Declaration: I suggest illustrators and arts cannot be replaced by AI, although these models can accelerate design/drawing, the details, sprite-inside, visual-logics cannot be Datafication in Neural Networks.The 3d hand lora is:<ul><li>Dataset: 512*512</li><li>Trigger words: hand</li><li>Realistic checkpoint suggested</li><li>DPM ++2S a Karras suggested<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/c95091f2-eca0-4fd3-a8c2-41055ed3259e/width=525/c95091f2-eca0-4fd3-a8c2-41055ed3259e.jpeg" /></li></ul>-----------------------------——·--··c🫰c--··—--------------------------------This lora is trained by 221 high-quality image, classified by full body &amp; half body. V2.0 adds objects image to be trained, and it has greater outputs. Add hires to adjust details in txt2img.Used without trigger words.<ul><li>Train dataset:512*512</li><li>CFG scale:7-8</li><li>Sampling Steps:20-30</li><li>Suggested sampler: Euler</li><li>Suggested VAE: animevae.pt</li></ul>No Trigger words<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/7ab01307-9b23-44d5-8178-b30b7c434a7b/width=525/7ab01307-9b23-44d5-8178-b30b7c434a7b.jpeg" />All train data collection are human-manual, and training cloud environment costs me much. hope your donation to support my new model. <a target="_blank" rel="ugc" href="https://ko-fi.com/cecily34">https://ko-fi.com/cecily34</a>If you have any questions related to the model or its samples, how to get started or just want to share your creations, feel free to join my discord: <a target="_blank" rel="ugc" href="https://discord.gg/GgZFF3qPEB">https://discord.gg/GgZFF3qPEB</a>That is my pleasure.🌸 Loves U.

3d_Chracters_illustration

V2.0 is trained by 3d objects image, adjusting network dim parameter and learning times.

Files with SHA256: df466cf16fcab4ff5284e9f0783c5b30115847c9f04b73a7d969a23de37f1d0d