Main prompt tags: broadwayxl, anthro, teal gargoyle, fat, wings, solo, loincloth, black belt, (gold buckle:0.5) <------ should always be included

Style control:

• for mixed style only keep cartoon in positive prompt

• for the retro TV show style use following positive prompts: cartoon, retro

• to avoid the retro cartoon style put cartoon, retro into negative prompt

Recommended samplers:
- Euler Ancestral Scheduler: Normal CFG: 6.0 Steps: 20 Lora strength: 1.0
- DPM++ 2M SDE Scheduler: Karras CFG: 6.0 Steps: 20 Lora strength: 1.0
- euler_ancestral_cfg_pp Scheduler: Normal CFG: 0.5-1.0 Steps: 20-25 Lora strength: 1.0

Prompt tips (green - positive, red - negative):
- loincloth, gold buckle, black belt - full base clothing
- (gold buckle:0.5) - lower weight helps fix his belt buckle often appearing duplicate
- trench coat, brown fedora, beige belt (+ remove wings from positives) - detective version
- (dark cape:1.3) can be used to simulate his wings wrapped around like a cape - very hard concept to train, will often just look like a regular cape
- blank eyes for the aggressive mode canonical to the show
- 4 fingers / 4 claws will help showing canonical number of claws
- navel helps remove navel (canonically he has no navel showing)
- only 4 fangs + duplicate fangs, multiple fangs - helps control correct amount of fangs for open mouth shots
- vhs filter will give the style even more retro feel closer to the original cartoon

The LoRa should support all kinds of Illustrious checkpoints. Tested working well with the following:

• WAI-NSFW-illustrious-SDXL v12.0

• NovaFurryXL Illustrious V7B

To improve details:
- generate using higher base resolution (e.g. 1216x1216) or use latent upscaling / highres fix - especially when trying to do full body poses
- for fixing wonky face/eyes I use FaceDetailer node (comfyui) + Adetailer Face finder model

Last image in the gallery can be imported into ComfyUI with a basic workflow:
No custom nodes required anymore! Workflow includes a HiresFix pass with x1.3 latent upscaling by default.
For portraits/upper body shots I recommend lowering the upscaling ratio ('Upscale Latent By' node) - otherwise you might get distorted details.