---
license: other
license_name: fair-ai-public-license-1.0-sd
license_link: https://freedevproject.org/faipl-1.0-sd/
tags:
  - text-to-image
  - stable-diffusion-xl
  - sdxl
  - anime
  - pencil-drawing
  - illustration
---

# anima_pencil-XL_clear

- **Guide v2 (External site)**: [English](https://www.ai-image-journey.com/2026/03/anima-pencil-xl-clear-v2.html) | [Japanese](https://note.com/ai_image_journey/n/n81c831329572)
- **Guide v1 (External site)**: [English](https://www.ai-image-journey.com/2025/11/anima-pencil-xl-v500-clear.html) | [Japanese](https://note.com/ai_image_journey/n/n6c48ea64dee9)
- [**Civitai**](https://civitai.com/models/2130524)
- [**SDXL_anime_clear_vae**](https://huggingface.co/easygoing0114/SDXL_anime_clear_vae)

<div style="display: flex; justify-content: center; align-items: center; gap: 2em;">
  <div>
    <img src="./images/anima_pencil-XL_clear_v2_white_dress_and_red_rose.png" alt="white_dress_and_red_rose" width="400" height="566">
  </div>
  <div>
    <img src="./images/anima_pencil-XL_clear_v2_red_hat_blonde_girl.png" alt="red_hat_blonde_girl" width="400" height="566">
  </div>
</div>

## v2 (latest)

anima_pencil-XL_clear_v2 | anima_pencil-XL_clear_v1

<div style="display: flex; justify-content: center; align-items: center; gap: 2em;">
  <div>
    <img src="./images/anima_pencil-XL_clear_v2_compare_1.png" alt="anima_pencil-XL_clear_v2_compare_1" width="400" height="566">
  </div>
  <div>
    <img src="./images/anima_pencil-XL_clear_v1_compare_1.png" alt="anima_pencil-XL_clear_v1_compare_1" width="400" height="566">
  </div>
</div>

<div style="display: flex; justify-content: center; align-items: center; gap: 2em;">
  <div>
    <img src="./images/anima_pencil-XL_clear_v2_compare_2.png" alt="anima_pencil-XL_clear_v2_compare_2" width="400" height="566">
  </div>
  <div>
    <img src="./images/anima_pencil-XL_clear_v1_compare_2.png" alt="anima_pencil-XL_clear_v1_compare_2" width="400" height="566">
  </div>
</div>

<div style="text-align: center; margin-left: auto; margin-right: auto; width: 800px; max-width: 90%;">
  <img src="./images/anima_pencil-XL_clear_v2_compare_2_close_up.png" alt="Close-up comparison" width="800" height="400">
</div>

v2 has been tuned to work well with the standard **Euler sampler** and **low CFG scale**. This significantly reduces the color burning that commonly occurs at high CFG values, resulting in more natural color expression.

Compared to v1 on the right, the output from anima_pencil-XL_clear_v2 on the left has more **vibrant** and **lively** colors.

On the other hand, to create a cleaner look, the backgrounds have been simplified compared to v1.

### Recommended Settings (v2)

- CFG scale: 2-4
- Sampler: Euler
- Scheduler: beta
- Steps: 12-20 (around 15)

Quality Tags and Negative Prompts are not always necessary.

### Workflow

<div style="text-align: center; margin-left: auto; margin-right: auto; width: 800px; max-width: 90%;">
  <img src="./images/SDXL_simple_workflow_20260317.png" alt="SDXL_simple_workflow_20260317" width="800" height="400">
</div>

This PNG image contains ComfyUI workflow.

### Merge Recipe (v2)

<div style="text-align: center; margin-left: auto; margin-right: auto; width: 800px; max-width: 90%;">
  <img src="./images/anima_pencil-XL_clear_v2_merge_recipe.png" alt="anima_pencil-XL_clear_v2_merge_recipe" width="800" height="400">
</div>

- UNET: [anima_pencil-XL-v5.0.0](https://huggingface.co/bluepen5805/anima_pencil-XL)
- VAE: [SDXL_anime_clear_vae](https://huggingface.co/easygoing0114/SDXL_anime_clear_vae)
- Model Scale SDXL node: [ComfyUI-easygoing-nodes](https://github.com/easygoing0114/ComfyUI-easygoing-nodes)

---

## v2_INT8_ConvRot_HQ (light weight)

This is a lightweight version of v2. The **CLIP and VAE remain unchanged**, while only the **intermediate layers of the UNet** have been converted to INT8_ConvRot format.

Image quality is slightly lower than the original v2, but it is particularly well-suited for fast generation in low-VRAM environments (4-6 GB).

INT8_ConvRot is currently supported in **ComfyUI** and **Stable Diffusion webUI Forge NEO**.

---

## v1

### Compare to anima_pencil-XL-v5.0.0 (Original)

anima_pencil-XL-v5.0.0_clear | anima_pencil-XL-v5.0.0 (Original)

<div style="display: flex; justify-content: center; align-items: center; gap: 2em;">
  <div>
    <img src="./images/anima_pencil-XL-v5.0.0_clear_image1.png" alt="anima_pencil-XL-v5.0.0_clear_image1" width="400" height="400">
  </div>
  <div>
    <img src="./images/anima_pencil-XL-v5.0.0_original_image1.png" alt="anima_pencil-XL-v5.0.0_original_image1" width="400" height="400">
  </div>
</div>

<div style="display: flex; justify-content: center; align-items: center; gap: 2em;">
  <div>
    <img src="./images/anima_pencil-XL-v5.0.0_clear_image2.png" alt="anima_pencil-XL-v5.0.0_clear_image2" width="400" height="400">
  </div>
  <div>
    <img src="./images/anima_pencil-XL-v5.0.0_original_image2.png" alt="anima_pencil-XL-v5.0.0_original_image2" width="400" height="400">
  </div>
</div>

<div style="text-align: center; margin-left: auto; margin-right: auto; width: 800px; max-width: 90%;">
  <img src="./images/anima_pencil-XL-v5.0.0_compare_close_up.png" alt="Close-up comparison showing finer details and sharper edges in anima_pencil-XL-v5.0.0_clear anime outputs." width="800" height="400">
</div>

A fine-tuned version of [**anima_pencil-XL**](https://huggingface.co/bluepen5805/anima_pencil-XL) model, designed to produce clearer and more vibrant outputs.

Compared to the original, this model generates illustrations with **higher contrast**, **richer colors**, and more **refined details**.

### Recommended Settings (v1)

- CFG scale: 2-4
- Sampler: DPM++ 2M SDE
- Scheduler: beta
- Steps: 15-25 (around 20)

Quality Tags and Negative Prompts are not always necessary.

### Merge Recipe (v1)

<div style="text-align: center; margin-left: auto; margin-right: auto; width: 800px; max-width: 90%;">
  <img src="./images/anima_pencil-XL_v5.0.0_clear_merge_workflow.png" alt="anima_pencil-XL_v5.0.0_clear ComfyUI merge workflow" width="800">
</div>

- UNET: Suppression of overly reactive layers (e.g., `time_embed.`, `label_embed.`)
- VAE: Replacement with an anime-specific VAE ([SDXL Anime VAE Dec-only B3](https://huggingface.co/Anzhc/Anzhcs-VAEs/tree/main))

---

## Upscaler

Your choice. Examples:

- [RealESRGAN_x4Plus Anime 6B](https://openmodeldb.info/models/4x-realesrgan-x4plus-anime-6b) (Commercial use)
- [IllustrationJaNai_V1_ESRGAN](https://openmodeldb.info/models/4x-IllustrationJaNai-V1-ESRGAN) (Non-commercial use)

---

## Detailer

Works well.

---

## Tips (External site)

- Steps and Scheduler: [English](https://www.ai-image-journey.com/2025/06/step-schedulers.html) | [Japanese](https://note.com/ai_image_journey/n/n0878f3eb6e6e)
- Upscalers: [English](https://www.ai-image-journey.com/2025/04/ai-upscale-hires-fix.html) | [Japanese](https://note.com/ai_image_journey/n/n15bf2384cd7b)
- Negative Prompt: [English](https://www.ai-image-journey.com/2024/12/negative-prompt.html) | [Japanese](https://note.com/ai_image_journey/n/n752bf830b745)
- About VAE: [English](https://www.ai-image-journey.com/2026/04/sdxl-anime-natural-vae.html) | [Japanese](https://note.com/ai_image_journey/n/nd22f8c4cabc7)

---

## License
- [Fair AI Public License 1.0-SD](./LICENSE)
- [License Official Page](https://freedevproject.org/faipl-1.0-sd/)