My first mix in illustrious category aiming to bring more details and flexibility to animated style of this type of models. Various results can be achieved - from animated to semi-realistic style depending on the prompt.
As always my gratitude and due respect to the creators of original models that are used in the mix:
https://civarchive.com/models/827184/wai-nsfw-illustrious-sdxl?modelVersionId=1490781
https://civarchive.com/models/1231009/be-mix-illustrious?modelVersionId=1387129
https://civarchive.com/models/959736/rillusm-realistic-il?modelVersionId=1448475
https://civarchive.com/models/1412760/lunarcherrymix-illustrious?modelVersionId=1637795
https://civarchive.com/models/1695253/smooth-mix-illustrious2-noobai
https://civarchive.com/models/1318945?modelVersionId=2319122
Version 6.0: Experimental formula with addition of new elements to the mix for future development.
Version 5.0: Update with newer versions of the components.
Version 4.0: Return to older (v2.1) formula with improvements in composition and prompt adherence.
Version 3.0: Experimental mix with a little shift to more anime style and more vivid palette.
Version 2.1: Improved stability, composition and faces.
Version 2: Cranking up overall details and contrast. Colors look more vivid too. Needs further testing. Has more of its "own identity" compared to version 1.0.
Version 1: Overall very decent prompt adherence and anatomy. Stylisticaly close to anime-semirealism. High flexibility: some combinations of LORAs give very interesting results (you can find examples in the images).
Recommended setitings:
Sampling method: Euler a, DPM++ 2M, DPM++ 2M SDE, DPM++ 2S a, DPM2 a, DEIS
Schedule type: Karras, SGM Uniform
Sampling steps: 20-50
CFG Scale: 3-7
Highres.fix + Adetailer for face are recommended
Description
Improved details and lighting
FAQ
Comments (20)
I just got used to using v2.0... AND YOU PULL ME BACK IN.
This life never ends. You're here forever, my people.
v2.0 was great. Let's see if v2.1 lives the dream.
I GENERATE USING ONLY CPU ON A 192GB RACK SERVER WITH XEONS...
This checkpoint works for me on thse settings.
Steps; 27
CFG; 5.0
Sampler; Euler_Ancestral
Scheduler; SIMPLE
DeNoise; 0.95
ModelSamplingDiscrete_SAMPLING; EPS
ModelSamplingDiscrete_ZSNR; FALSE
VAE; SDXL/sdxl.vae.fixed.safetensors
VAE_MODE; fp32
VAE_DEVICE; cpu
Works very well.
By the way sdxl.vae.fixed.safetensors is baked into the model, so you can try without it
@Axelros It's in my workflow as a separate element as a constantly change between IL checkpoints and I know it works. Some of the VPRED ones are tempremental. Thank You. You should put that on the page.
Where can I find Highres.fix and Adetailer (link would help)?
Best model I've used so far, don't even need too many lora's with this one.
It depends on the gui that you use for generation (I use Forge right now). Highres.fix is built-in (it basically increases resolution of the generated image). Adetailer is an extension for Forge (Automatic1111) that does the same but for face/hands. You can install it in extensions tab.
@Axelros I use Fooocus.
Just beautiful. Thank you for your work.
I have enjoyed using your model. Thanks very much.
The best there is, thanks.
Great one!
THE best model online, so good!
This no longer works for me. Does anyone have any tips?
why did they take her out of the gen!?? this mix is freaking awesome, it's like my go-to for illustrious models. 🥺
Definitely one of the go-to cps for illustrious. It needs more love.
My favorite model. I hope you keep updating this one!!
best one i know
quickly became one of my favorites
Details
Files
Available On (2 platforms)
Same model published on other platforms. May have additional downloads or version variants.