Sponsorship: For sponsorship inquiries, please reach out to us on <a target="_blank" rel="ugc" href="https://discord.gg/6Y3XcMu3aE">Discord</a>. Your support helps us grow and improve our future work.Buy Custom Models: Interested in purchasing a custom LoRA model? <a target="_blank" rel="ugc" href="https://discord.gg/e5TwfRdsCA">Contact us</a> we can deliver quickly.<hr /><h1 id="niji-style-flux-kakabl7e0">Niji Style FLUX</h1>I’m excited to share my new model, Niji Style FLUX. This model is crafted to generate stunning Niji-style images, known for their vibrant colors and expressive, anime-inspired art.Model Details:<ul><li>Type: Niji-style image generation</li><li>Trigger Words: None required, but using them may enhance results.</li><li>Output: High-detail, vibrant, and expressive Niji-style images that truly capture the essence of anime art.</li><li>NSFW Support: No</li></ul>How I Made This Model:Following a proven approach, I trained a LoRA model specifically for Niji-style artwork. Afterward, I merged it with a base model to optimize for the unique characteristics of Niji art.Training Configuration:<ul><li>GPU: A6000</li><li>Dataset Size: 2,000 images</li><li>Captioning Tool: WD14</li><li>Batch Size: 1</li><li>Optimizer: AdamW</li><li>Learning Rate: 1e-4</li><li>Total Training Steps: 25k</li><li>Training Duration: 24+ hours</li></ul>How to Use This Model:This model is versatile and can be easily integrated into your preferred setup. If you're familiar with my previous models, you'll find this one just as user-friendly.Quick Parameters:<ul><li>Sampler: Euler</li><li>Scheduler: Simple</li><li>Sampling Steps: 20 (If using Schnell, steps should be set to 4)</li><li>CFG Scale: 1</li></ul>Model Versions:<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></ul>Note:<ul><li>If you downloaded the 11.08GB 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>Join My Community: Share your feedback, learn, and have fun with us! 😊<a target="_blank" rel="ugc" href="https://discord.gg/n4HGJkXMeK">Discord</a>

Niji Style FLUX

nijiStyleFLUX_devFp8.safetensors

dev fp8

schnell fp8

Sponsorship: For sponsorship inquiries, please reach out to us on <a target="_blank" rel="ugc" href="https://discord.gg/6Y3XcMu3aE">Discord</a>. Your support helps us grow and improve our future work.Buy Custom Models: Interested in purchasing a custom LoRA model? <a target="_blank" rel="ugc" href="https://discord.gg/e5TwfRdsCA">Contact us</a> we can deliver quickly.<hr /><h1 id="niji-style-flux-kakabl7e0">Niji Style FLUX</h1>I’m excited to share my new model, Niji Style FLUX. This model is crafted to generate stunning Niji-style images, known for their vibrant colors and expressive, anime-inspired art.Model Details:<ul><li>Type: Niji-style image generation</li><li>Trigger Words: None required, bu* ***ng them may enhance results.</li><li>Output: High-detail, vibrant, and expressive Niji-style images that truly capture the essence of anime art.</li><li>NSFW Support: No</li></ul>How I Made This Model:Following a proven approach, I trained a LoRA model specifically for Niji-style artwork. Afterward, I merged it with a base model to optimize for the unique characteristics of Niji art.Training Configuration:<ul><li>GPU: A6000</li><li>Dataset Size: 2,000 images</li><li>Captioning Tool: WD14</li><li>Batch Size: 1</li><li>Optimizer: AdamW</li><li>Learning Rate: 1e-4</li><li>Total Training Steps: 25k</li><li>Training Duration: 24+ hours</li></ul>How to Use This Model:This model is versatile and can be easily integrated into your preferred setup. If you're familiar with my previous models, you'll find this one just as user-friendly.Quick Parameters:<ul><li>Sampler: Euler</li><li>Scheduler: Simple</li><li>Sampling Steps: 20 (If using Schnell, steps should be set to 4)</li><li>CFG Scale: 1</li></ul>Model Versions:<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></ul>Note:<ul><li>If you downloaded the 11.08GB 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>Join My Community: Share your feedback, learn, and have fun with us! 😊<a target="_blank" rel="ugc" href="https://discord.gg/n4HGJkXMeK">Discord</a>

Files with SHA256: 71e080f1ba6b498a3f88a8ea3bfeae9c790c9dd8888003fa5cc99ca735c6d5bd