Read the version details and recommendations in the "About this Version" section first.<h2 id="lora-trained-at-civitai-based-on-furry-artist-drako-goqwcfja6">LoRA, trained at Civitai based on furry artist Drako</h2>or known as drakonsfw / drakodoge / drako1997Support the artist using these links:<a target="_blank" rel="ugc" href="https://www.patreon.com/drakodoge">https://www.patreon.com/drakodoge</a><a target="_blank" rel="ugc" href="https://www.furaffinity.net/user/drako1997">https://www.furaffinity.net/user/drako1997</a><a target="_blank" rel="ugc" href="https://www.deviantart.com/drako1997">https://www.deviantart.com/drako1997</a><a target="_blank" rel="ugc" href="https://itaku.ee/profile/drakodoge">https://itaku.ee/profile/drakodoge</a><a target="_blank" rel="ugc" href="https://drakodoge.newgrounds.com">https://drakodoge.newgrounds.com</a><a target="_blank" rel="ugc" href="https://bsky.app/profile/drakodoge.bsky.social">https://bsky.app/profile/drakodoge.bsky.social</a><a target="_blank" rel="ugc" href="https://subscribestar.adult/drakodoge">https://subscribestar.adult/drakodoge</a><a target="_blank" rel="ugc" href="https://mixcloud.com/drakodoge">https://mixcloud.com/drakodoge</a><a target="_blank" rel="ugc" href="https://x.com/DrakoNSFW">https://x.com/DrakoNSFW</a><a target="_blank" rel="ugc" href="https://x.com/DrakoDoge">https://x.com/DrakoDoge</a> 1) Always use the tag by drako2) This LoRA was based on the Pony V6 version / Illustrious3) Even though the Pony V6 base / Illustrious 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:Drako_Style_Lora_Illustrious:1&gt;</code></pre>Pony (v1.0)<pre><code>&lt;lora:Drako_Style_Lora-000019:0.8&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 (v1.0)<pre><code>Civitai slider = 1

positive prompt: &lt;lora:Drako_Style_Lora_Illustrious:1&gt;</code></pre>Pony (v1.0)<pre><code>Civitai slider = 0.8

positive prompt: &lt;lora:Drako_Style_Lora-000019:0.8&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: Dean<pre><code>by drako, furry, furry male, anthro, dean, domestic dog, canine, blonde hair, short hair, blonde eyebrow, yellow eyes, purple fur, white fur, body fur, two-tone fur, ear piercing, piercing, eyewear, glasses, rectangular glasses, neck tuft, animal ears, animal nose, snout, 1boy, solo, big ass, anus, perineum, big testicles, tail, smile, grin, nipples, looking at viewer, looking back, presenting, ass focus, completely nude, blush, lying, on side, from behind, half-closed eyes, seductive smile, hand on own ass, pectorals, closed mouth, spread ass, spread anus, happy, grabbing own ass, feet out of frame, green background, orange background, gradient background, halftone background</code></pre>Diane<pre><code>by drako, furry, furry female, anthro, diane, domestic dog, canine, blonde hair, long hair, blonde eyebrow, yellow eyes, purple fur, white fur, body fur, two-tone fur, ear piercing, piercing, eyewear, glasses, rectangular glasses, neck tuft, animal ears, animal nose, snout, 1girl, solo, large breasts, pussy, open mouth, tongue out, looking at viewer, looking back, anus, all fours, from behind, happy, presenting, presenting ass, paws, pawpads, smile, bangs, half-closed eyes, top-down bottom-up, completely nude, blush, tail raised, animal ear fluff, black fur, teeth, sideboob, breast press, pussy juice, pussy juice dripping, feet out of frame, yellow background, red background, gradient background, halftone background</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: ILLUSTRIOUS (v1.0)ModelNova Furry XL - Illustrious v8BLoraDrako 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 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 drako, furry, furry female, anthro, furry male, domestic cat, feline, 1girl, 1boy, sex, cowgirl position, sex, vaginal, female on top, girl on top, large breasts, huge breasts, open mouth, tongue out, nipples, cum, cum in pussy, cum in uterus, cervical contact, penis, tail, animal ears, animal nose, white hair, black hair, navel, pussy, vaginal, nude, on bed, collar, indoors, blush, long hair, on back, bed, male lying, body fur, bedroom, window, female focus, ahegao face, stomach, overflow, ejaculation, snout, saliva, fertilization, ovum, impregnation</code></pre>Prompt (Negative)<pre><code>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 digits, fewer digits, cropped, very displeasing, (worst quality, bad quality:1.2), bad anatomy, sketch, jpeg artifacts, signature, watermark, username, simple background, conjoined, bad ai-generated</code></pre><hr />PONY (v1.0)ModelPony Diffusion V6 XL - V6 (Start with this one)LoraDrako Style Lora - v1.0 (Pony) - 0.4 ~ 0.8 (Preferably 0.8)AdvancedCFG Scale - 5.0 ~ 9.0 (Preferably 5)Sampler - DDIM / Euler a / Euler / Heun / DPM2 / DPM++ 2M Karras / Uni PC (Preferably Euler a)Steps - 20 ~ 50 (Preferably 30)Clip Skip - 1/2VAE - nonePrompt (Positive)<pre><code>score_9, score_8_up, score_7_up, by drako, furry, anthro, solo focus, female, breasts, avian, bird, pussy, blue body, blue hair, black eyes, hair, large breasts, arms up, makeup, open mouth, looking at viewer, arms behind head, curvy figure</code></pre>Prompt (Negative)<pre><code>zPDXL-neg, 3D, 2D</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 Drako 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>

Drako Style Lora (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 Embedding / Face Fix to reduce errors in the face.Example Images - (<a target="_blank" rel="ugc" href="https://civitai.com/posts/18462652">https://civitai.com/posts/18462652</a>)

Files with SHA256: c16718f79cd1b1d3c8ebbd91eb640a697d8b13e15a991601383b385a27f513c7