATIC1111 version of Stable Diffusion. Forge changed a bit the API, so certain things stop working at times, and SDNext uses a slightly different way to use things.
Also, some clothing confuses the AI generator so black screens or monsters are to be expected. I'm attaching a bastardized version (a.k.a. modded by me with some fixes to that.). Don't expect any support for them.
V1 is the some clothes bugfix only. Some clothes work fine, some others work randomly, and some doesn't work at all (cop dress doesn't) and dresses in particular are a difficult issue, but the original also has them, the logic is not consistent ,and from a coding standpoint, is kinda hard to follow, so no support for it from me. Maybe some day will do my own version of this, but not now. In case of doubts , just try this. NO SUPPORT!!
V2 has two added requirements: requires ADETAILER plugin for Automatic1111, and it's model "hand_yolov8s.pt" (usually, installing the plugin from the UI browser will install all of adetailer models). This is done in a try to fix the hands issues, but is not perfect, tho at least in most cases will work ok. And requires the yogis ( Stable_Yogis_PDXL_Negatives2-neg, Stable_Yogis_PDXL_Positives2) text inversors installed in the SD installation. ONLY FOR PEOPLE WHO KNOWS WHAT ARE DOING. AND NO SUPPORT!!. In doubt, use the V1 or just ignore this post entirely, and move on
.
Hopefully, some hero could redo the models of the game. One can hope
Also, some clothing confuses the AI generator so black screens or monsters are to be expected. I'm attaching a bastardized version (a.k.a. modded by me with some fixes to that.). Don't expect any support for them.
V1 is the some clothes bugfix only. Some clothes work fine, some others work randomly, and some doesn't work at all (cop dress doesn't) and dresses in particular are a difficult issue, but the original also has them, the logic is not consistent ,and from a coding standpoint, is kinda hard to follow, so no support for it from me. Maybe some day will do my own version of this, but not now. In case of doubts , just try this. NO SUPPORT!!
V2 has two added requirements: requires ADETAILER plugin for Automatic1111, and it's model "hand_yolov8s.pt" (usually, installing the plugin from the UI browser will install all of adetailer models). This is done in a try to fix the hands issues, but is not perfect, tho at least in most cases will work ok. And requires the yogis ( Stable_Yogis_PDXL_Negatives2-neg, Stable_Yogis_PDXL_Positives2) text inversors installed in the SD installation. ONLY FOR PEOPLE WHO KNOWS WHAT ARE DOING. AND NO SUPPORT!!. In doubt, use the V1 or just ignore this post entirely, and move on
.Hopefully, some hero could redo the models of the game. One can hope
Last edited:
Magister Crudi
Member
- May 23, 2023
- 267
- 185
- 119
I find it's all over the shop depending on what models you use. A good example is that few models know what 'Capris' are and so render the girls wearing them as bottomless.
I also find most models will spit the dummy beyond a certain level of prompt complexity, giving you monsters or splatterings of colour only Jackson Pollock would see as women.
I've now tried to customise AnotherMike's GenAI to several different models. StableYogi ones tend to give the best sex positions (I'd recommend realismByStableYogi_ponyV3VAE and his Porncraft models) but tend to fall short on clothes, appearances of women and backgrounds. Cyberrealistic ones are fairly good all round but are more likely to generate monsters. Both have their own sets of positive and negative prompt files (textual inversions) but they don't fix everything.
ADetailer can fix a few minor glitches (e.g. hands) and can help a lot with faces - especially when they're upside down in the piledriver position - but I'm finding it more than doubles image generation time, so when actually playing the game instead of messing with images you end up clicking through most of them and missing it. Ten seconds per image is about as far as my patience stretches and I like to keep it close to five seconds.
When I get a bit of time I'm going to start training a model to specific prompts I'll use to customise the GenAI code, but that's a fairly long term project.
Here's the tweak of AnotherMike's prompt builder I'm currently trialling with
You must be registered to see the links
and its
You must be registered to see the links
and
You must be registered to see the links
prompt embeddings. Right now I'm trying to make 'kneeling oral' work consistently. I'm using the 'Euler a' sampler, with 25 steps, CFG 9 (!) and 0.35 denoising with both img2img and basic prompts turned off. Mostly I leave upscaling and ADetailer off but sometimes switch them on for sex scenes.
Last edited:
True. Adetailer adds more time (tho, i cheat a lot here: i game on a notebook, but i do generate the images on a desktop PC). SDnext has a better detailer, but genai is not compatible. For clothing and placing (yup, places can also bork the generation) is better to keep simple, but the game models are anything but that.
Maybe sometime soon i will code a better parser for generating images, but no promises tho.
Maybe sometime soon i will code a better parser for generating images, but no promises tho.