1
by skypavel •
•

Play to earn crypto games place

Excepteur sint occaecat atat non proident, sunt in culpa qui officia deserunt mollit anim id est labor umLor em ipsum dolor amet, consteur adiscing Duis elentum solliciin is yaugue euismods Nulla ullaorper. Ipsum is simply dummy text of printing and typee
Read more

Juggernaut XL

Lightining 4S Version 12 Juggernaut 9
1 32

Recommended Settings(VAE is baked in):

Res: 832*1216 (For Portrait, but any SDXL Res will work fine)

Sampler: DPM++ 2M SDE

Steps: 30-40

CFG: 3-6 (less is a bit more realistic)

Negative: Start with no negative, and add afterwards the Stuff you don´t wanna see in that image.

VAE is already Baked In

HiRes: 4xNMKD-Siax_200k with 15 Steps and 0.3 Denoise + 1.5 Upscale

Checkpoints
WRITTEN BY
V9 merged with the 4 Steps Lightning LoRA

Recommended Settings:

Sampler: DPM++ SDE

Steps: 4-6

CFG: 1-2

Hands XL + SD 1.5 + FLUX.1-dev + Pony + Illustrious

Hand F1D 2.0
1 3

You can try model with or without trigger word(s) and see yourself which works better for you

LoRas
WRITTEN BY
This version is much better than previous flux version. Chances of extra finger or missng one are reduced. However, you may still experience some weirdness occasionally.

You can try model with or without trigger word(s) and see yourself which works better for you.

In addition, try starting with low lora weight. Start with 0.1 and work you way up till 1.

You'll notice some generated images are much better with low lora weight while others are great with higher weight. It's tricky, but you'll need to adjust the weight till you reach best spot.

Hands XL + SD 1.5 + FLUX.1-dev + Pony + Illustrious

Hand F1D 2.0
1 3

You can try model with or without trigger word(s) and see yourself which works better for you

LoRas
WRITTEN BY
This version is much better than previous flux version. Chances of extra finger or missng one are reduced. However, you may still experience some weirdness occasionally.

You can try model with or without trigger word(s) and see yourself which works better for you.

In addition, try starting with low lora weight. Start with 0.1 and work you way up till 1.

You'll notice some generated images are much better with low lora weight while others are great with higher weight. It's tricky, but you'll need to adjust the weight till you reach best spot.

Juggernaut XL

Lightining 4S Version 12 Juggernaut 9
1 32

Recommended Settings(VAE is baked in):

Res: 832*1216 (For Portrait, but any SDXL Res will work fine)

Sampler: DPM++ 2M SDE

Steps: 30-40

CFG: 3-6 (less is a bit more realistic)

Negative: Start with no negative, and add afterwards the Stuff you don´t wanna see in that image.

VAE is already Baked In

HiRes: 4xNMKD-Siax_200k with 15 Steps and 0.3 Denoise + 1.5 Upscale

Checkpoints
WRITTEN BY
Used version 12 as the base for training to bring it back into photorealism. Trained another NSFW set on SDXL (using Booru tags). Then trained the same NSFW set again, this time using the great Lustify Model by Coyotte as the base.

Both NSFW sets were then merged into the trained photorealism model (0.15 ratio for the trained SDXL NSFW set and 0.1 ratio for the trained Lustify set)

Juggernaut XL

Lightining 4S Version 12 Juggernaut 9
1 32

Recommended Settings(VAE is baked in):

Res: 832*1216 (For Portrait, but any SDXL Res will work fine)

Sampler: DPM++ 2M SDE

Steps: 30-40

CFG: 3-6 (less is a bit more realistic)

Negative: Start with no negative, and add afterwards the Stuff you don´t wanna see in that image.

VAE is already Baked In

HiRes: 4xNMKD-Siax_200k with 15 Steps and 0.3 Denoise + 1.5 Upscale

Checkpoints
WRITTEN BY
The whole Juggernaut 9 Dataset recaptioned and trained for XI (15k Images)

Res: 832*1216 (For Portrait, but any SDXL Res will work fine)

Sampler: DPM++ 2M SDE

Steps: 30-40

CFG: 3-6 (less is a bit more realistic)

Negative: Start with no negative, and add afterwards the Stuff you don´t wanna see in that image. I don´t recommend using my Negative Prompt, i simply use it because i am lazy :D

VAE is already Baked In

HiRes: 4xNMKD-Siax_200k with 15 Steps and 0.3 Denoise + 1.5 Upscale

Juggernaut XL

Lightining 4S Version 12 Juggernaut 9
1 32

Recommended Settings(VAE is baked in):

Res: 832*1216 (For Portrait, but any SDXL Res will work fine)

Sampler: DPM++ 2M SDE

Steps: 30-40

CFG: 3-6 (less is a bit more realistic)

Negative: Start with no negative, and add afterwards the Stuff you don´t wanna see in that image.

VAE is already Baked In

HiRes: 4xNMKD-Siax_200k with 15 Steps and 0.3 Denoise + 1.5 Upscale

Checkpoints
WRITTEN BY
V9 merged with the 4 Steps Lightning LoRA

Recommended Settings:

Sampler: DPM++ SDE

Steps: 4-6

CFG: 1-2
Subscribe to