metadata

tags:
  - text-to-image
  - lora
  - diffusers
  - template:diffusion-lora
widget:
  - text: '-'
    output:
      url: images/ComfyUI_temp_oublb_00001_.png
  - text: '-'
    output:
      url: images/ComfyUI_temp_apqhc_00001_.png
  - text: '-'
    output:
      url: images/ComfyUI_temp_mpjsx_00001_.png
base_model: OnomaAIResearch/Illustrious-xl-early-release-v0
instance_prompt: midniji, vibrant colors, detailed character design, dynamic poses
license: cdla-permissive-2.0

Midjourney_Niji_Anime

Model description

TRIGGER: midniji, vibrant colors, detailed character design, dynamic poses

SOME QUALITY PROMPTS I USED: hdr, low contrast, masterpiece, best quality, absurdres, highres, perfect anatomy, perfect lighting, (sharp image), dynamic angle

Tested on all Illustrious models. I have not tested on any other.

Steps: 20-30 (use model recommendation / I trained on 24 steps)

Cfg: 7.0 (Use what is recommended by model)

Sampler: Euler_A

Scheduler: normal / simple / beta (may produce artifacts)

HIGH RES FIX: ((((HIGHLY recommend)))

Steps: 13

Denoise: 0.58

Upscale type: latent

Latent upscale: nearest_exact

Upscale by: 1.5

FOR UPSCALER: 4x RealESRGAN X PLUS

Daemon detailer (PLEASE USE IF YOU WANT EXTREME DETAIL 4K LIKE)

MY SETTINGS:

Face and hand detailer (Optional)

HAPPY GENERATIONS!

Source

https://civitai.com/models/1223801/midjourney-niji-anime-model-style-for-illustriousxl-or-mix-of-v5-and-v6?modelVersionId=1378822

Credit

https://civitai.com/user/QuestGlitch

Trigger words

You should use midniji to trigger the image generation.

You should use vibrant colors to trigger the image generation.

You should use detailed character design to trigger the image generation.

You should use dynamic poses to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.