A real-anima、Noob Realistic photography ...

( Not my Model )


 <a href="https://civitai.com/models/1646878/a-real-animanoob-realistic-photography-cosplay-portrait?modelVersionId=3129527" rel="noopener noreferrer nofollow" target="_blank">
 https://civitai.com/models/1646878/a-real-animanoob-realistic-photography-cosplay-portrait?modelVersionId=3129527
 </a>




 
 Steps: 8
 


 
 CFG: 1
 


 
 Sampler: er_sde

anima-test2-00032

( Not my Model )


 <a href="https://civitai.com/models/1646878/a-real-animanoob-realistic-photography-cosplay-portrait?modelVersionId=3077227" rel="noopener noreferrer nofollow" target="_blank">
 https://civitai.com/models/1646878/a-real-animanoob-realistic-photography-cosplay-portrait?modelVersionId=3077227
 </a>




 
 Steps: 8
 


 
 CFG: 1
 


 
 Sampler: ER_SDE

anima-test2-00025_turbo

( Not my Model )


 <a href="https://civitai.com/models/1646878/a-real-animanoob-realistic-photography-cosplay-portrait?modelVersionId=3070877" rel="noopener noreferrer nofollow" target="_blank">
 https://civitai.com/models/1646878/a-real-animanoob-realistic-photography-cosplay-portrait?modelVersionId=3070877
 </a>



<h3>
 
 If you like my work and want to support me in a diferent way you can buy me a
 
 <a href="https://ko-fi.com/dawn6666" rel="ugc" target="_blank">
 
 Ko-Fi
 
 </a>
 
 if you want.
 
</h3>



 Updated 2026.06.25: testV2 is retrained based on anima_base V1.0 using 14,000 images. In addition to realistic photos, the dataset also includes @3dcg and Blender style images. The turbo version adds an 8-step LoRa model to the 00006ep .


 Turbo Lora is no longer required separately.


 Cfg: 1-3, steps 8-24.

anima-test2-00018_turbo

( Not my Model )


 <a href="https://civitai.com/models/1646878/a-real-animanoob-realistic-photography-cosplay-portrait?modelVersionId=3065934" rel="noopener noreferrer nofollow" target="_blank">
 https://civitai.com/models/1646878/a-real-animanoob-realistic-photography-cosplay-portrait?modelVersionId=3065934
 </a>



<h3>
 
 If you like my work and want to support me in a diferent way you can buy me a
 
 <a href="https://ko-fi.com/dawn6666" rel="ugc" target="_blank">
 
 Ko-Fi
 
 </a>
 
 if you want.
 
</h3>

 Updated 2026.06.02: Based on "
 
 Anima base1.0"
 
 , I made some full-scale fine-tuning attempts. When used with the
 <a href="https://civitai.red/models/2639613/a-real-anima-photorealistic?modelVersionId=2981516" rel="ugc" target="_blank">
 LoRa model
 </a>
 I released, the results are even better.


 The dataset contains approximately 4,000 to 5,000 images.


 All tests were performed using "
 <a href="https://civitai.com/models/2560840/anima-turbo-lora" rel="ugc" target="_blank">
 anima-turbo-lora-v0.2
 </a>
 ", "8steps", "er_sde", and "simple".


 Trigger Word: photorealistic (range 1-5)