Modelpublic

easygoing0114/mellow_pencil-XL_clear

sourceHugging Faceotherupdated 3mo agoView on Hugging Face

2likes

Model Card

mellowpencil-XLclear

—Guide v2(External site): English | Japanese
—Guide v1(External site): English | Japanese
—Civitai

mellowpencil-XLclear_v2

mellowpencil-XLclear_v2 vs v1

mellowpencil-XLclearv2 | mellowpencil-XLclearv1

The previous mellow_pencil-XL_clear_v1 was a model specifically enhanced with intermediate noise to create a sharp, high-definition output.

While this increased contrast and detail, it sometimes resulted in a "burnt" color look or left behind color blotches/unevenness caused by noise artifacts.

In mellow_pencil-XL_clear_v2, I have slightly reduced the intermediate noise to achieve natural color expression and a cleaner texture. As a trade-off, the density of fine background details is slightly lower compared to v1.

Recommended Settings (v2)

—CFG scale: 3 (2-4)
—Sampler: euler a
—Scheduler: beta
—Steps: 12-20 (around 15)

Quality Tags and Negative Prompts are not always necessary.

Workflow

This PNG image contains ComfyUI workflow.

Merge Recipe (v2)

—UNET: mellow_pencil-XL-v1.0.0-base
—input_blocks.0: x0.85
—output_blocks.6: x1.1
—out.: x1.05
—CLIP: mellow_pencil-XL-v1.0.0-base
—VAE: SDXL_anime_clear_vae

mellowpencil-XLclearv2INT8ConvRotHQ

This is a lightweight version of mellowpencil-XLclearv2. The **CLIP and VAE remain unchanged**, while only the **intermediate layers of the UNet** have been converted to INT8ConvRot format.

Image quality is slightly lower than the original mellowpencil-XLclear_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.

mellowpencil-XLclear_v1

Compare to mellow_pencil-XL (Original)

mellowpencil-XLclearv1 | mellowpencil-XL-v1.0.0-base (Original)

Fine-tuned model of the **mellow_pencil-XL** series, reduced noise for a clearer look and ensures vivid color expression even when the CFG scale is set low.

Recommended Settings (v1)

—CFG scale: 3 (3-5)
—Sampler: euler a
—Scheduler: beta
—Steps: 15-25 (around 20)

Quality Tags and Negative Prompts are not always necessary.

Merge Recipe (v1)

—UNET: mellow_pencil-XL-v1.0.0-base
—time_embed.: x0.90
—input_blocks.0: x0.90
—CLIP: mellow_pencil-XL-v1.0.0-base
—clip_l.encoder.layers.4: x0.95
—clip_g.encoder.layers.13: x0.95
—clip_g.encoder.layers.31: x0
—VAE: SDXL_anime_clear_vae

Upscaler

your choice, examples:

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

Detailer

works well.

Tips (External site)

—Color Prompts: English | Japanese
—Color Correct custum nodes in ComfyUI: English | Japanese
—About VAE: English | Japanese
—Illustrious-XL series License: English | Japanese

License

The mellowpencil-XLclear model released here is subject to the restrictions of both of the following two licenses:

—Fair AI Public License 1.0-SD
—CreativeML Open RAIL-M

The key points of these two licenses are the requirement to publish the recipe when releasing a derivative model, and furthermore, that Onoma AI, the source of Illustrious-XL 2.0, retains the right to modify the derivative model and its outputs.

We have inquired with Onoma AI regarding the detailed license for derivative models of Illustrious-XL 2.0, but until a response is received, both of the above restrictions shall apply.