<h1 id="anima_pencil-xl_clear">anima_pencil-XL_clear</h1><ul><li>Guide (External site): <a target="_blank" rel="ugc" href="https://www.ai-image-journey.com/2025/12/animagine-xl-30-clear.html">English</a> | <a target="_blank" rel="ugc" href="https://note.com/ai_image_journey/n/n5d945ee3aefa">Japanese</a></li><li><a target="_blank" rel="ugc" href="https://huggingface.co/easygoing0114/animagine-xl-3.0_clear">Hugging Face</a></li></ul><h2 id="compare-to-animagine-xl_3.0-(original)">Compare to Animagine-XL_3.0 (Original)</h2>Animagine-XL_3.0_clear | Animagine-XL_3.0 (Original)<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/4c666bf5-02b8-4a78-a111-8113db1ec7c5/width=525/4c666bf5-02b8-4a78-a111-8113db1ec7c5.jpeg" /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/25b0d90c-66b8-46b8-b9a9-c802af68adf4/width=525/25b0d90c-66b8-46b8-b9a9-c802af68adf4.jpeg" /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/1440a14c-4884-4ec4-8be2-56d6e1d1b37b/width=525/1440a14c-4884-4ec4-8be2-56d6e1d1b37b.jpeg" />A fine-tuned version of <a target="_blank" rel="ugc" href="https://civarchive.com/models/260267/animagine-xl-v3?modelVersionId=293564">Animagine-XL_3.0</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.<hr /><h2 id="int8_convrot_hq-(light-weight)">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 /><h2 id="recommended-settings">Recommended Settings</h2><h3 id="general">General</h3><ul><li>CFG scale: 4-6</li><li>Sampler: DPM++ SDE, Euler A</li><li>scheduler: beta</li><li>Steps: 15-25 (around 20)</li></ul><h3 id="upscaler">Upscaler</h3>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><h3 id="detailer">Detailer</h3>works well.<hr /><h3 id="merge-recipe">Merge Recipe</h3><ul><li>UNET: <a target="_blank" rel="ugc" href="https://civarchive.com/models/260267/animagine-xl-v3?modelVersionId=293564">Animagine-XL_3.0</a><ul><li>time_embed.: x0.95</li><li>input_blocks.0: x0.92</li></ul></li><li>CLIP: <a target="_blank" rel="ugc" href="https://civarchive.com/models/260267/animagine-xl-v3?modelVersionId=293564">Animagine-XL_3.0</a><ul><li>clip_l.embeddings: x0.5</li><li>clip_l.encorder_layers.1: x0</li><li>clip_g.encorder_layers.31: x0</li></ul></li><li>VAE: <a target="_blank" rel="ugc" href="https://civarchive.com/models/2171491">SDXL_clear_vae</a></li></ul><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>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://huggingface.co/easygoing0114/animagine-xl-3.0_clear/blob/main/LICENSE">Fair AI Public License 1.0-SD</a></li><li><a target="_blank" rel="ugc" href="https://freedevproject.org/faipl-1.0-sd/">License Official Page</a></li></ul>

Files with SHA256: 8dd28840693c2459527f3c8d9795d08d62ed59d0e01332663fdca53af5924763