<h2 id="inspiration">Inspiration</h2>💃 This is a reimagining of the fictional character Manuela Vicious, by Tower13Studios: Manuela V. is 20yo and from Belfast Northern Ireland and a proud member of the gigantic Vicious family. They are nice people and gave birth to a lot of pretty daughters, the best about them is... they are entirely fictional.<hr /><h2 id="moss-image">Moss-Image</h2><ul><li>Diffusion Model: <a target="_blank" rel="ugc" href="https://openmoss.ai/MOSS-Image">Moss-Image</a></li><li>LoRA strength: 0.2–1.1</li><li>Sampler: euler or er_sde</li><li>Scheduler: simple or sgm_uniform</li><li>Steps: 30–50 —or 4–15 when paired with a Turbo LoRA</li><li>CFG Scale: 1–5</li><li>Trigger word (for superior results): ATRX_MANUELA_MOSS</li></ul><h2 id="krea-2">Krea 2</h2><ul><li>Diffusion Model: <a target="_blank" rel="ugc" href="https://www.krea.ai/krea-2-open-source">Krea 2</a>; try the Raw model paired with the Turbo LoRA set to 0.5–1</li><li>LoRA strength: 0.8–1.5</li><li>Sampler: euler or euler_ancestral | er_sde (refiner)</li><li>Scheduler: simple or beta | sgm_uniform (refiner)</li><li>Steps: 8–12 for Raw paired with Turbo LoRA —or try about 6–12 steps on a first sampler and 2–3 on a second sampler with 0.1–0.4 denoise</li><li>CFG Scale: 1 with Turbo model</li><li>Trigger word (for superior results): ATRX_MANUELA_KREA2</li></ul><h2 id="flux.2-klein-9b">Flux.2 Klein 9B</h2><ul><li>Diffusion Model: <a target="_blank" rel="ugc" href="https://civarchive.com/models/2322332/flux2-klein">Flux.2 Klein 9B</a></li><li>LoRA strength: 0.8–1.6</li><li>Sampler: euler, euler_ancestral, res_multistep, or dpmpp_2s_ancestral</li><li>Scheduler: simple or beta</li><li>Steps: 4–12; 30–50 for base model</li><li>CFG Scale: 1, or try 1.2–3; 2–5 for base model</li><li>Trigger word (for superior results): ATRX_MANUELA_FLUX2KLEIN9B</li></ul><h2 id="z-image-turbo">Z-Image —Turbo</h2><ul><li>Diffusion Model: <a target="_blank" rel="ugc" href="https://civarchive.com/models/2168935/z-image-turbo">Z-Image Turbo</a>, or try <a target="_blank" rel="ugc" href="https://civarchive.com/models/2342797/z-image-base">Z-Image [Base]</a> —or try a finetuned model, with very good results paired with <a target="_blank" rel="ugc" href="https://civarchive.com/models/2218365/cyberrealistic-z-image-turbo?modelVersionId=2780276">CyberRealistic Z-Image Turbo v3.0</a></li><li>LoRA strength: 1–1.6</li><li>Sampler: dpmpp_2s_ancestral</li><li>Scheduler: simple or beta</li><li>Steps: 4–12</li><li>CFG Scale: 1, or try 1.2–3; CFG Norm: 1–1.12</li><li>Shift: 7 (first sampler) and 0.6 (second sampler)</li><li>Trigger word (for superior results): ATRX_MANUELA_ZIMAGE</li><li>Negative prompt (as needed): "Asian woman, black hair"</li></ul><h2 id="qwen-image-2512">Qwen-Image 2512</h2><ul><li>Diffusion Model: <a target="_blank" rel="ugc" href="https://civarchive.com/models/2268063/qwen-image-2512">Qwen-Image 2512</a></li><li>LoRA strength: 0.8–1</li><li>Sampler: res_multistep</li><li>Scheduler: simple</li><li>Steps: 20+, or 4–8 with <a target="_blank" rel="ugc" href="https://huggingface.co/lightx2v/Qwen-Image-2512-Lightning">lightning LoRA</a></li><li>CFG Scale: 2–5, or 1 with lightning LoRA; CFG Norm: 0.94–0.98</li><li>Shift: 3.1</li><li>Trigger word (strictly required!): ATRX_MANUELA_QWEN2512</li></ul><h2 id="qwen-image">Qwen-Image</h2><ul><li>Diffusion Model: <a target="_blank" rel="ugc" href="https://civarchive.com/models/1864281">Qwen-Image</a></li><li>LoRA strength: 0.75–1</li><li>Sampler: euler</li><li>Scheduler: simple</li><li>Steps: 15+, but 20+ is better, or 4–8 with <a target="_blank" rel="ugc" href="https://huggingface.co/lightx2v/Qwen-Image-Lightning">lightning LoRA</a></li><li>CFG Scale: 2–5, or 1 with lightning LoRA; CFG Norm: 0.8–0.9</li><li>Shift: 3.1</li></ul><ul><li>IMG-2-IMG denoise: 0.2–0.6</li></ul><h2 id="flux.1">Flux.1</h2><ul><li>Diffusion Model: <a target="_blank" rel="ugc" href="https://civarchive.com/models/618692/flux">Flux.Dev 1.0</a></li><li>LoRA strength: 0.8–1.4</li><li>Sampler: deis or euler</li><li>Scheduler: beta or simple (or ddim_uniform for different look, but add steps)</li><li>Steps: 15+, but 20+ is better, or 8–12 with <a target="_blank" rel="ugc" href="https://civarchive.com/models/876388/flux1-turbo-alpha">turbo LoRA</a></li><li>CFG Scale: 2–5</li></ul><ul><li>IMG-2-IMG denoise: 0.65–0.85</li></ul><h2 id="pony">Pony</h2><ul><li>Checkpoint: <a target="_blank" rel="ugc" href="https://civarchive.com/models/153568?modelVersionId=832353">Real Dream SDXL Pony 12</a></li><li>LoRA strength: 0.6–1</li><li>Sampler: DPM++ SDE or euler</li><li>Scheduler: turbo or simple</li><li>Steps: 20–30+, or 8–12 with <a target="_blank" rel="ugc" href="https://civarchive.com/models/1181892?modelVersionId=1330126">turbo LoRA</a></li><li>CFG Scale: 2–5</li><li>ADetailer recommended</li></ul>

Manuela V. —Reimagined

Character likeness may be helped by including the trigger word: ATRX_MANUELA_MOSS.The dataset for training consisted of 75 high-quality photorealistic images AI-generated in Google Flow using Imagen 4 [sadly now sunsetted across all platforms]. References were pulled from previously rendered images of the same character. SeedVR2 in ComfyUI was used to upscale images from 1024x1024 to 1280x1248. Most captioning was initially produced by Qwen Chat for previous datasets.No known reference to any real person was included in any part of the training.

Files with SHA256: f77ccc1da4511ac7a99894b5e1d0d56df9e767b33bda3b1098a1b367e8ec13d1