Posts

@derp621
Ooh, nice! I looked into Gradio some time ago for a small extension and didn’t get far; a better solution in webui itself would def. be handy.

@Teaspoon
Great work!

I made something similar last year but lost interest at some point. Maybe I should start developing it again as a webui alternative to this one?

Edit: updated my project to use latest version of Gradio and added install/usage guide

I was getting annoyed with the dataset tag editor extension and other solutions felt cumbersome, so I went ahead and set this thing up to make my own life easier.

LORA:Them’s Fightin’ Herds Velvet
https://civitai.com/models/1250076/thems-fightin-herds-velvet

@Cypher
Yep, added!

1.Lora:OC: Lustrous https://civitai.com/models/1226996/my-little-ponymlp-g4-oc-lustrous

2.lora: OC:Athena https://civitai.com/models/1223922/my-little-ponymlp-g4-ocathena

Should be updated; sorry for slowness, am trying to only do this once a week :x

I use an rgthree image comparer in ComfyUI, that has a nice slider that overlays images on top of each other to spot the minor-est differences when tweaking just the small stuff:

I guess it isn’t that useful when images have big differences between them, but consider this.

@Scarlet Ribbon
Yep. Nothing fancier than that.

I just wanna be clear on the usage here … this is basically a tool that attempts to rank images in a dataset by showing you two images and asking you to pick which one you like more?

So I was looking for a simple pair comparison sort tool and all the ones I could find were ad bloated or just not good.

Why? idk. Often I gen a bunch of stuff with minor differences, or do several inpaintings in one go, or tinker with styles and end up mired in indecision. You can use it for whatever, deciding who’s best pony or which meal you want I guess.

I’ve used this one to generate Sea Swirls!

lora Mita (MiSide) was, deleted

Idk this might help
https://notebooklm.google.com/notebook/aac69946-f2cb-4959-99ac-65e0d7fe9072/audio

Lora: MLP G4 Luster Dawn https://civitai.com/models/1195836/my-little-ponymlp-g4-luster-dawn

lora: MLP G4 OC: Kimono Silk https://civitai.com/models/1169710/my-little-ponymlp-g4-oc-kimono-silk

@MareStare
(I thought that was obvious, but yes, this account is currently “Teaspoon”, at least until there’s a different “Admin” and I can just, like, enjoy pony for once…)

Lol, Teaspoon is an admin??! 😳

@Cypher
Thanks! Will add them in next pass Soon!

@Teaspoon
1.LORA:Lily Valley https://civitai.com/models/1185223
2.LORA:Mjölna https://civitai.com/models/1186001/my-little-ponymlp-g4-mjolna

I saw a couple of X Y plots ages ago, and wonder what is the best way to generate them, automatically adding image as well as the configuration that changed for them in the plot.
(Things like model, sampler, scheduler, steps, prompt, CFG, size/aspect ratio etc.)

@tyto4tme4l
It’s intended to be NSFW in my case.

@Thoryn
If it’s SFW, then maybe try prompting it in Bing Image Creator and then use the result for img2img in Stable Diffusion? Bing has a much better prompt following.

I’m struggling hard with text to image prompts getting characters to interact with furniture, prompting for them to be on something like a changing table is seemingly impossible with PonyV6 and ZoinksNoob. I’ve tried CFG from 4 to 7, and even kept the prompts to 75 blocks(?) on many of the attempts.

Figured I’d work around it by using a dresser instead, but it refuses to put characters on it.
The dresser gets identified, since if I type e.g. wooden or white dresser it usually changes accordingly, but it still puts the character on a bed, in a crib, ordinary table or the floor instead. Even when I up the strength for dresser, and puts crib and bed in negative prompts, it still includes one of them to put the character there, if not the floor.
Using alternative words for dresser, like chest of drawers, or similar things like commode, has the same outcome.

Later in the year I’ll hopefully have a better setup and can try inpainting/sketching (as if I’m not bad enough at drawing under optimal conditions already, trackpad really sucks for drawing), but for now I’m dumbfounded as to why I can’t get my prompts to work how I want. Any tips would be appreciated.