Senko-san_NAI-V5-Curated_ORIGINAL-ANIME_ULTRA (仙狐さん)

Anime-faithful character LoRA for Senko-san from The Helpful Fox Senko-san, for use with Krea 2 Turbo.

Built from an entirely new dataset of 1,000 native 1024 × 1024 NovelAI 5.0 Curated generations, this ORIGINAL-ANIME version captures the look and feeling of the original TV anime. Each training image was generated to resemble a frame from an episode, emphasizing softer linework, familiar colors, and faithful character design.

ORIGINAL-ANIME?

Where the HD version emphasizes ultra-crisp detail and high-fidelity rendering, ORIGINAL-ANIME prioritizes Senko’s on-screen likeness and the softer, screencap-like finish of the series. It is designed for txt2img character generation and img2img, with strong identity consistency and flexible natural-language prompting.

This LoRA is an ULTRA variant built using the same prompt set and dataset structure as the previously released ULTRA variants, with all images newly generated in NovelAI 5.0 Curated to match the original TV anime’s look. Its 598-image core character set establishes Senko’s identity across varied angles, expressions, poses, and framing, while its 402 activity scenes expand that foundation with the camera angles, shot types, and poses found across a wide range of activities.

The Trigger Word

senko_san

Include senko_san in your positive prompt, followed by a description of the outfit, activity, setting, and visual style you want.

What This Model Does Best

• Character identity: Reproduces Senko’s recognizable face, amber eyes, short layered golden-blonde hair, fox ears, fluffy fox tail, hair ornament, and anime appearance.

• Outfit flexibility: Maintains her identity across dresses, casual clothing, jackets, hoodies, kimono, and other outfits.

• Natural-language prompting: Supports descriptive prompts through Krea 2 Turbo’s Qwen3-VL-4B text encoder. Describe poses, expressions, clothing, lighting, and composition in clear sentences.

• Scene flexibility: Handles indoor, outdoor, traditional, modern, daytime, sunset, and nighttime environments.

• Fast generation: Uses Krea 2 Turbo’s 8-step generation workflow for quick iteration.

Recommended Generation Settings

Use these settings as your out-of-the-box starting point in ComfyUI:

Setting Recommendation

Base model Krea 2 Turbo

Text encoder Qwen3-VL-4B, loaded with type krea2

VAE Qwen Image VAE

Trigger word senko_san

Prompt style Descriptive natural language

LoRA weight Start at 1.0; adjust within 0.85–1.0

Sampler Euler (euler)

Scheduler Simple (simple)

Steps 8

CFG scale 1.0 in ComfyUI

Denoise 1.0 for txt2img

Resolution Start at 1024 × 1024; Turbo also supports generation up to 2048 × 2048

Negative prompt Leave empty at the recommended CFG

Guidance setting: ComfyUI’s CFG 1.0 disables additional classifier-free guidance. In Krea’s official inference code or Diffusers, use CFG 0.0 / guidance_scale=0.0 for the equivalent setting.

Start with LoRA weight 1.0. Lower it toward 0.85 if you want more freedom in clothing, composition, or style. For stronger character influence, experiment with 1.1–1.2, checking for exaggerated features or reduced outfit flexibility.

For prompting, keep senko_san intact and describe the desired image directly. Detailed natural-language prompts are a strong starting point for Krea 2 Turbo.