# Krea 2 - Wulver Full fine-tune of Krea 2 Raw (12.8B DiT) — anthro &amp; furry, with strong anime / kemonorange and true multi-character composition. Trained on 1.5M+ curated images withmulti-format captions. &gt; In Shetland folklore, the Wulver is a wolf-headed being that was never cruel —&gt; 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 developmentand 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 &amp; kemono styles — not the usual western-model anime approximation- Multi-character scenes — characters interacting, not merged into one blob- Artist styles via <code>@artistname</code> prefixes (Curently under development)- Best results with detailed descriptive prose — see prompting tips below ## Settings | | ||---|---|| Steps | 14 || CFG | 1.5 || Sampler / Scheduler | euler / simple || Resolution | 1024 native || CLIPLoader type | krea2 | ## ComfyUI setup 1. <code>Wulver_v0.1_fp8.safetensors</code> → <code>ComfyUI/models/diffusion_models/</code>2. Text encoder <code>qwen3vl_4b_bf16.safetensors</code> from [Comfy-Org/Krea-2](<a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/Krea-2">https://huggingface.co/Comfy-Org/Krea-2</a>) → <code>models/text_encoders/</code>3. VAE <code>qwen_image_vae.safetensors</code> from the same repo → <code>models/vae/</code>4. Drag the attached workflow into ComfyUI and hit queue. ## Prompting tips This model was trained on long natural-language captions, so detailed prose gets youthe most out of it. Template that works: &gt; *A digital painting of [subject &amp; species, appearance details]. [What they are doing,&gt; pose, expression]. [Clothing / body details]. The background features [setting,&gt; lighting, atmosphere]. [Artistic style / medium notes].* - 60–120 words is the sweet spot. Short prompts work, detail works better- <code>@artistname, </code> at the very start for artist styles- Keep CFG at 1.0 — this is a guidance-distilled blend; higher CFG burns the image- Copy the prompts from the sample gallery to see the dialect in action ## Compatibility notes - LoRAs trained on base Krea 2 may behave differently on Wulver (weights have moved)- bf16 version available on request ## License This is a modified version of the Krea 2 model by Krea.Krea 2 is licensed under the [Krea 2 Community License Agreement](<a target="_blank" rel="ugc" href="https://krea.ai/krea-2-licensing">https://krea.ai/krea-2-licensing</a>) —by using this model you agree to its terms (including [Acceptable Use Policy])(<a target="_blank" rel="ugc" href="https://www.krea.ai/krea-2-use-policy">https://www.krea.ai/krea-2-use-policy</a>).Not affiliated with or endorsed by Krea. ---by Vaelico — generate online shortly at [<a target="_blank" rel="ugc" href="http://vaelico.ai">vaelico.ai</a>](<a target="_blank" rel="ugc" href="https://vaelico.ai)*">https://vaelico.ai)</a>

Wulver (Krea - 2)

# Wulver v0.1 — Non-Turbo BF16Original Wulver v0.1 full DiT checkpoint before the Turbo adapter was merged, intended as a base for LoRA training and further fine-tuning.- Architecture: Krea 2 RAW, 12.8B DiT.- Precision: BF16, 25.64 GB.- Full model weights, not a LoRA.- Preserved <code>sft_crema_epoch2</code> checkpoint, renamed without altering its bytes.- Text encoder and VAE are separate: Qwen3-VL-4B and Qwen Image VAE, as used by Wulver.- Requires a trainer with explicit Krea 2 support. Compatibility with a particular third-party trainer has not been newly tested for this upload.This is the Non-Turbo counterpart of the existing v0.1 release, not a newly trained Wulver version. The Turbo release's 14-step / low-CFG recommendations do not apply automatically. File: <code>Wulver_v0.1_non_turbo_bf16.safetensors</code>SHA256: <code>82d4f30e2477fe7532ecbbe9396bff284110a72b96694fdaa44e1554081c2514</code>Hugging Face: <a target="_blank" rel="ugc" href="https://huggingface.co/Vaelico/Wulver">https://huggingface.co/Vaelico/Wulver</a>Modified Krea 2 model. Same Krea 2 Community License, Acceptable Use Policy, and attribution notice as the existing Wulver release; see <a target="_blank" rel="ugc" href="http://LICENSE.md">LICENSE.md</a> and NOTICE in the Hugging Face repository. Not affiliated with or endorsed by Krea.

Files with SHA256: 82d4f30e2477fe7532ecbbe9396bff284110a72b96694fdaa44e1554081c2514