31st January 2023 Update:
djzAirlockV15 released!19th January 2023 Update:
djzAirlockV21-512-inpainting released!
you will need the 2-1-512-inpainting.yaml config, so grab that too!
2.1-768 model: Example merging Rick-Roll, JunglePunk & Airlock:
credit: RickInversion
These "strong style" Models are intended to be merged with each other and any model for Stable Diffusion 2.1
I recommend merging with 0.5 (50/50 blend) then using prompt weighting to control the Aesthetic gradient.
example merged model prompt with automatic1111:
(Airlock:1.2) (yourmodeltoken:0.8)
if you drop the "djz" and the "V21" what remains is the token you need to call up the concept in the model. All examples shown were the Raw Token, no other words. Tokens are case sensitive and in almost all models it will match the filename.
It is possible to merge these models with each other using a different value. It is possible to pair models and then merge those resulting models. In this way we can blend abstract concepts together and then weight the tokens to achieve the result we may wish to create. Of course to eliminate all those tokens, you can simply train a new custom model from the outputs, which means you are back to a single token.
A video explanation will follow, but for now the above explanation should do. We are focused on getting as many style/aesthetic models into artist hands to enhance the creativity already at their finger tips.
Art Freedom for all!!
[all original artwork used for training with full permission from Drift Johnson]
Description
FAQ
Comments (6)
Checkpoint.
You keep using that word.
I do not think it means what you think it means.
TLDR, RTM. Results speak for themselves, if you don't want to try new things, that's up to you, but Spamming my releases is just pointless. All you need is Imagination, so these cheap shots you are trying to take just bounce off. If you understand "Venn Diagrams" and how "K-Diffusion" operated in the Context of "Nearest Neighbor" (KNN5) works - you would have no trouble understanding how to apply this.
You merge the models.
Please Enjoy them!
Merge the Textual Inversions.
Accomplish the same thing for thousands of times less ungainly storage space.
See this? Huggingface style concepts library. They know what they're doing,.
Thanks for that explanation, it really helps to explain it in terms beyond ELI5, which is rare to see. Giving me new Combination Ideas! Can we suggest new style models for merging anywhere?
Hey Rick, DJ and I saw a bunch of your review, nice work, please contact us on Twitter or Discord. We would love to have you help us out if you have time! We can talk more there. Short answer is Yes, but Johnson is creating the datasets - i'm just building the models for him
michaelangelo, you seem to miss the point of merging, aesthetic gradients are the only thing close and do not work with SD2.0/2.1 yet. If they ever come back then you can expect me to update them all.
No reason to go around spamming the same stuff because you fail to see what merging is. The filesize does not increase with a merge. Your whole premise is it takes up "more space" and is somehow ungainly. We are offering more unique styles and images to extend any model - through merging. It's been demonstrated now clearly. You can still use Textual Inversions, we know what they are. The advantages are clear as day. Please let people at least have their fun ;)
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.