Read the version details and recommendations in the "About this Version" section first.<h2 id="lora-trained-at-civitai-based-on-furry-artist-milkybody">LoRA, trained at Civitai based on furry artist MilkyBody</h2>or known as mabocorescant / askmssukiSupport the artist using these links:<a target="_blank" rel="ugc" href="https://www.patreon.com/MaboCorescant">https://www.patreon.com/MaboCorescant</a><a target="_blank" rel="ugc" href="https://www.furaffinity.net/user/milkybody/">https://www.furaffinity.net/user/milkybody/</a><a target="_blank" rel="ugc" href="https://twitter.com/MaboCorescant/">https://twitter.com/MaboCorescant/</a><a target="_blank" rel="ugc" href="https://milkybody.deviantart.com/">https://milkybody.deviantart.com/</a><a target="_blank" rel="ugc" href="https://bsky.app/profile/mabocorescant.bsky.social">https://bsky.app/profile/mabocorescant.bsky.social</a><a target="_blank" rel="ugc" href="https://e621.net/artists/askmssuki.tumblr.com/">askmssuki.tumblr.com/</a>1) Always use the tag by milkybody2) This LoRA was based on the Illustrious3) Even though the Illustrious base model is used, some other models may have some inconsistencies in the images, especially in the eyes and hands, if used in Civitai, use some Embedding / Face Fix to get better results. For those who use Comfyui, the best results will be with some Hirefix / DDetailer to improve the image of the character's face.4) LoRA weight change in Civitai is at your discretion5) To better use Lora in Civitai, I recommend using VAE (SDXL VAE) to reduce errors in the details of the hands and eyes.6) Depending on the pose, you may need to increase the tag weight in the positive prompt—for example (ass focus:1.4) or (from behind:1.4) and even include extra tags like cowboy shot, feet out of frame or close-up. This is because the artist uses full-body character shots in about 80% of their images.7) Check first for a model compatible with your chosen image, some models affect Lora in the final result of the image generation for some types such as: furry, human, realistic images, etc. Therefore, the same model may not always be suitable for different types of images.8) If you want to force the image generator to use the Lora weight you chose, use the following tag in the positive prompt:Illustrious<pre><code>&lt;lora:MilkyBody_Style_Lora_Illustrious:1&gt;</code></pre>Note: the number at the end of the Lora name (1) refers to the Lora weight. In image generators, we have a weight slider, but if you want to "force" it, use the same number as the image generator slider in the positive prompt, for example:Illustrious<pre><code>Civitai slider = 1

positive prompt: &lt;lora:MilkyBody_Style_Lora_Illustrious:1&gt;</code></pre>9) I added tags related to the artist's best-known characters, if you want an image close to the character, don't forget to enter the character's name, I will leave examples of prompt positive right below each character:Suki<pre><code>by milkybody, suki (by milkybody), humanoid, female, cat humanoid, animal humanoid, feline humanoid, brown body, dark skin, dark-skinned female, purple hair, long hair, makeup, eyelashes, yellow eyes, red lips, lipstick, huge breasts, belly, thick thighs, wide hips, claws, yellow claws, curvy, plump, fluffy tail, (mature female:1.4), 1girl, solo, office lady, business suit, red jacket, blazer, frills, cleavage, bursting breasts, red skirt, pencil skirt, miniskirt, garter straps, black thighhighs, standing, legs together, holding fruit, apple, looking at viewer, seductive smile, hand on own hip, simple background, gradient background, cowboy shot, feet out of frame</code></pre>Note: The artist uses several well-known furry characters (cartoons, movies, comics, etc.), but in the training I left Lora flexible and malleable to be adapted / mixed with other Loras. My recommendation is that you use a character-specific Lora so that the final result is satisfactory.Below is an initial configuration, but any other type of configuration is up to you: ILLUSTRIOUSModelIllustrious XL personal merge (noob v-pred0.5 test merge updated) - v3.0_noob-1.0basedLoraMilkyBody Style Lora v1.0 (illustrious) - 0.5 ~ 1.0 (Preferably 1)AdvancedCFG Scale - 3.0 ~ 9.0 (Preferably 5)Sampler - DDIM / Euler a / Euler / Heun / DPM2 / DPM++ 2M Karras / Uni PC (Preferably Euler a)Steps - 20 ~ 60 (Preferably 25)Clip Skip - 1/2VAE - SDXL VAEPrompt (Positive)<pre><code>masterpiece, best quality, amazing quality, very aesthetic, high resolution, ultra-detailed, absurdres, newest, scenery, depth of field, scenery, volumetric lighting, by milkybody, furry, furry male, anthro, animal ears, animal nose, snout, domestic dog, dobermann, dog boy, dog ears, black fur, body fur, 1boy, solo, completely nude, (inflatable, living inflatable, expansion:1.4), latex, midriff, navel, (hyper penis, hyper testicles:1.4), lying, on side, on floor, full body, arm rest, head rest, looking at viewer, smile, simple background, grey background</code></pre>Prompt (Negative)<pre><code>bad quality, worst quality, worst detail, sketch, lowres, jpeg artifacts, signature, watermark, username, artist name, big belly</code></pre>General Observations:<ul><li>If possible, give credit to the author MilkyBody while using this LoRA.</li><li>Do not sell or commercialize this LoRA.</li><li>Do not remove metadata from images generated by LoRA.</li></ul>

MilkyBody Style Lora (Illustrious)

<div data-type="blurb" data-id="78">About this versionMore distant images may show some artifacts, distortions or disproportions in the face when generating images in Civitai, which is why the recommendation of this LoRA is to use characters closer to the image or use some Embedding / Face Fix to reduce errors in the face.</div>

Files with SHA256: 1180bae56744d29263d7c273f346bfd4ab0164894017495b7fe0bc101ededbc5