Search found 9 matches

by Max-Plank
Mon Oct 27, 2025 10:05 am
Forum: Art Contributions
Topic: [AI Technique] Banter, shared ideas, and frustrations
Replies: 13
Views: 12651

Re: [AI Technique] Banter, shared ideas, and frustrations

xs70 wrote: Mon Oct 27, 2025 3:56 am A special edition for lovers of pointy things.

shannon7.jpg
https://motherless.com/68D6D64

(highres still + animation)
And here I am again with my questions :)
I understand this is an animation in Wan2.2?
Can this be achieved with a simple prompt or do I need to use specific LoRA?
by Max-Plank
Fri Oct 24, 2025 10:28 am
Forum: Art Contributions
Topic: [AI Technique] Banter, shared ideas, and frustrations
Replies: 13
Views: 12651

Re: [AI Technique] Banter, shared ideas, and frustrations

Best at creating scenes (drawing from scratch) in my experience: Non-NSFW: Flux or SDXL Photographic NSFW: SDXL Consensual NSFW: Pony Any NSFW: Illustrious I use Illustrious to create GIMP scenes from scratch: based on SDXL like Pony, it works like SDXL/Pony. But Illustrious is trained on danbooru ...
by Max-Plank
Fri Oct 24, 2025 7:20 am
Forum: Art Contributions
Topic: Experimenting with Stable Diffusion
Replies: 267
Views: 1100635

Re: Experimenting with Stable Diffusion

Thanks. ;) It depends on what family of models you use. Flux indeed won't do any of that stuff. Most Illustrious basemodels will. This image resulted from an experiment with Qwen, one of the recent new (Chinese) models. It's pure text to image, no Photoshop or specialized LoRA involved. I'm current...
by Max-Plank
Wed Oct 22, 2025 1:19 pm
Forum: Art Contributions
Topic: Experimenting with Stable Diffusion
Replies: 267
Views: 1100635

Re: Experimenting with Stable Diffusion

jennifer.jpg https://motherless.com/4250779 As always, excellent work. I noticed that basic AI models (checkpoints), even finetuned NSFW ones, can't draw unusual objects on the human body. For example, electrodes, wires, needles... You need special LoRa for that. Do you make these LoRa yourself or ...
by Max-Plank
Fri Oct 03, 2025 7:35 am
Forum: Art Contributions
Topic: Teds Pics
Replies: 84
Views: 115467

Re: Teds Pics

Ted wrote: Wed Oct 01, 2025 10:24 pm That method of upscaling doesn't resample the image using a model, so any corruption in the original image will exist in the upscaled image.
I think I understand. The method you suggested is called "inpaint" or "refine".

Can I ask you how you make such LoRA? Thank you :)
by Max-Plank
Wed Oct 01, 2025 5:27 am
Forum: Art Contributions
Topic: Teds Pics
Replies: 84
Views: 115467

Re: Teds Pics

I would be very grateful for the workflows. Is this done on a ComfyUI platform?
by Max-Plank
Tue Sep 30, 2025 9:12 am
Forum: Art Contributions
Topic: Teds Pics
Replies: 84
Views: 115467

Re: Teds Pics

3) Generate images with the base model and then upscale them with one of the other models (I use fuxCapacityNSFW) The initial image will have corruption, but the upscaling will correct it. This is the method I now use, and the above images were created using this method. Could you please elaborate ...
by Max-Plank
Mon Aug 04, 2025 4:27 pm
Forum: Art Contributions
Topic: Experimenting with Stable Diffusion
Replies: 267
Views: 1100635

Re: Experimenting with Stable Diffusion

it almost happened
it almost happened
it almost happened
by Max-Plank
Sat Aug 02, 2025 1:21 am
Forum: Art Contributions
Topic: Experimenting with Stable Diffusion
Replies: 267
Views: 1100635

Re: Experimenting with Stable Diffusion

Thanks. I've been thinking about that effect, based on your work. The short answer is that it can't be done with a prompt since there's no LoRA for it. That said, I plan to try using some of the inpainting techniques I've been working on lately, similar to the electrode needles piercing the bases o...

Go to advanced search