anima_pencil-XL_clear

Guide v2 (External site): English | Japanese
Guide v1 (External site): English | Japanese
Hugging Face
SDXL_anime_clear_vae

v2 (latest)

anima_pencil-XL_clear_v2 | anima_pencil-XL_clear_v1

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 background detail has been intentionally reduced, so background complexity is simpler 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.

Merge Recipe (v2)

UNET: anima_pencil-XL-v5.0.0
VAE: SDXL_anime_clear_vae
Model Scale SDXL node: 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_clear_v1 | anima_pencil-XL-v5.0.0 (Original)

A fine-tuned version of anima_pencil-XL-v5.0.0 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.

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

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)

Upscaler

your choice, examples:

Detailer

works well.

Tips (External site)

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

License

Fair AI Public License 1.0-SD

Search AI Models & Addons

very few results