(ConcoctionMix-a1 [Vodka]'s Recipe) - Has metadata

(ConcoctionMix-a2 [Vermouth]'s Recipe) - No metadata

WARNING: HERE BE DRAGONS!

This model is made though merging with ComfyUI and, therefore, incompatible with Model Toolkit. Do not use Model Toolkit to check/prune this model, for this is impossible without destroying the model itself. See this article for more information.

What is this model?

ConcoctionMix is my experimental branch for OpenSolera, my Stable Diffusion 1.5 anime-style model. The model is my foray into ComfyUI merging (yes, the workflow above is the entire merge recipe) and continuation of CLIP experiments (thanks @daskmaster for the CLIPs). This is probably one of, if not the hardest model to work with that I've made.

The model should work the same as other Stable Diffusion 1.5 checkpoints, just much harder to merge with other models without ComfyUI.

This model is made from 1 base model (OpenSolera-a5 [Serif]) and several other models using DARE-TIES in ComfyUI:

Checkpoints:

• OpenSolera - a5 [Serif]

• Wormwood - a1

LoRAs:

• CluelessC's Hololive - 6.3-a10-eps-resized-512

• AIOMonsterGirl - v4-LoRA/LyCORIS

• Theovercomer8's Contrast Fix

• DPO LoRA

CLIP: zer0int's ViT-L-14 smoothGmP

VAE (baked in): PPPAniMix - v3

(Other recommended VAE: nubby/kl-f8-anime2-blessed)

How to use this model?

Prompting:

This model (in my testing) uses booru tags very well, but can use natural language when necessary.

For best results, a style must be prompted (in artist and/or medium) to give this model a style to work with. Versatility is this model's strong point. Base model (without style prompt) jumps between styles very often. and can sometimes drift into 3D/2.5D art styles and sometimes realism.

Like most anime checkpoints, this one also has a female bias, but it can be countered.

This model is mainly tested against ComfyUI's prompt parser and reForge's default parser.

Character recognition should work well with really popular characters, but not much else.

Parameters:

(Anything in bold has been tested and working decently fine)

• Sampler + Scheduler: Almost anything works, with recommendations being: Euler a, DPM++ 2M Karras/AYS, DPM Adaptive, UniPC-simple, DDIM (with ddim_uniform),

• Steps: 20+

• CFG: 6-12 (recommended range: 7-12)

• CLIP Skip: 1-2

• Resolution: 3:2 aspect ratio tested, 640x640, 640x960, 960x640, 512x512, 512x768, 768x512 all works to some degree

• Hi.res fix: Recommended, but not necessary for close-ups. For multiple people, this is a necessity. (This is wrong as of CCM-a2. Hi.res fix for CCM-a2 is more required to get strong results)

See OpenSolera's page for some recommendation and guides

On a technicality, this would be OpenSolera-a6 [Plex] (or at least a version of it), but due to it being hard to work with for everyone and the difference in style, this model is separated from the series.

Documentation

This section will be used to list my findings and recommendations on this model. Maybe I'll make it into a separate article if it gets big enough.

• Realistic prompts: (realistic, photorealistic: 1.2). With this, this model could feasibly be a DreamShaper knock-off since it can do both realism and anime easily. Also remember to lower the strength of any other negative tags (worst quality, low quality,...) when using theses tags.

  • Please note that for a2 [Vermouth], these tags should be thrown into negative prompts to get the anime style. If you want, you could somehow make a 2.5D style out of this

• Without clothes prompt, this model will generate nude in many cases, even when you don't want it, so please, give them clothes.

• Styles and mediums:

  For all mediums, add \(medium\) at the end of each set. Tag strength at 1.2 is also recommended to enforce the style/medium properly (on base ComfyUI parser, no normalization)

  • Western comics: working, use western comics

  • Alphes (style): unsure

  • Traditional art mediums: some works, currently: watercolor (works as expected), ballpoint pen (gives pencil-like drawings), airbrush (not sure what style it gives), charcoal, colored pencil (kinda), color ink and ink (compatible with color tags), crayons (kinda), gouache (not sure), graphite (mostly), marker, nib pen (unsure), oil painting, pastel, photo (gives realism), watercolor pencil,... Additional tags that synergize is paper, canvas,...

  • Digital art software: photoshop (realism), painttool sai (drawings, as expected), clip studio paint (UI on every image, drawings), krita (drawings), medibang paint (unique style), ibispaint (soft style, might feature UI),...

  • Dakimakura (body pillow): somewhat working, recommend simple background tag (sometimes). The fabric can be dyed by setting the background color (sometimes). Double dakimarura also works as a medium if that's more your style

  • Cards: for trading cards, use card, for tarot cards, use tarot card or tarot. If you with to have regular playing cards (can't make actual cards atm), put trading card in negatives

  • Traditional art styles: abstract, art deco/art nouveau (different movements, but it blended into one another), fine art parody (maybe), impressionism, ukiyo-e, sketch, surreal

  • Posters: works pretty well for propaganda and movie posters. Other forms are untested

  • Calendars: works, but why would you want to generate a calendar outright with this thing? (genuine question)

  • Clear files: technically works, but again, why would you want that when you could generate a simple (and better) portrait/landscape pic and put that up instead? (genuine question)

  • Blueprints: technically works, not sure what to do with it though

  • Close-ups: works surprisingly well with specific body parts (limited to what humans have)

描述:

The second version of ConcoctionMix, now with Wormwood built-in for better realism and slightly more cohesive images. More of a side-grade than an outright upgrade

Original name: CCM-a2-Vermouth.safetensors

This version's codename, Vermouth. follows upon the alcoholic drinks idea. There's been historical reports of people mixing wormwood into white wine, so this is a serendipity for the most part. I just like the name and idea.

Changelog:

• Added Wormwood and CCM-a1 into the model (through trainDifference merging)

  • More realism and realistic feel - partially countered by putting "realistic" and "photorealistic" into negatives.

  • Lost quite a bit of color during this. This can be fixed by using a different VAE than the one bundled in this model - WD1-4-kl-f8-anime2-bless09

  • Slightly better hands. In regular poses, hands are more solid and decent than before. Still fucks up in many cases

  • Surprisingly decent prompt comprehension - managed to recover the "centaur" tags

  • Worse area conditioning (until I can figure something out at least)

  • Styles still work pretty well (if you put any of the realism stuff into the negatives)

  • Both CLIP Skip 1 and 2 still works well

  • Sometimes forgets details, which I don't like that much

• Even more complicated merging workflow - this is getting really hard to put in 1 image lol

训练词语: