Read the version details and recommendations in the "About this Version" section first.Preferably use the updated and stable version 2.0 if you use the Pony version<h2 id="lora-trained-at-civitai-based-on-furry-artist-melonart">LoRA, trained at Civitai based on furry artist MelonArt</h2>or known as MLeonheArt / mleonheartfaSupport the artist using these links:<a target="_blank" rel="ugc" href="https://www.patreon.com/melonart">https://www.patreon.com/melonart</a><a target="_blank" rel="ugc" href="https://subscribestar.adult/melonart">https://subscribestar.adult/melonart</a><a target="_blank" rel="ugc" href="https://www.pixiv.net/en/users/3842757">https://www.pixiv.net/en/users/3842757</a><a target="_blank" rel="ugc" href="https://www.furaffinity.net/user/mleonheartfa/">https://www.furaffinity.net/user/mleonheartfa/</a><a target="_blank" rel="ugc" href="https://twitter.com/MelonArt_X">https://twitter.com/MelonArt_X</a><a target="_blank" rel="ugc" href="https://itaku.ee/profile/melonart">https://itaku.ee/profile/melonart</a><a target="_blank" rel="ugc" href="https://mleonheart.tumblr.com">https://mleonheart.tumblr.com</a><a target="_blank" rel="ugc" href="https://melonart.newgrounds.com">https://melonart.newgrounds.com</a><a target="_blank" rel="ugc" href="https://bsky.app/profile/melonart.bsky.social">https://bsky.app/profile/melonart.bsky.social</a> 1) Always use the tag by melonart2) This LoRA was based on the Pony V6 version / Illustrious3) Even though the Pony V6 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) To better use Lora in Civitai, I recommend using VAE (SDXL VAE) and also Embedding (Pony PDXL Negative Embeddings) to reduce errors in the details of the hands and eyes7) 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 (v1.0)<pre><code>&lt;lora:MelonArt_Style_Lora_Illustrious:0.8&gt;</code></pre>Pony (v1.0)<pre><code>&lt;lora:MelonArt_Style_Lora-000017:1&gt;</code></pre>Pony (v2.0)<pre><code>&lt;lora:MelonArt_Style_Lora_v2:0.8&gt;</code></pre>Note: the number at the end of the Lora name (0.8) 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 (v1.0)<pre><code>Civitai slider = 0.8

positive prompt: &lt;lora:MelonArt_Style_Lora_Illustrious:0.8&gt;</code></pre>Pony (v1.0)<pre><code>Civitai slider = 0.8

positive prompt: &lt;lora:MelonArt_Style_Lora-000017:0.8&gt;</code></pre>Pony (v2.0)<pre><code>Civitai slider = 0.8

positive prompt: &lt;lora:MelonArt_Style_Lora_v2:0.8&gt;</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: ILLUSTRIOUSModelWAI-NSFW-illustrious-SDXL - v12.0LoraMelonArt Style Lora - v1.0 (illustrious) - 0.5 ~ 1.0 (Preferably 0.8)AdvancedCFG Scale - 3.0 ~ 9.0 (Preferably 6)Sampler - DDIM / Euler a / Euler / Heun / DPM2 / DPM++ 2M Karras / Uni PC (Preferably DPM++ 2M Karras)Steps - 20 ~ 60 (Preferably 50)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 melonart, furry, furry female, anthro, bunny, rabbit, nightclub, female focus, public, lights, light particles, 1girl, breasts, animal ears, rabbit ears, tail, rabbit tail, blonde hair, tongue, rabbit girl, one eye closed, leotard, tongue out, short hair, red eyes, cleavage, cup, playboy bunny, orange leotard, covered navel, looking at viewer, beer mug, huge breasts, holding, alcohol, mug, tray, strapless leotard, strapless, blush, smile, beer, body fur, thick thighs, bare shoulders, standing, colored skin, white fur, blurry background, hand on hip, large breasts, cowboy shot, holding tray, bangs, closed mouth, snout, animal nose, holding cup, highleg</code></pre>Prompt (Negative)<pre><code>nails, fingernails, bad quality, worst quality, worst detail, bad quality, worst quality, worst detail, sketch, censor, human, 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 (v1.0)ModelPony Diffusion V6 XL - V6 (Start with this one)LoraMelonArt Style Lora - v1.0 (Pony) - 0.5 ~ 1.0 (Preferably 1)AdvancedCFG Scale - 3.0 ~ 9.0 (Preferably 6)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>score_9, score_8_up, score_7_up, by melonart, Charizard, 1girl, nipples, solo, breasts, thick thighs, on side, huge breasts, colored skin, shiny skin, nude, orange skin, wings, thighs, lying, furry female, fire, furry, pokemon (creature), flame-tipped tail, wide hips, completely nude, tail, indoors, shiny, collarbone, curvy, half-closed eyes, large areolae, claws, pillow, bedroom background, nighttime</code></pre>Prompt (Negative)<pre><code>zPDXL-neg, 3D, score_6, score_5_up, score_4_up, human</code></pre><hr />PONY (v2.0)ModelIncursio's Meme Diffusion (SDXL, Pony)LoraMelonArt Style Lora - v1.0 (Pony) - 0.5 ~ 1.0 (Preferably 0.8)AdvancedCFG Scale - 3.0 ~ 9.0 (Preferably 4)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>score_9, score_8_up, score_7_up, by melonart, 1girl, furry female, furry, breasts, huge breasts, swimsuit, solo, goat girl, horns, red eyes, goat ears, o-ring, ocean, day, thighs, thick thighs, sky, wide hips, purple one-piece swimsuit, tail, outdoors, animal ears, snout, beach background, blue sky, cleavage, smile, body fur, water, blurry background, breast squish, squish</code></pre>Prompt (Negative)<pre><code>zPDXL3, 3D, 2D, human</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 MelonArt 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>

MelonArt Style Lora (Illustrious / Pony)

About this versionLora improvements added compared to version 1.0- Faces, eyes and hands with more definition and fewer errors- Greater compatibility with the various Pony models- Reduction of errors in image generation in Civitai- Reduction of errors in local image generation (A111, ComfyUI, etc.)- Improvements in training and better adaptation to the model's styleExample Images - (<a target="_blank" rel="ugc" href="https://civitai.com/posts/8158234">https://civitai.com/posts/8158234</a>)

Files with SHA256: 39fe33e03f7d7dd7db4f07064cea231a8b88d6cb44106b720e38831fb5cd7db0