Tensor.ART Note: The original version is on CivitAI, and all future model uploads, including merge recipes are available there first.
(Also check out the original Solera checkpoint to know this series' origin)
What is this model?
For people familiar with my previous model: This model is a remake of my original Solera model for commercial use, based on many of the models used in the original Solera and additional models for more functionality. Currently in testing phase.
For people unfamiliar with my previous model: This is a merged Stable Diffusion 1.5 model meant for generating 2D style anime pictures made from the following models:
Checkpoints:
AuroraONE (CivitAI | HuggingFace)
Something v2.2 (HuggingFace)
VividOrangeMix - NSFW (CivitAI | HuggingFace)
Hassaku - v1.3 (CivitAI)
YiffyMix - v37 (CivitAI)
******** Hentai - 1.3 (CivitAI)
Mistoon_Anime - v3.0 (CivitAI)
(a2 onwards) ElixirProject - v1.6 (CivitAI)
(a2 onwards) Nitro-Diffusion (CivitAI - unofficial | HuggingFace)
(a3 onwards) Furryrock - v_7.0 (CivitAI)
LoRAs:
AIOMonsterGirls - LoRA/LyCORIS (CivitAI)
CluelessC's Hololive - v6.3-eps-resized-512 (HuggingFace)
(a3 onwards) Ken Sugimori style LoRA - v3_offset (CivitAI)
The main goal of this model is to create a "jack-of-all-trades, master of one" anime model that can do almost anything. This model can output SFW and NSFW images, but current testing indicates that this model tends towards SFW more, but is quite suggestive.
All models have a baked-in VAE, Check the model details for what VAE was used.
How to use this model?
Prompting
Same as most other anime models, this model mainly uses booru-style prompts with no underscores (see Danbooru's Tag Groups wiki for more details and NovelAI's Basics page alongside looking at the tags and AI metadata on booru sites (e.g: AIBooru, Gelbooru, Danbooru,...) for usage), but can also use natural language in some cases.
When prompting this model, be specific and mention every detail you want to include.
Note: Pony quality tags (or as I call them, score tags) are untested and possibly useless on this model.
Also note the prompt parser used as well. This model is mainly tested against SD.Next's "Full attention" parser and ComfyUI's default parser.
This model can generate good results using minimal positive quality prompts and negative quality prompts. To get a better idea on this, look at the example images.
Positive: best quality, absurdres
Negative: (worst quality:1.3), (low quality:1.3) + any additional issues
For anyone trying to get furry content from this model, you'll need to beat it out of this model with strength and very specific prompting, combined with seed fishing. Be prepared to see furry faces on human skin, a lot.
Note: Most of the strengths listed here are suggestions. Do what you like, I don't take responsibility for your bad prompting or what you generate with this thing.
Sampler
This model is mainly tested against DPM++ 2M Karras, but DDIM, Euler ancestral, UniPC (with ComfyUI's "simple" scheduler) are other great options.
Step count is dependent on sampler, but 20 steps is a good start for most. For furry generations, lower steps works better.
CLIP Skip works best at 1-2, depending on each version.
Resolution
This model supports all three normal SD1.5 resolutions: 512x512, 512x768, 768x512
Each resolution deals with things differently, with prompt accuracy being best at 512x512, followed by 512x768, then 768x512. Details-wise, 768x512 is the best (imo) and 512x768 can generate at similar quality.
For upscaling, x2 AniScale2 ESRGAN, 4x Remacri and x4 Lollypop are my choice.
Q&A - Lightning Round:
Which model should I use? This or the original Solera?
Use this one. The original Solera has a couple of differences, but not significant. For legacy and testing purposes, I still keep SoleraV7 around for comparison. In most cases, I think this model would out-perform my original by quite a bit, if you can tolerate losing some contrast.
Why OpenSolera?
It's Solera, but open to everyone (including commercial uses). Pretty simple, really. Also differentiate it from the original Solera model. Internally, this model has another name: SoleraV9.
What happened to previous versions of Solera?
V1-V3: Lost to time. They're all very rudimentary merges of AbyssOrangeMix3 (specifically AOM3, Anything V5, and Hassaku.
V4: Don't like it that much, still exists but not really usable or useful.
V5: Absorbed too much of Pastel-Mix, completely destroyed the background
V6 (internal name SoleraRemix): Don't like it that much. It was a decent foundation for future merge ideas, but not much remains.
V7: Uploaded to CivitAI as SoleraV7-a9.
V8: Went nowhere.
V9: Uploaded to CivitAi as OpenSolera.
Where did the name "Solera" came from?
From *********: "Solera is a process for aging liquids such as wine, beer, vinegar, and brandy, by fractional blending in such a way that the finished product is a mixture of ages, with the average age gradually increasing as the process continues over many years."
My actual origin for the name is the Infinity Bottle: "An infinity bottle, also referred to as a "solera", "fractional", or "living" bottle, is your own personal blend of whiskeys that is ever changing. By simply combining a bit of your favorite whiskeys in an empty bottle (or by adding to a base whiskey) you get a personal, never-ending blend of your own creation. This blend will likely have never been possessed or enjoyed by anyone else, ever. As you continue to add more, the flavor profile of the bottle is always new, evolving, and taking on a life of its own."
I don't actually drink myself, but I find the concept interesting, so I adapted the name for my merges.
I want to use your model for...
Downloading and generating on your own: Go ahead. If you post it online, give some credits somewhere.
Merging (and changing license after merging): Go ahead, just give some credits somewhere.
Sell the images: None of the models stop it, so go ahead. I don't care either way, just give credit to the model.
Online generations: Go ahead, I'm fine with it
Selling the model: No dice
See the license near my profile card for more information. For any other purpose, contact me on Discord: @azeluslightvale (Azelus光山)
If any of the original model owners have issues with this model (due to licensing), please contact me. I try to be as thorough as possible, but I might miss something.
Please note that I don't check my Discord very often, if at all. If I take a few weeks to respond, please forgive me, I don't use social media. (T_T)
Where's the merge recipe?
Check the zip file labelled "Training Data" on the version you're downloading on CivitAI. The actual merge takes too long to list now.
Basically, it's 13+ steps with a lot of long fractional numbers. Can't really copy them over properly.
Why does your writing switch between casual and formal/professional so often?
The more tired I get, the less I care about professionalism. Simple as that.
Do you actually use this model or are you just making them for clout?
I make these for daily use for the most part. Every version of Solera replaces the previous one for me. Every image I make on CivitAI will use the Solera series, and most, if not all of my generations are from that line of models as well. I truly want to push SD1.5 to the limit with merging alone to see how far it can go. Tl;dr: yes, this is for daily use for the most part.
Is this similar to SD-Silicon?
No. This model series does not use any form of automation (except XYZ Grid for testing) in merging. Goal-wise, though, they are quite similar.
