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.3D Cartoon Vision | FLUXI'm excited to introduce my latest creation, 3D Cartoon Vision. Unlike my previous model, Vision Realistic Flux dev fp8, which focused on photorealism, this model is specifically designed for generating high-quality 3D cartoon images.Why 3D Cartoon Vision?While my earlier work aimed at perfecting realistic imagery, I wanted to explore a different style with this model. 3D Cartoon Vision brings vibrant, detailed 3D cartoon visuals to life. The model handles textures, lighting, and character design in a way that sets it apart from more realistic models.How I Made This Model:I trained new LoRA models focused on 3D cartoon aesthetics and then merged them into three different versions of 3D Cartoon Vision to suit various needs:<ul><li>FP8 Model (No CLIP and VAE): 11.08GB – Ideal for users with lower GPU power, offering efficiency while maintaining quality.</li><li>FP8 Model with Baked VAE &amp; CLIP: 15.91GB – A balanced option with baked-in components for those who prefer an all-in-one model.</li><li>FP16 Full Model (Without CLIP &amp; VAE): 22.17GB – For those who want the highest quality and have the GPU power to handle it.</li></ul>Note:<ul><li>If you downloaded the 11.08GB/22.17GB model, move it to <code>ComfyUI\models\unet</code> after downloading.</li><li>If you downloaded the 15.91GB model, move it to <code>ComfyUI\models\checkpoints</code> after downloading.</li></ul>All versions are built to perform efficiently on different hardware setups, giving you the flexibility to choose based on your system's capabilities.How to Use This Model:You can run this model on ComfyUI. I’ve only had time to test it on ComfyUI, so if you try it on something else, I’d love to hear about your experience in the comments.Quick Parameters for ComfyUI:<ul><li>VAE: Already baked in</li><li>Sampler: Euler</li><li>Scheduler: Simple</li><li>Sampling Steps: 20</li><li>CFG Scale: 1</li></ul>Workflow<a target="_blank" rel="ugc" href="https://civarchive.com/models/658885?modelVersionId=737240">fp8/fp16 Clip+vae</a><a target="_blank" rel="ugc" href="https://civarchive.com/models/658885?modelVersionId=737240"><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/852a84cb-8799-4741-a034-28b5b746ffec/width=525/852a84cb-8799-4741-a034-28b5b746ffec.jpeg" />fp8 baked clip+vae</a><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/9bcdfdfa-5e39-48a2-b21e-ca8cdeb7d87d/width=525/9bcdfdfa-5e39-48a2-b21e-ca8cdeb7d87d.jpeg" />3D Cartoon Vision | SD3M I am excited to present my latest creation: a 3D Cartoon checkpoint model based on SD3M. This model has undergone over 30k training steps and is currently in its beta version. I am also working on another version, which has completed training and is undergoing testing. What about this model?This is a Cartoon model, capable of generating images in cartoon style, 3D cartoon, and real cartoon formats. No trigger words are needed. Configuration I used for training :<ul><li>GPU: A6000x2</li><li>Dataset: A mix of 2k real cartoon and 3D cartoon images</li><li>Batch Size: 8</li><li>Optimizer: AdamW</li><li>Scheduler: cosine with restarts</li><li>Epoch: Target of 200 epochs</li><li>Captioning: WD14 and BLIP mix</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>Available on <a target="_blank" rel="ugc" href="https://tensor.art/models/751522146385161429?source_id=nzy3r1nrkkezpfQiYH_x9hcl">tensor.art</a> with Free GPU acceleration<ul><li><a target="_blank" rel="ugc" href="https://tensor.art/models/751522146385161429?source_id=nzy3r1nrkkezpfQiYH_x9hcl">Model</a></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><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/fa4e480c-1a47-4d5b-bb88-ff197dfaf0e1/width=525/fa4e480c-1a47-4d5b-bb88-ff197dfaf0e1.jpeg" />Important : Do not include NSFW-related/mature words or censor words in your prompt. Doing so may result in unreliable or undesirable image outcomes. Note : This is not a merged or modified model. It is the original 3D Cartoon 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: 333c413309eda9ad3dfa676c90333ae8e3e3d670a60843abedc120dd6d2c5067