<h3 id="raemu-flux-23uv1sgin">Raemu Flux</h3>A finetuned model built on top of Flux.1-dev, specifically focused on anime. It has been finetuned with dataset nearly 1,500 carefully curated, high-quality aesthetic anime images, resulting in noticeable improvements in anime scene rendering and visual quality.<hr />Enjoying my work? Consider supporting the development of my models by buying me a coffee on <a target="_blank" rel="ugc" href="https://ko-fi.com/raelina">Ko-fi</a>Also check out my other models on Mage: <a target="_blank" rel="ugc" href="https://www.mage.space/play/55ee9a305fc7e3572509def13acbefbf">Raepix Focus XL</a> / <a target="_blank" rel="ugc" href="https://www.mage.space/play/08df2e9b11b4d9587dcbb6846a9dda11">Raepix Focus XL Lightning</a> / <a target="_blank" rel="ugc" href="https://www.mage.space/play/41658a734e3918e89e700c76f103ffc7">Raevitamix Realistic</a> / <a target="_blank" rel="ugc" href="https://www.mage.space/play/b1586a8de40e97411fdcda1fe03ceb60">Raevista XL</a><hr /><h3 id="recommended-setting-inie0m26e">Recommended Setting</h3>The model does not include VAE and CLIP, which are essential components. You must have them.*Baked version already included all clips and vae.Download both clip_l and t5 from <a target="_blank" rel="ugc" href="https://huggingface.co/comfyanonymous/flux_text_encoders/tree/main">here</a> and place them in the respective folders: <code>text_encoder</code> for ForgeUI and <code>clip</code> for ComfyUI.<ul><li>steps: 20 - 30</li><li>Distilled CFG/Guidance: 3.5 - 4.0</li><li>CFG: 1.0</li><li>Sampler: euler/dpm++ 2m simple</li><li>Vae: flux ae</li><li>clip: clip_l and t5xxl</li></ul><h3 id="usage-75fi8kfc0">Usage</h3>Be sure to include "anime" in your prompt; otherwise, the output may appear realistic. For example: "A woman anime hold sign that says Hello World."<h3 id="license-cc0clj0wa">License</h3>The model falls under <a target="_blank" rel="ugc" href="https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md">flux-1-dev-non-commercial-license</a>

Raemu Flux

Baked version included all clips and vae

raemuFlux_v10Baked.safetensors

v1.0 baked

v1.0

Raemu FluxA finetuned model built on top of Flux.1-dev, specifically focused on anime. It has been finetuned with dataset nearly 1,500 carefully curated, high-quality aesthetic anime images, resulting in noticeable improvements in anime scene rendering and visual quality.If you enjoy my work and like it, you can support me at <a target="_blank" rel="ugc" href="https://ko-fi.com/raelina">Ko-fi</a>Recommended Setting<ul><li>steps: 20 - 30</li><li>Distilled CFG/Guidance: 3.5 - 4.0</li><li>CFG: 1.0</li><li>Sampler: euler/dpm++ 2m simple</li><li>Vae: flux ae</li><li>clip: clip_l and t5xxl</li></ul>How to promptBe sure to include "anime" in your prompt; otherwise, the output may appear realistic. For example: "A woman anime hold sign that says Hello World."LicenseThe model falls under <a target="_blank" rel="ugc" href="https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md">flux-1-dev-non-commercial-license</a>

Files with SHA256: d6ba807c5827a3042467718e9f05bc23fe2166b9c266e19364f2b1fe1ccfaa44