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:
(InfiniteSupply: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 (3)
Great job man, and for the people who want something like this on 1.5 and only 1mb, check this LORA
FALSE/ your model does not do a tenth of what this one can -
You can use this model without the trigger.
That LORA you made doesn't make good images without the using the Trigger word.
No Cigar.
that's interesting that you figured out how to use the Extraction / Conversion tool. That is like a wav2mp3, a very cool new process which only used the CPU/RAM. These models are made for merging. Merging can be done by Sum Weight, Add Difference, Double Sum and Triple Sum. There are 20 position every 0.05 decimal on Alpha Blending. Also there are over 20 Graphs for the UNET blocks. This means that with 150 models being merged with only each other, you get the following math for a single prompt and seed:
(150*150)*20*5*20 = 45,000,000
This is something a LORA cannot do. Produce 45 Million Unique Images from a single prompt and Seed. Of course these LORA's are used "on top" further extending this number, factor in Textual Inversions and Hypernetworks and you only make this technique even stronger.
These models are made as resources for people to build advanced models and images, so while they might be used alone, they are quite limited. Also at the time of writing, merging LORA's does not have the same depth. Maybe one day soon.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.