Semi-Real Anima Blend

( Not my Model )


 <a href="https://civitai.com/models/2727034/semi-realistic-anima-blend?modelVersionId=3292699" rel="noopener noreferrer nofollow" target="_blank">
 https://civitai.com/models/2727034/semi-realistic-anima-blend?modelVersionId=3292699
 </a>




 About this version


 Version 2.0 is a complete new merge with more realistic style, better poses and improved prompt adherence.


 
 Recommended settings:


 Sampler / Scheduler: ER-SDE + Linear Quadratic
 
 Steps: 20 - 35
 
 CFG: 3-5

v2.0

( Not my Model )


 <a href="https://civitai.com/models/2727034/semi-real-anima-blend?modelVersionId=3065326" rel="noopener noreferrer nofollow" target="_blank">
 https://civitai.com/models/2727034/semi-real-anima-blend?modelVersionId=3065326
 </a>




 Semi-Real Anima Blend is a model based on the latest Version base-v1.0 of the new Anima checkpoint.


 It offers a semi-realistic Anime style and supports prompting in booru tags and natural language.


 
 You need to download additional text encoder and VAE to use this model:


 Text encoder:
 <a href="https://huggingface.co/circlestone-labs/Anima/blob/main/split_files/text_encoders/qwen_3_06b_base.safetensors" rel="noopener noreferrer nofollow" target="_blank">
 https://huggingface.co/circlestone-labs/Anima/blob/main/split_files/text_encoders/qwen_3_06b_base.safetensors
 </a>


 VAE:
 <a href="https://huggingface.co/circlestone-labs/Anima/blob/main/split_files/vae/qwen_image_vae.safetensors" rel="noopener noreferrer nofollow" target="_blank">
 https://huggingface.co/circlestone-labs/Anima/blob/main/split_files/vae/qwen_image_vae.safetensors
 </a>




 
 Recommended Settings:
 

<ul>
 <li>
 
 
 Sampler / Scheduler:
 
 Euler A or ER SDE with SGM Uniform, Simple or Beta
 
 </li>
 <li>
 
 
 Sampling steps:
 
 20-35
 
 </li>
 <li>
 
 
 CFG Scale:
 
 3-5
 
 </li>
 <li>
 
 
 Shift:
 
 3-4.5
 
 </li>
 <li>
 
 
 Recommended resolution: 1024px based
 
 
 </li>
 <li>
 
 
 Model tested with
 
 <a href="https://github.com/Haoming02/sd-webui-forge-classic" rel="ugc" target="_blank">
 
 Forge Neo
 
 </a>
 
 </li>
</ul>

 Please refer to the official model page for detailed instructions:
 <a href="https://civitai.com/models/2458426/anima-official" rel="noopener noreferrer nofollow" target="_blank">
 https://civitai.com/models/2458426/anima-official
 </a>




 I recommend using a post processing upscale instead of a usual High-res fix.


 The preview images were 4x upscaled with
 <a href="https://github.com/Haoming02/sd-forge-nvidia-vfx" rel="ugc" target="_blank">
 [Nvidia] HD Ultra.
 </a>




 
 Quality tags:
 


 Positive:

<pre><code>masterpiece, best quality, score_9</code></pre>

 Negative:

<pre><code>score_1, score_2, score_3, blurry, jpeg artifacts,lowres, worst quality, low quality, bad hands, bad anatomy,signature, text, watermark, censor, bar censor, mosaic censorship, mosaic censor, sound effects, blubble speech, patreon logo, patreon username, twitter username, twitter logo, blur, multiple views or similars.</code></pre>

 
 Merged models:
 


 sparsityAnima_v1


 cyberrealisticAnima_v10


 +styling loras


 Permission: no commercial use, no selling, use only on Civitai (please also check the sources for their respective permissions)