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
NOT for txt2img and NOT for training. Only for inpainting and outpainting
FAQ
Comments (21)
Where can I find this version?
Model hash: 64b14b6ca5
it's the hash of NeverEndingDream (v1) BakedVAE. Check the tabs above. It's one of the 3 versions there. Just pick the smallest one.
Hi! I was wondering whether your uploaded contents are available for commercial use?
I've seen your work and was utterly amazed at how realistic and unique each content was and thought it would be great if I can use it for my purposes.
If there are any guidelines or restrictions on using the contents (e.g. copyright, crediting, etc.) it would be greatly helpful.
Thank you so much in advance and hope to hear from you soon.
you can check the license here on civitai. You can do whatever you want except reselling the model (since it's free). You can sell generated images (provided they do not violate other copyrights) or use this model on generation services. No restrictions.
Is there any minimum dataset needed to make the AI generate a realistic photo? The dataset i used had 50 img [in different artstyle] and it still turned as a 3d render/2d image and not realistic.
hard to diagnose like that. Maybe the training went well but you're not generating in the right way? Give me more, I can't help you otherwise, or hit me on Discord.
nice model, kills my 4070ti computer
The original pruned files, baked VAE and noVAE, have the same hash and show up as duplicates on my computer. The full versions seem fine though.
Great model by master Lykon. Great work. Best regards.
Tutorial for this model NeverEnding Dream easy and fast
Try "a cute cat looking at a mirror" and you got human + cat head photo.
vae baked or non vae models generate blurry image for me. should I use a different vae or it's supposed to be such washed out? need recommendation.
Did you manage to solve it? I have the same problem
@DRAKKONCWB With baked/non vae I often have the same problem when the CFG setting is set too low. With most models this occurs below CFG:5.5
Surprisingly good model, love it so far!
Where are you ? you always update the models and then it disappears :/
Need a help. I tried this model, the body part is great, but the eyes look strange, the two eyes are not the same size. Does anyone encounter this problem too? How to fix it, I tried some lora and embedding but the effect was not significant
It happens with almost all sd 1.5 models. Try some negative prompts
Not bad
Well done!
It was once a very strong cool model. Time has passed, but it is still very powerful.