QGO - PromptingReal - QGO - PromptingReal - v1

NSFW

Hello world

Let's get real

It's been a while since the last update, and this iteration is quite different than the last. That's not to say it is necessarily groundbreaking compared to anything else on this website (it's a merge after all), but I've tried to focus on a couple of very specific things:

A high amount of realism without any use of LoRAs or embeddings.
Having a good basis provides a lot of room to go crazy with those later.
Functional with a limited/small negative prompt.
Similarly, a small negative prompt often makes for the most realistic outputs. It is always possible to write your novel, or add embeddings in there along the way.
Consistency in poses / hands / other features within these constraints.
Decent control over light and darkness through prompt alone
There are great LoRAs out there for lighting / noise offset, but there is already some great functionality by default.
Responsiveness to the wildest lists of wildcards ChatGPT has to offer.
I like to have random lists of locations, time periods, clothing/materials, concepts, all generated (and embellished) by your local GPT.

Recommended VAE (not included): vae-ft-mse-840000-ema-pruned

-High base resolutions are advised: such as 640x896 for a portrait format

-If possible use hires.fix or a similar implementation: a denoise of 0.3~0.5 will do well in most situations various ESRGAN upscalers give good results. x1_ITF_SkinDiffDetail_Lite_v1 is the one used in all examples here, but there are other great options.

-Don't feel obligated to use time consuming samplers such as the one in most examples. I was suffering from a short bout of SDE Karras addiction when generating the examples, but I have since come back to 2M Karras @ 15~20 steps, which is usually my baseline and more than fine on its own (even with hires.fix).

*Note that some of the example prompts can generate nudity, prompt against this to prevent it. For actual examples of nudity you can check out the album uploaded separately.

**The model in the metadata is QGO-3002a, which is the same as QGO-PromptingReal-v1

Description

A high amount of realism without any use of LoRAs or embeddings.
Having a good basis provides a lot of room to go crazy with those later.
Functional with a limited/small negative prompt.
Similarly, a small negative prompt often makes for the most realistic outputs. There is always room to write your novel, or add embeddings in there later.
Consistency in poses / hands / other features within these constraints.
Responsiveness to the wildest lists of wildcards ChatGPT has to offer.
I like to have random lists of locations, time periods, clothing/materials, concepts, all generated (and embellished) by your local GPT.

Recommended VAE (not included): vae-ft-mse-840000-ema-pruned

*Note that some of the example prompts can generate nudity, prompt against this to prevent it. For actual examples of nudity you can check out the album uploaded separately.

**The model in the metadata is QGO-3002a, which is the same as QGO-PromptingReal-v1

FAQ

Comments (23)

OttoDAIJun 5, 2023· 3 reactions

CivitAI

This is quickly becoming my favorite realistic model.

tymis86Jun 5, 2023

CivitAI

what is this file? were put him? x1_ITF_SkinDiffDetail_Lite_v1

QEGo

Author

Jun 6, 2023· 3 reactions

This is an upscaler (for hires.fix for example), it goes in: [Stable Diffusion folder] \models \ ESRGAN
there quire a few good options to choose from in terms of upscaling, but the examples use this one for the hires.fix

hagane_no_kintamaJun 9, 2023

CivitAI

Sometimes the qgo10a model is referred as qgo10a_qgo10a is this just a naming issue or is it another model (I don't have the hash of the other model)

QEGo

Author

Jun 10, 2023

I'm pretty sure that's always just the same model, it's Civitai (or my mistake :D) that duplicates the model names.

hagane_no_kintamaJun 11, 2023

Thank you for the clarification and Thank you for the good model.

anon10661215Jun 11, 2023· 1 reaction

CivitAI

Great work! Thank you.

djsvJun 18, 2023· 3 reactions

CivitAI

This is my my favorite!

jcc021058Jun 21, 2023· 3 reactions

CivitAI

should i put it in the lora folder?

FewJun 24, 2023· 4 reactions

no, this goes into your \stable-diffusion-webui\models\Stable-diffusion file ( could be a different directory based on where you located your folder or named them :)

jcc021058Jun 24, 2023

@saudi Thanks very much!

odakyu11Jun 30, 2023

CivitAI

file 'qgo10b_qgo10bFixFixedCLIP.ckpt' came up with a trojan warning on windows defender.

avernalvigilAug 3, 2023· 4 reactions

CivitAI

To me this is gold

Especially since it always gave me the best girls 😂

(with no need to use a dozen LORAs)

I hope the author hasn't abandoned it and publishes a new version

dragonalumniSep 12, 2023· 1 reaction