models/AnyLoRA - Checkpoint - bakedVae fp16 NOT-PRUNED

AnyLoRA - Checkpoint - bakedVae fp16 NOT-PRUNED

|
1/20/2026
|
4:59:12 PM
| Discussion|
0
Pneuma from Xenoblade wearing a black and white armor bodysuit with blue and silver accents, long turquoise ponytail, green eyes, a tiara, and jewelry.

Recommended Prompts

1girl, looking at viewer, solo

Recommended Negative Prompts

(painting by bad-artist-anime:0.9), (painting by bad-artist:0.9), error, text, blurry, cropped, worst quality, watermark, jpeg artifacts, low quality, normal quality, signature, username, artist name, (worst quality, low quality:1.4), bad anatomy

Recommended Parameters

samplers

DPM++ SDE Karras, Euler a, DPM++ 2M Karras

steps

20 - 30

cfg

8 - 9

resolution

512x704, 512x768

vae

baked vae versions

other models

AnyLoRA_noVae_fp16-pruned (b0c91a8a93)

Recommended Hires (High-Resolution) Parameters

upscaler

R-ESRGAN 4x+, R-ESRGAN AnimeVideo, 4x_foolhardy_Remacri, R-ESRGAN General 4xV3

upscale

1.7 - 1.8

steps

10 - 20

denoising strength

0.28 - 0.45

Tips

Use the pruned versions for training to reduce VRAM consumption.

Adjust the LoRA weight to around 0.65 and offset to 1 for effective results, which can be easily done with ComfyUI.

Use booru style tags when training for better style accuracy.

Use a good VAE or baked VAE versions when generating images to avoid desaturated outputs.

Version Highlights

Use this for generating images, not for training.

Creator Sponsors

Add a ❤️ to receive future updates.

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

Available on the following websites with GPU acceleration:

AnyLoRA

Add a ❤️ to receive future updates.
Do you like what I do? Consider supporting me on Patreon 🅿️ or feel free to buy me a coffee

For LCM read the version description.

Available on the following websites with GPU acceleration:

Remember to use the pruned version when training (less vram needed).
Also this is mostly for training on anime, drawings and cartoon.

I made this model to ensure my future LoRA training is compatible with newer models, plus to get a model with a style neutral enough to get accurate styles with any style LoRA. Training on this model is much more effective compared to NAI, so at the end you might want to adjust the weight or offset (I suspect that's because NAI is now much diluted in newer models). I usually find good results at 0.65 weigth that I later offset to 1 (very easy to do with ComfyUI).

This is good for inference (again, especially with styles) even if I made it mainly for training. It ended up being super good for generating pics and it's now my go-to anime model. It also eats very little vram.

Get the pruned versions for training, as they consume less VRAM.

Make sure you use CLIP skip 2 and booru style tags when training.

Remember to use a good vae when generating, or images wil look desaturated. Or just use the baked vae versions.

Contributor

Previous
Fantexi_v0.9Beta - Fantexi_v0.9Beta
No next image

Model Details

Model type

Checkpoint

Base model

SD 1.5

Model version

bakedVae fp16 NOT-PRUNED

Model hash

b775b13509

Creator

Discussion

Please log in to leave a comment.