modelle/Add More Details Detail Enhancer Tweaker LoRA - v10

Add More Details Detail Enhancer Tweaker LoRA - v10

|
7/1/2024
|
9:11:31 PM
| Discussion

Empfohlene Prompts

masterpiece

Empfohlene Parameter

samplers

DPM++ 2M Karras, DPM++ SDE Karras

steps

20 - 30

cfg

4.5 - 9

resolution

512x640, 512x683, 512x704, 512x768, 512x896

other models

aka_shiba_offset, AnyLoRA_bakedVae_fp16_NOTpruned (b775b13509), mecha_offset, AbsoluteRealityV1_pruned (bfea7e18e2), cetusMix_Codaedition (bd518b9aee), DreamShaper_6_BakedVae_noema (c249d7853b), napata_offset, neon_palette_offset

Empfohlene Hires (Hochauflösungs-) Parameter

upscaler

Latent (bicubic antialiased), 4x_foolhardy_Remacri, 8x_NMKD-Superscale_150000_G

upscale

1.5 - 1.85

steps

10 - 25

denoising strength

0.4 - 0.5

Tipps

Use the Detail Enhancer with a weight between 0.5 and 1 for optimal results.

Negative weights can produce interesting effects—experiment to see what works best.

Make sure to update webui using 'git pull' or redownload it to ensure compatibility.

Copy the file to the 'stable-diffusion-webui/models/lora' directory.

Change the weight from the default as it is usually too high.

Ersteller-Sponsoren

Do you like what I do? Consider supporting me on Patreon 🅿️ or feel free to buy me a coffee

Add More Details - Detail Enhancer / Tweaker

Do you like what I do? Consider supporting me on Patreon 🅿️ or feel free to buy me a coffee

I've been using the (great) Detail Tweaker by CyberAIchemist for a while now, and I was really curious. I really just wanted to know if I was capable of doing something similar.

I had a lot of fun doing this, and I think it came out pretty great. I wil ldefinitely incorporate it in most of my work going forward.

You should use this between 0.5 and 1 weight, depending on your preference. You can go lower than 0.5 for a more subtle effect, of course.

I also found out that this gives some interesting results at negative weight, sometimes. See the examples to see what I mean.

How to use LoRA's in auto1111:

  • Update webui (use git pull like here or redownload it)

  • Copy the file to stable-diffusion-webui/models/lora

  • Select your LoRA like in this video

  • Make sure to change the weight (by default it's :1 which is usually too high)

Zurück
PicX_real - 10
Weiter
EnvyBetterHands LoCon - beta2

Modell-Details

Modelltyp

LORA

Basismodell

SD 1.5

Modellversion

v1.0

Modell-Hash

d9cf2f88de

Ersteller

Diskussion

Bitte log in um einen Kommentar zu hinterlassen.

Modellsammlung - Add More Details Detail Enhancer Tweaker LoRA