Main prompt tags: boomerXL, 1boy, anthro, wolf <------ should always be included
Style control:
to get closest to Nanoff's original style use : cartoon prompt + Low CFG/step count + no negative quality prompts - example of this is image #4 in gallery
Recommended samplers:
- Euler Ancestral Scheduler: Normal CFG: 5.0-6.0 Steps: 20-25 Lora strength: 1.0
Prompt tips (green - positive, red - negative):
- ash hair - helps correct his hair color in case it turns too dark
- print tank top, tank top, jumpsuit, shorts, pants, black tank top, belt, briefs - common clothing items for Boomer
- black eyebrows - he was trained on images where he has sometimes black sometimes grey eyebrows. This will help steer generation towards grey eyebrows
- mature male - will help make him older
The LoRa should support all kinds of Illustrious checkpoints. Tested working well with the following:
WAI-NSFW-illustrious-SDXL v12.0
Nova FurryXL Illustrious v5.0
The LoRa should work well with different furry/bara artist styles. When using with Style LoRAs I recommend lowering strength of my LoRA.
Dsharp, Zoroj etc.
To improve details:
- generate using higher base resolution (e.g. 1384x1384) 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:
Requires download of FaceDetailer custom nodes + Eyeful_v2-Paired.pt + FacesV1.pt models. Workflow includes a HiresFix pass with x1.30 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.
Description
Character Lora for Boomer, OC from Nanoff
Trained using Illustrious XL v0.1.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.