Read the version details and recommendations in the "About this Version" section first.<h2 id="lora-trained-at-civitai-based-on-furry-artist-takahirosi">LoRA, trained at Civitai based on furry artist Takahirosi</h2>Support the artist using these links:<a target="_blank" rel="ugc" href="https://www.patreon.com/takahirosi">https://www.patreon.com/takahirosi</a><a target="_blank" rel="ugc" href="https://x.com/takahiro_si">https://x.com/takahiro_si</a><a target="_blank" rel="ugc" href="https://www.furaffinity.net/user/takahirosi/">https://www.furaffinity.net/user/takahirosi/</a><a target="_blank" rel="ugc" href="https://bsky.app/profile/takahirosi.bsky.social">https://bsky.app/profile/takahirosi.bsky.social</a><a target="_blank" rel="ugc" href="https://itaku.ee/profile/takahirosi">https://itaku.ee/profile/takahirosi</a><a target="_blank" rel="ugc" href="https://ko-fi.com/tktktk">https://ko-fi.com/tktktk</a><a target="_blank" rel="ugc" href="https://takahirosi.itch.io/">https://takahirosi.itch.io/</a> 1) Always use the tag by takahirosi2) This LoRA was based on the Pony V6 version / Illustrious-XL3) 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) If you want to force the image generator to use the Lora weight you chose, use the following tag in the positive prompt:<pre><code>&lt;lora:Takahirosi_Style_Lora: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:<pre><code>Civitai slider = 0.8

positive prompt: &lt;lora:Takahirosi_Style_Lora:0.8&gt;</code></pre>8) I added extra tags to enable artist specific content and put the tag always on the positive prompt:Dronification<pre><code>(featureless face, null face, mouthless:1.2), drone, dronification, dronesuit, latex, latex clothing, latex skinsuit, black skinsuit</code></pre>Bodysuit<pre><code>bodysuit, skinsuit, latex, latex clothing, latex skinsuit</code></pre>Goo creature<pre><code>goo creature, latex, assimilation</code></pre>Symbiote creature<pre><code>symbiote, latex</code></pre>Below is an initial configuration, but any other type of configuration is up to you: ILLUSTRIOUSModelWAI-NSFW-illustrious-SDXL - v7LoraTakahirosi Style Lora v1.0 (illustrious) - 0.5 ~ 1.0 (Preferably 0.8)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 takahirosi, (featureless face, null face, mouthless:1.2), drone, dronification, latex, latex clothing, latex skinsuit, demon, 1boy, muscular male, male focus, wings, muscular, demon boy, bara, solo, demon wings, abs, demon horns, penis, pectorals, horns, thick thighs, thighs, erection, large pectorals, full body, tail, demon tail, glowing, colored skin, red background, nipples, bulge, testicles, veins, stomach,</code></pre>Prompt (Negative)<pre><code>bad quality, worst quality, worst detail, sketch, censor</code></pre><hr />PONYModelIncursio's Meme Diffusion (SDXL, Pony) - v2.7PDXLLoraTakahirosi Style Lora v1.0 (Pony) - 0.5 ~ 1.0 (Preferably 0.8)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>score_9, score_8_up, score_7_up, by takahirosi, (featureless face, null face, mouthless:1.2), equid, qeuine, drone, dronification, latex, latex clothing, latex skinsuit, chubby, large female, female focus, large breasts, 1girl, solo, hyper breasts, camel toe, chubby, furry, furry female, lying, tail, wet, glistening body, excessive pussy juice, high-angle view, dutch angle, laboratory background</code></pre>Prompt (Negative)<pre><code>zPDXL3, 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 Takahirosi 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>

Takahirosi Style Lora (Pony / Illustrious)

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/9546501">https://civitai.com/posts/9546501</a>)

Files with SHA256: 9eba007acf50be712c0d3fd8806ebec3921ee30a40381ded926d38e32b711d71