NeverEnding Dream (a.k.a. NED)
This is a dream that you will never want to wake up from
Add a ❤️ to receive future updates. This took much time and effort, please be supportive 🫂
Do you like what I do? Consider supporting me on Patreon 🅿️ or feel free to buy me a coffee ☕
V1.22 update: thanks to Bokus for some of the preview images and the tests.
Available on the following websites with GPU acceleration:
It has been a while since I made a model. I've been making LoRA's non stop for the last month, but I felt like I needed something. A big problem with DreamShaper is that it wasn't much compatibles with the LoRA's I was making. So I wanted to create a model that was "artistic" like DreamShaper but also able to use my LoRA's and booru tags for generating images. Plus I wanted this to be able to make good anime stuff out of the box, without needing an additional LoRA.
After a lot of tests and also fine tuning (plus LoRA merges) here is my newest model.
It came out a bit more realistic then I wanted, but I won't complain.
What is this model great at?
Generating cosplay images
Generating anime pictures
Work accurately with character LoRA
Generating good looking people
Generating realistic animals
Generating images using booru-like tags
What is this model not too good at?
Generating pictures from complex sentences
Making fantasy/sci-fi paintings
So this basically complements DreamShaper, and it also doesn't include Dreamlike in the mix.
I hope you'll enjoy it!
Some tips:
Use CLIP skip 2.
Select "auto" as vae if you're using the baked vae version.
Use highres fix or img2img to upscale the images after you get a preview. See the examples generation data for settings suggestions, I've tested various techniques.
If you're making images where the subject is far, remember you can inpaint eyes and faces selecting "only masked".
Stable Diffusion is great, have fun with it!
Description
The most ideal for training
FAQ
Comments (16)
For the v1.22 no vae, which external vae do you recommend ?
Do you have any suggestions for the upscaler, how much to upscale an image to (upscale by, I think), and the denoising strength? Thanks.
depends on the style. You can find upscaling info on the examples. Just copy the generation data. For photoreal and cgi I often use latent(nearest) at 0.6 denoise and 15-20 steps. If that comes up bad I redo with general ersgan at 0.5 denoise and 15 steps. For anime and drawings I use foolhardy at 0.4 denoise and 10 steps.
alright, thanks.
Many lora have Asian eyes and appearance, especially on anime characters. We have to add lora with a European appearance.
Use these words on negative prompt : Asian face, Japanese face, Chinese face, korean face. If you don't want any asian face
@marspluto81685 No use, still Asian appearance in many lora. Two and 3 brackets don't give the right effect. I add euro lora and then I have to adjust the weight. Often these are either costumes or anime characters.
@Lykon
You can see for yourself. Anime characters or cartoons have a penchant for Asian appearance. Only the use of lora euro helps, and then you have to adjust the weight so as not to break the art
@fansay anime character loras looking Asian doesn't surprise me. Anyway if the "dafault" face looks asian just prompt for different appearances like I did. CLIP has ethnicities, celebrities, facial features.
Hello everyone, can I just use v1.22 for inpainting?