Krea 2 - Wulver _{v0.1 beta}

Full fine-tune of Krea 2 Raw (12.8B DiT) — anthro & furry, with strong anime / kemono range
and true multi-character composition. Trained on 1.5M+ curated images with multi-format captions.

Civitai page · vaelico.ai

In Shetland folklore, the Wulver is a wolf-headed being that was never cruel — it fished the lochs and left its catch on the windowsills of those in need.

This is a v0.1 beta — expect rough edges. An aesthetic pass is in active development and updates will roll out as the base training matures.

What it does

• Anthro / furry as its home turf — species knowledge far beyond generalist models
• Anime & kemono styles — not the usual western-model anime approximation
• Multi-character scenes — characters interacting, not merged into one blob
• Best results with detailed descriptive prose — see prompting tips below

Files

File	Size	Use
Wulver_v0.1_fp8_e4m3fn.safetensors	12.8 GB	ComfyUI — the one most people want
Wulver_v0.1_int8_convrot.safetensors	13.5 GB	forge-neo and other int8 runtimes
Wulver_v0.1_bf16.safetensors	25.6 GB	Full precision — merging, quantizing, training on top
Wulver_workflow.json	—	Drag-and-drop ComfyUI workflow

GGUF quants (Q8_0, Q5_0, Q4_0) are on the Civitai page.

Settings

Steps	14
CFG	1.0 – 2.0
Sampler / Scheduler	euler / simple
Resolution	1024 native
CLIPLoader type	krea2

ComfyUI setup

1. Wulver_v0.1_fp8_e4m3fn.safetensors → ComfyUI/models/diffusion_models/
2. Text encoder qwen3vl_4b_bf16.safetensors from Comfy-Org/Krea-2 → models/text_encoders/
3. VAE qwen_image_vae.safetensors from the same repo → models/vae/
4. Drag Wulver_workflow.json into ComfyUI and hit queue.

Prompting tips

This model was trained on long natural-language captions, so detailed prose gets you the most out of it. Template that works:

A digital painting of [subject & species, appearance details]. [What they are doing, pose, expression]. [Clothing / body details]. The background features [setting, lighting, atmosphere]. [Artistic style / medium notes].

• 60–120 words is the sweet spot. Short prompts work, detail works better
• CFG 1.0 is the distilled default, but CFG above 1 works fine — 1.5 is a good everyday value, and negative prompts start taking effect from there up. Past 3 it deforms unless you add steps, which doesn't help much
• Copy the prompts from the Civitai sample gallery to see the dialect in action

Compatibility notes

• Artist-name conditioning (@artistname) is not functional in v0.1 — the model ignores the prefix. A proper artist mechanism is in development for v1

• LoRAs trained on base Krea 2 may behave differently on Wulver (weights have moved)

License

This is a modified version of the Krea 2 model by Krea. Krea 2 is licensed under the Krea 2 Community License Agreement — by using this model you agree to its terms (including the Acceptable Use Policy). The full license text is included as LICENSE.md and the attribution notice as NOTICE in this repository. Not affiliated with or endorsed by Krea.

by Vaelico — generate online shortly at vaelico.ai