animagine-xl-3.0_clear

anima_pencil-XL_clear

• Guide (External site): English | Japanese
• Ciivitai
• Animagine-XL_4.0_Opt_clear

<div style="display: flex; justify-content: center; align-items: center; gap: 2em;"> <div> <img src="./images/Animagine-XL_3.0_clear_cover_image1.png" alt="cover_image1" width="400" height="566"> </div> <div> <img src="./images/Animagine-XL_3.0_clear_cover_image2.png" alt="cover_image2" width="400" height="566"> </div> </div>

Compare to Animagine-XL_3.0 (Original)

Animagine-XL_3.0_clear | Animagine-XL_3.0 (Original)

<div style="display: flex; justify-content: center; align-items: center; gap: 2em;"> <div> <img src="./images/Animagine-XL_3.0_clear_compare_2.png" alt="Animagine-XL_3.0_clear_compare_2" width="400" height="400"> </div> <div> <img src="./images/Animagine-XL_3.0_original_compare_2.png" alt="Animagine-XL_3.0_original_compare_2" width="400" height="400"> </div> </div> <div style="display: flex; justify-content: center; align-items: center; gap: 2em;"> <div> <img src="./images/Animagine-XL_3.0_clear_compare_3.png" alt="Animagine-XL_3.0_clear_compare_3" width="400" height="400"> </div> <div> <img src="./images/Animagine-XL_3.0_original_compare_3.png" alt="Animagine-XL_3.0_original_compare_3" 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/Animagine-XL_3.0_clear_compare3_close_up.png" alt="Animagine-XL_3.0_clear_compare3_close_up" width="800" height="400"> </div>

A fine-tuned version of Animagine-XL_3.0 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.

INT8_ConvRot_HQ (light weight)

INT8_ConvRot_HQ is a lightweight version. 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.

Recommended Settings

General

• CFG scale: 4-6
• Sampler: DPM++ SDE, Euler A
• scheduler: beta
• Steps: 15-25 (around 20)

Upscaler

your choice, examples:

• RealESRGAN_x4Plus Anime 6B (Commercial use)
• IllustrationJaNai_V1_ESRGAN (No-Commercial use)

Detailer

works well.

Merge Recipe

• UNET: Animagine-XL_3.0
  • time_embed.: x0.95
  • input_blocks.0: x0.92
• CLIP: Animagine-XL_3.0
  • clip_l.embeddings: x0.5
  • clip_l.encorder_layers.1: x0
  • clip_g.encorder_layers.31: x0
• VAE: SDXL_anime_clear_vae

---

Tips (External site)

• Steps and Scheduler: English | Japanese
• Upscalers: English | Japanese
• Negative Prompt: English | Japanese
• Improving Prompt Encoding in SDXL: English | Japanese

---

License

• Fair AI Public License 1.0-SD
• License Official Page