Any≽^•⩊•^≼Gurim [illustrious]

This model is the result of merging models WAI-illustrious-SDXL(V16,V14) + AniMayhem - Pale Rider V3 + Hassaku XL V3.4 . It is part of my model series(Lain2Waill16Pale3_V05b, LainHass4c_V0.4c, LainWaill14Pale2_V0.3a, LainWaillPale_V0.1a) and currently represents my best result so far.

For some reason, errors occur during the final processing stage in Forge, so I recommend using this model exclusively with ComfyUI!

In version LainGurimV0.9m everything is fixed.

If anyone has any issues with the model, please DM me.

WAI-illustrious-SDXL(V16,V14)https://civitai.com/models/827184/wai-illustrious-sdxl?modelVersionId=2514310

AniMayhem - Pale Rider V3https://civitai.com/models/1984400/animayhem-pale-rider?modelVersionId=2672638

Hassaku XL V3.4https://civitai.com/models/140272/hassaku-xl-illustrious

This model supports tag-based workflows, and is compatible with both ComfyUI and the WebUI API.

For some reason, errors occur during the final processing stage in Forge, so I recommend using this model exclusively with ComfyUI!

In version LainGurimV0.9m everything is fixed.

The usage of this model is practically identical to the models it was derived from, so you won’t find anything new in this regard. However, just in case, here’s how to use the model.

Using the model:

• The model was trained primarily on images with minimal disruptive elements, such as floating text, logos, speech bubbles, or signatures. If any of these elements appear in an image, please include "signature" in your negative prompt.

• A CFG scale between 3 and 5 is recommended. For best results, use CFG 3.5 with the Euler a sampler.

• Refer to the example images, to understand, how the model should be used.

• The model is designed to be simple and straightforward to prompt. Use the following tag order:

  1. Number of characters

  2. Character Tags

  3. All remaining tags
     Example: 1girl, rem \(re:zero\), standing, masterpiece, upper body

  4. Don't be afraid to add a description of the scene

• Here are some resolution options for SDXL:

  • 1536 x 640

  • 1344 x 768

  • 1216 x 832 (recommended)

  • 1152 x 896

  • 1024 x 1024

  • 896 x 1152

  • 832 x 1216 (most recommended)

  • 768 x 1344

  • 640 x 1536

(Problems were found with DPM++ 2M and 2M SDE, I recommend Euler A)

In version LainGurimV0.9m everything is fixed.

DPM++ 2M and 2M SDE 
Karras 
30-40 steps 
Cfg under 5

Or 
Euler A
Normal  
20-30 steps (25)
cfg 3-5 (3.5)

I personally recommend using VAE F2-2 if you want more saturated colors, along with setting CFG to 4.

Lora use:

• NoobAIs Loras working for the most part better in compare to Illustrious loras

• Overall, everything works well except for one issue (S1 Dramatic Lighting). I’m not sure what’s causing it yet, but I’ll look into it in the future.

Just a note: the model performs well on RTX 2060, 2070, and similar older GPUs. It also runs successfully on Linux with Radeon graphics cards.