Sponsorship: For sponsorship, please contact us on <a target="_blank" rel="ugc" href="https://discord.gg/6Y3XcMu3aE">Discord</a>. Your support helps us grow and improve future work. Buy Custom Models: If you're interested in buying a LoRA model, <a target="_blank" rel="ugc" href="https://discord.gg/T9dYN3zfXJ">contact us</a>—we can get it done in a short time.Update: New Version Released!I have retrained Anime Vision V1 with a completely new setup. This new version is far better than the beta version, incorporating the following enhancements:<ul><li>Dataset: 10K images</li><li>Target Epoch: 300</li><li>Total Training Steps Completed: 150K</li><li>NSFW: Still not possible</li><li>Trigger Words: No longer needed</li><li>Important Note: Avoid including NSFW-related/mature words in your prompts. Doing so may result in unreliable image outcomes. Also, avoid using too long prompts as smaller prompts work better on SD3.</li></ul>Configuration I used for training:<ul><li>GPU: A6000x2</li><li>Batch Size: 8</li><li>Optimizer: AdamW</li><li>Scheduler: Cosine with restarts</li><li>Captioning: WD14</li></ul>I hope you enjoy the improvements in this new version. As always, feel free to share your feedback in the comments or join my Discord server for more information.<h3 id="sd3-anime-vision-beta-version-is-finally-here!-5tcjyul24">SD3 Anime Vision Beta Version is Finally Here!</h3>Introducing Anime Vision, my first SD3 anime model. My friend and I started working on fine-tuning SD3, and this is the first drift of the SD3 anime model. Is this model really good for anime? Not entirely, as mentioned in the title, it's a beta version or an experimental model. We are currently testing to ensure everything is going well. I trained this model for 20k steps. After some testing, I noticed that sometimes the results were not great, so we decided to pause the SD3 training for now. Here is a quick guidelines to use this Model to its full potential :<ul><li>If you are trying to create any specific subject or object, use the trigger word 'anime style' in your prompt.</li><li>If you're targeting a character, you can ignore the keyword and go with something like this:<ul><li>For a male character: 'anime boy'</li><li>For a female character: 'anime girl' </li></ul></li></ul>Quick Guide and Parameters :<ul><li>Clip Encoder: No need</li><li>VAE: No need</li><li>Sampler: dpmpp_2m</li><li>Scheduler: sgm_uniform</li><li>Sampling Steps: 25+</li><li>CFG Scale: 3+</li></ul>For better results, try using ComfyUI<a target="_blank" rel="ugc" href="https://drive.google.com/file/d/11ZjPfdIZAkWUcKFMJL_fE7rYr27NDuME/view?usp=sharing">Workflow</a> <h3 id="available-on-tensor.art-and-shakker.ai-with-free-gpu-acceleration-mtc4olm51">Available on <a target="_blank" rel="ugc" href="http://tensor.art">tensor.art</a> and <a target="_blank" rel="ugc" href="http://shakker.ai">shakker.ai</a> with Free GPU acceleration</h3><ul><li><a target="_blank" rel="ugc" href="https://tensor.art/models/749118162995308332/Anime-Vision-Beta">tensor.art</a></li><li><a target="_blank" rel="ugc" href="https://www.shakker.ai/modelinfo/560ce5193fb142e0b7697a6c467f0b6b?from=personal_page">shakker.ai</a> </li></ul>Important : Do not include NSFW-related/mature words or censor words in your prompt. Doing so may result in unreliable or undesirable image outcomes.A big thanks to <a target="_blank" rel="ugc" href="https://civarchive.com/user/Shopon_Skp">Shopon SKP</a> for working so hard with me.Note : This is not a merged or modified model. It is the original Anime Vision fine-tuned model. Some users have been spreading incorrect information in the model's comment section. If you have any questions or want to know more, join my <a target="_blank" rel="ugc" href="https://discord.gg/VY7SeBwEx8">Discord</a> server or share your thoughts in the comment section. Thank you for your time.

Files with SHA256: 5dbacd216836572c642745303ccf24c4c164da9c3585a45f18f1951fa723713b