<h2 id="anima-base-vivid-v1-realism-fine-tune-(fft)">Anima Base Vivid V1 - Realism Fine-Tune (FFT)</h2>Hello everyone! I decided to try training the Anima Base V1 model on my custom dataset to push it towards realism. This is a full FFT (Full Fine-Tuning) trained on a dataset of 1,500 image-caption pairs. <h3 id="key-features">Key Features</h3><ul><li>Dual-Prompting Support: The dataset captions were split into both natural English and Danbooru tags. As a result, the model understands both prompting styles perfectly.</li><li>Character Memory Retention: Thanks to a gentle, 2-stage fine-tuning process using Kohya scripts, the model successfully retains memory of standard characters from its base training.</li><li>High Dataset Variability: The training set features diverse camera angles, dynamic lighting, and a high variety of NSFW themes (including futanari, sex, nudity, yuri, anthropomorphic/furry, and high-quality aesthetic shots).</li><li>Future Potential: As a first version, it already demonstrates that the model can be pushed significantly further into realism with an even larger dataset.</li></ul><hr /><h3 id="recommended-generation-settings">Recommended Generation Settings</h3>My Personal Setup<ul><li>Sampler: <code>deis_3m</code></li><li>Scheduler: <code>beta57</code></li><li>CFG Scale: <code>4</code></li><li>Steps: <code>30–40</code></li></ul>Standard / Lighter Setup<ul><li>Sampler: <code>euler_a</code></li><li>Scheduler: <code>normal</code></li></ul>Note: While faster, standard settings may result in fewer details and more "plastic-looking" skin.<hr /><h3 id="prompting-guide">Prompting Guide</h3>Positive PromptStart your prompt with:&gt; <code>masterpiece, best quality, realistic, absurdres</code>* Tip: <code>realistic</code> is the key trigger word for this fine-tune. I highly recommend keeping it in your prompt at all times. Prompt Style: Natural language isn't separated by commas and offers more control than tags, while tags produce more vivid results—though this isn't an absolute rule.Negative Prompt&gt; <code>(white background:1.2), simple background, worst quality, low quality, low details, bad anatomy, bad hands, deformed hands, missing fingers, fused fingers, sketch, censor, score_1, score_2, score_3, text, watermark, artist name, flat color, (anime_source:1.2)</code><hr /><h3 id="installation">Installation</h3>* Format: This is a diffusion model (UNet), not a full standalone checkpoint. * ComfyUI Path: Place the model file in: <code>ComfyUI\models\diffusion_models\</code>* Required Files: You will need to use the standard Anima VAE and Text Encoders alongside this model.<hr />No images of real people were used during training.

Files with SHA256: 56ac2ade08153aea426402ab8d73ff42f8d7a38c5647eafe9bd5020fb2fa6ec6