<ul><li>Guide v2 (External site): <a target="_blank" rel="ugc" href="https://www.ai-image-journey.com/2026/03/anima-pencil-xl-clear-v2.html">English</a> | <a target="_blank" rel="ugc" href="https://note.com/ai_image_journey/n/n81c831329572">Japanese</a></li><li>Guide v1 (External site): <a target="_blank" rel="ugc" href="https://www.ai-image-journey.com/2025/11/anima-pencil-xl-v500-clear.html">English</a> | <a target="_blank" rel="ugc" href="https://note.com/ai_image_journey/n/n6c48ea64dee9">Japanese</a></li><li><a target="_blank" rel="ugc" href="https://huggingface.co/easygoing0114/anima_pencil-XL_clear">Hugging Face</a></li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/2171491">SDXL_anime_clear_vae</a></li></ul><hr /><h2 id="v2-(latest)">v2 (latest)</h2>anima_pencil-XL_clear_v2 | anima_pencil-XL_clear_v1<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/3012b4f8-ad9a-4d54-99c6-df8d82b247e5/original=true/3012b4f8-ad9a-4d54-99c6-df8d82b247e5.jpeg" /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/38e119b3-fb78-49c6-ac49-fcfb9fbc5f1b/original=true/38e119b3-fb78-49c6-ac49-fcfb9fbc5f1b.jpeg" /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/abaa26fa-d279-4af2-9498-c238fee01345/original=true/abaa26fa-d279-4af2-9498-c238fee01345.jpeg" />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.<hr /><h2 id="v2_int8_convrot_hq-(light-weight)">v2_INT8_ConvRot_HQ (light weight)</h2>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.<hr /><h3 id="recommended-settings-(v2)">Recommended Settings (v2)</h3><ul><li>CFG scale: 2-4</li><li>Sampler: euler</li><li>scheduler: beta</li><li>Steps: 12-20 (around 15)</li></ul>Quality Tags and Negative Prompts are not always necessary.<h3 id="merge-recipe-(v2)">Merge Recipe (v2)</h3><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/3bc77c34-ce58-4ce2-afb4-00a84ce60cb4/original=true/3bc77c34-ce58-4ce2-afb4-00a84ce60cb4.jpeg" /><ul><li>UNET: <a target="_blank" rel="ugc" href="https://civarchive.com/models/261336/animapencil-xl">anima_pencil-XL-v5.0.0</a></li><li>VAE: <a target="_blank" rel="ugc" href="https://civarchive.com/models/2171491">SDXL_anime_clear_vae</a></li><li>Model Scale SDXL node: <a target="_blank" rel="ugc" href="https://github.com/easygoing0114/ComfyUI-easygoing-nodes">ComfyUI-easygoing-nodes</a></li></ul><hr /><h2 id="v1">v1</h2><h3 id="compare-to-anima_pencil-xl-v5.0.0-(original)">Compare to anima_pencil-XL-v5.0.0 (Original)</h3>anima_pencil-XL_clear_v1 | anima_pencil-XL-v5.0.0 (Original)<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/113590e2-b820-40b8-ade5-d27375686e9b/width=525/113590e2-b820-40b8-ade5-d27375686e9b.jpeg" /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/897ea122-dd99-4dac-8e38-137a698869fe/width=525/897ea122-dd99-4dac-8e38-137a698869fe.jpeg" /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/2f22a399-850f-4f0a-abee-44d682e16c33/width=525/2f22a399-850f-4f0a-abee-44d682e16c33.jpeg" />A fine-tuned version of <a target="_blank" rel="ugc" href="https://civarchive.com/models/261336/animapencil-xl">anima_pencil-XL-v5.0.0</a> 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.<h3 id="recommended-settings-(v1)">Recommended Settings (v1)</h3><ul><li>CFG scale: 2-4</li><li>Sampler: DPM++ 2M SDE</li><li>scheduler: beta</li><li>Steps: 15-25 (around 20)</li></ul>Quality Tags and Negative Prompts are not always necessary.<h3 id="merge-recipe">Merge Recipe</h3><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/de2a405f-b997-4845-bb74-226267dc3a2b/width=525/de2a405f-b997-4845-bb74-226267dc3a2b.jpeg" /><ul><li>UNET: Suppression of overly reactive layers (e.g., <code>time_embed.</code>, <code>label_embed.</code>)</li><li>VAE: Replacement with an anime-specific VAE (<a target="_blank" rel="ugc" href="https://huggingface.co/Anzhc/Anzhcs-VAEs/tree/main">SDXL Anime VAE Dec-only B3</a>)</li></ul><hr /><h2 id="upscaler">Upscaler</h2>your choice, examples:<ul><li><a target="_blank" rel="ugc" href="https://openmodeldb.info/models/4x-realesrgan-x4plus-anime-6b">RealESRGAN_x4Plus Anime 6B</a> (Commercial use)</li><li><a target="_blank" rel="ugc" href="https://openmodeldb.info/models/4x-IllustrationJaNai-V1-ESRGAN">IllustrationJaNai_V1_ESRGAN</a> (No-Commercial use)</li></ul><hr /><h2 id="detailer">Detailer</h2>works well.<hr /><h2 id="tips-(external-site)">Tips (External site)</h2><ul><li>Steps and Scheduler: <a target="_blank" rel="ugc" href="https://www.ai-image-journey.com/2025/06/step-schedulers.html">English</a> | <a target="_blank" rel="ugc" href="https://note.com/ai_image_journey/n/n0878f3eb6e6e">Japanese</a></li><li>Upscalers: <a target="_blank" rel="ugc" href="https://www.ai-image-journey.com/2025/04/ai-upscale-hires-fix.html">English</a> | <a target="_blank" rel="ugc" href="https://note.com/ai_image_journey/n/n15bf2384cd7b">Japanese</a></li><li>CFG and Negative Prompt: <a target="_blank" rel="ugc" href="https://www.ai-image-journey.com/2024/12/negative-prompt.html">English</a> | <a target="_blank" rel="ugc" href="https://note.com/ai_image_journey/n/n752bf830b745">Japanese</a></li><li>Improving Prompt Encoding in SDXL: <a target="_blank" rel="ugc" href="https://www.ai-image-journey.com/2025/09/comfyui-easygoing-nodes.html">English</a> | <a target="_blank" rel="ugc" href="https://note.com/ai_image_journey/n/n5bb33311b866">Japanese</a></li></ul><hr /><h2 id="license">License</h2><ul><li><a target="_blank" rel="ugc" href="https://freedevproject.org/faipl-1.0-sd/">Fair AI Public License 1.0-SD</a></li></ul>

anima_pencil-XL_clear

anima_pencil-XL-v5.0.0_clear.safetensors

v2_INT8_ConvRot_HQ

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.

Files with SHA256: fdb50572ea0501c7360b9c622d257e1fb56abb5873abe1a7856dbdd2f3f78f30