This LoRA captures the 3D art style of hooves-art and is not focused on ponies. It performs well with any character, whether human, pony, or furry.

Usage

• Trigger words:

  • Illustrious v2.0 / Anima v1.0: hoovesart_style, 3d

  • Illustrious v1.0 / Pony v1.0: hoovesart-style, 3d

• Suggested settings:

  • Illustrious / Pony: CFG 4–8, 20–30 steps.

  • Anima: CFG 4.5, 40 steps, Euler a / Simple.

• LoRA strength:

  • Illustrious v2.0: 0.8–1.0.

  • Anima v1.0: start at 1.0. Try 1.2–1.5 for a stronger style, depending on the checkpoint and prompt.
    

Character compatibility: This is a style LoRA, not a character LoRA. Character recognition depends on your base checkpoint — some models may not reliably reproduce MLP characters. For a closer likeness, use a checkpoint that knows the character or add a dedicated character LoRA.

Style comparison

The examples below compare LoRA off, 0.8, and 1.0. Each row uses the same prompt, seed, and generation settings — only the LoRA strength changes.

Generation settings: NovaFurryXL_ilV180A · DPM++ 2M SDE / Karras · 30 steps · CFG 5.5.
The trigger words hoovesart_style, 3d are included in all examples, including those without the LoRA.

Anima

Tested settings: Anima Base v1.0 · LoRA strength 0.8–1.5 · Euler a / Simple · 40 steps · CFG 4.5.

For Anima 2.9B / 3.8B, use a loader with Anima block remapping, such as this ComfyUI patch. Style strength may vary between checkpoints.

The dataset was collected using a custom parser and processed with LaMa.