Phaenon — Character LoRA (Animagine XL / SDXL)

High-quality character LoRA for Phaenon, trained on a clean high-resolution dataset. Designed specifically for Animagine XL 3.1 and compatible SDXL anime checkpoints.

It captures his facial features, light blue eyes, signature white/silver hair with subtle blue gradients, and detailed outfit elements with high consistency, while offering excellent flexibility for clothing customization.

Recommended Settings

ParameterRecommended ValueBase ModelAnimagine XL 3.1 / Any SDXL Anime CheckpointLoRA Weight0.8 (optimal range: 0.7 - 0.9)Trigger WordphaenonHelper Tags1boy, solo, blue eyes, white hair, light blue hair tipsCFG Scale5.0 - 7.0Sampling Steps25 - 30SamplerEuler a or DPM++ 2M KarrasSchedule TypeKarrasResolution832x1216 (Portrait) / 1216x832 (Landscape)

Key Features

• Outfit Flexibility: Clean tag separation allows swapping his default gear for casual, modern, or alternative clothing without style bleeding.

• Pose Stability: Performs reliably across portraits, full-body shots, and dynamic action angles.

• High Facial Consistency: Maintains accurate eye color, hair shape, and facial features across different weights.

Example Prompts

Positive Prompt Template:

Plaintext

score_9, score_8_up, score_7_up, <lora:Phaenon:0.8>, 1boy, phaenon, solo, looking at viewer, upper body, casual clothes, outdoor, masterpiece, best quality, highly detailed

Negative Prompt Template:

Plaintext

score_4, score_3, score_2, score_1, lowres, bad anatomy, bad hands, missing fingers, extra digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, blurry

Feedback, reviews, and generations shared in the gallery are always appreciated.