Read the version details and recommendations in the "About this Version" section first.<h2 id="lora-trained-at-civitai-based-on-artist-demimond">LoRA, trained at Civitai based on artist Demimond</h2>or known as demimond / demi_🔞 / holard / ardenholmSupport the artist using these links:<a target="_blank" rel="ugc" href="https://www.patreon.com/Demimond">https://www.patreon.com/Demimond</a><a target="_blank" rel="ugc" href="https://www.furaffinity.net/user/demimond23">https://www.furaffinity.net/user/demimond23</a><a target="_blank" rel="ugc" href="https://demimond.newgrounds.com">https://demimond.newgrounds.com</a><a target="_blank" rel="ugc" href="https://cohost.org/Demimond">https://cohost.org/Demimond</a><a target="_blank" rel="ugc" href="https://www.hentai-foundry.com/user/Demimond23/profile">https://www.hentai-foundry.com/user/Demimond23/profile</a><a target="_blank" rel="ugc" href="https://piczel.tv/gallery/Demimond">https://piczel.tv/gallery/Demimond</a><a target="_blank" rel="ugc" href="https://piczel.tv/gallery/Holard">https://piczel.tv/gallery/Holard</a> 1) Always use the tag @demimond (Anima) / by demimond (Illustrious, Pony)2) This LoRA was based on the Anima / Illustrious / Pony V6 version3) Even though the Pony V6 / 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) Don't forget to use tags related to the Pony model<pre><code>score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up,</code></pre>5) LoRA weight change in Civitai is at your discretion6) Add the monochrome, greyscale tag to the negative prompt if you want colored images, as LoRA was composed of black and white images or just one color palette7) To use 100% Furry in Pony models I recommend using a model that is compatible with Furrys and also put the following tag in the negative prompt:<pre><code>(human:1.3)</code></pre>8) 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.9) If you want to force the image generator to use the Lora weight you chose, use the following tag in the positive prompt:Anima<pre><code>&lt;lora:Demimond_Style_LoRA_Anima_epoch_13:1&gt;</code></pre>Illustrious (v1.0)<pre><code>&lt;lora:Demimond_Style_Lora_Illustrious:1&gt;</code></pre>Pony (v1.0)<pre><code>&lt;lora:Demimond_Style_Lora: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:Anima<pre><code>Civitai slider = 1

positive prompt: &lt;lora:Demimond_Style_LoRA_Anima_epoch_13:1&gt;</code></pre>Illustrious (v1.0)<pre><code>Civitai slider = 1

positive prompt: &lt;lora:Demimond_Style_Lora_Illustrious:1&gt;</code></pre>Pony (v1.0)<pre><code>Civitai slider = 1

positive prompt: &lt;lora:Demimond_Style_Lora:1&gt;</code></pre>Below is an initial configuration, but any other type of configuration is up to you: ANIMAModelAnima - base-v1.0LoraDemimond Style Lora v1.0 (Anima) - 0.5 ~ 1.0 (Preferably 1)AdvancedCFG Scale - 4.0 ~ 6.0 (Preferably 5)Sampler - DDIM / Euler a / Euler / Heun / DPM2 / DPM++ 2M Karras / Uni PC / er_sde (Preferably Euler a)Steps - 20 ~ 60 (Preferably 30)Clip Skip - 1/2Prompt (Positive)<pre><code>masterpiece, best quality, amazing quality, very aesthetic, extremely detailed, very detailed, absurdres, newest, highres, score_9, score_8, @demimond, furry, furry female, anthro, animal ears, animal nose, snout, donkey kong (series), dixie kong, primate, brown fur, tan fur, two tone fur, body fur, green, eyes, blonde hair, blunt bangs, long hair, ponytail, black eyes, 1girl, solo, 1980s fashion, white leotard, highleg leotard, covered erect nipples, pink leggings, leggings, huge ass, covered ass, standing, three quarter view, from behind, holding water bottle, towel around neck, sweat, sweaty, very sweaty, shiny skin, wet hair, wet clothes, looking at viewer, looking back, half-closed eyes, seductive smile, open mouth, simple background, indoors, fitness gym, simple background</code></pre>Prompt (Negative)<pre><code>worst quality, low quality, score_1, score_2, score_3, blurry, jpeg artifacts, sepia, low quality, worst quality, blurry, bad anatomy, extra limbs, deformed, watermark, text, signature, bareness, artifacts, hands, copyrights name, jpeg_artifacts, scan_artifacts, bad hands, missing fingers, extra digit, fewer digits, artistic error, ye-pop, deviantart, logo, patreon logo, teeth</code></pre><hr />ILLUSTRIOUSModelNova Animal XL - Illustrious v3.0LoraDemimond Style Lora - v1.0 (illustrious) - 0.5 ~ 1.0 (Preferably 1)AdvancedCFG Scale - 3.0 ~ 9.0 (Preferably 7)Sampler - DDIM / Euler a / Euler / Heun / DPM2 / DPM++ 2M Karras / Uni PC (Preferably Euler a)Steps - 20 ~ 60 (Preferably 30)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 demimond, furry, furry female, anthro, krystal (star fox), star fox, 1girl, solo, tail, big ass, animal ears, short hair, looking back, tail ring, blue fur, (body fur:1.2), nude, tail ornament, blue hair, barefoot, sitting, object insertion, sex toy, tattoo, snout, anal, hairband, medium breasts, fox ears, animal nose, seiza, sitting on knees, barefoot, pawspads, paws, full body, looking at viewer, from behind, looking back, spacecraft, indoors, space, futuristic, moon, vehicle, window</code></pre>Prompt (Negative)<pre><code>monochrome, greyscale, bad quality, worst quality, worst detail, bad quality, worst quality, worst detail, sketch, censor, multiple tails, modern, recent, old, oldest, graphic, cartoon, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured, long body, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, very displeasing, (worst quality, bad quality:1.2), bad anatomy, sketch, jpeg artifacts, signature, watermark, username, simple background, conjoined, ai-generated, worst quality, low quality, off-topic, old, early, chromatic aberration, abstract, jpeg artifacts, scan artifacts, logo</code></pre><hr />PONY ModelPony Diffusion V6 XL - V6 (Start with this one)LoraDemimond Style Lora - v1.0 (Pony) - 0.5 ~ 1.0 (Preferably 1)AdvancedCFG Scale - 3.0 ~ 9.0 (Preferably 7)Sampler - DDIM / Euler a / Euler / Heun / DPM2 / DPM++ 2M Karras / Uni PC (Preferably Euler a)Steps - 20 ~ 60 (Preferably 30)Clip Skip - 1/2VAE - nonePrompt (Positive)<pre><code>score_9_up, score_8_up, score_7_up, by demimond, 1girl, solo, ass, dark skin, pussy, dark-skinned female, anus, looking back, bent over, brown hair, presenting, uncensored, no panties, bare shoulders, short hair, from behind, looking at viewer, lips, green eyes, grass, nail polish, thighhighs, thick thighs, huge ass, barefoot, off shoulder, thighs, single thighhigh, jewelry, makeup, high-angle view</code></pre>Prompt (Negative)<pre><code>zPDXL3, 3D, 2D, monochrome, greyscale</code></pre> As this model is based on Pony Diffusion there's not much need to specify anything in the negative prompt, because the Pony model is very flexible, but I always leave the zPDXL-neg tag (<a target="_blank" rel="ugc" href="https://civarchive.com/models/332646/pony-pdxl-negative-embeddings">https://civarchive.com/models/332646/pony-pdxl-negative-embeddings</a>).General Observations:<ul><li>If possible, give credit to the author Demimond 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>

Demimond Style Lora (Anima / Illustrious / Pony)

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 upscaling toolExample Images - (<a target="_blank" rel="ugc" href="https://civitai.red/posts/30462562">https://civitai.red/posts/30462562</a>)

Files with SHA256: feb66538cdb7f358b1b9ca56608683513467f08528b1f2b99f0a9540ff98ab70