@noswift
Read the version details and recommendations in the "About this Version" section first.LoRA, trained at Civitai based on furry artist NoSWIFTor known as NºSwift / No_SwiftSupport the artist using these links:https://www.patreon.com/noswifthttps://x.com/No_SWIFThttps://www.furaffinity.net/user/noswifthttps://subscribestar.adult/noswifthttps://bsky.app/profile/noswift.arthttps://itaku.ee/profile/noswift1) Always use the tag @noswift (Anima) / by noswift (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 modelscore_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up,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) Add the monochrome, greyscale, sketch tag to the negative prompt if you want colored images, as LoRA was composed of black and white images or just one color palette8) If you want to force the image generator to use the Lora weight you chose, use the following tag in the positive prompt:Animalora:NoSWIFT_Style_LoRA_Anima_anima_3275253_epoch_10:1Illustriouslora:NoSWIFT_Style_Lora_Illustrious:0.8Pony (v1.0)lora:NoSWIFT_Style_Lora:0.8Note: 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:AnimaCivitai slider = 1
positive prompt: lora:NoSWIFT_Style_LoRA_Anima_anima_3275253_epoch_10:1IllustriousCivitai slider = 0.8
positive prompt: lora:NoSWIFT_Style_Lora_Illustrious:0.8Pony (v1.0)Civitai slider = 0.8
positive prompt: lora:NoSWIFT_Style_Lora:0.8Note: 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:ANIMAModelAnima - base-v1.0LoraNoSWIFT 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)masterpiece, best quality, amazing quality, very aesthetic, extremely detailed, very detailed, absurdres, newest, highres, score_9, score_8, @noswift, furry, furry male, anthro, animal ears, animal nose, snout, horse, horse boy, horse ears, mudsdale, pokemon, pokemon (creature), brown body, body fur, brown eyes, black hair, red hair, multicolored hair, mohawk, long hair, hair over shoulder, 1boy, solo, (fat:1.2), completely nude, large pectorals, nipples, biceps, veins, belly, navel, pubic hair, male pubic hair, (animal penis, horse penis:1.4), huge penis, huge testicles, thick thighs, standing, penis grab, looking at viewer, seductive smile, half-closed eyes, teeth, hand on own hip, sweat, sweaty, very sweaty, shiny skin, feet out of frame, three quarter view, outdoors, night, forest, nature, tree, plant, yellow light, sidelightingPrompt (Negative)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 logoILLUSTRIOUSModelNova Furry XL - Illustrious v3.0LoraNoSWIFT 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)masterpiece, best quality, amazing quality, very aesthetic, high resolution, ultra-detailed, absurdres, newest, scenery, depth of field, scenery, volumetric lighting, by noswift, wolf, canine, canid, canis, bara, male focus, 1boy, muscular male, muscular, solo, pectorals, penis, furry male, abs, furry, animal ears, nipples, stomach, wolf boy, uncensored, large pectorals, male pubic hair, navel, topless male, pubic hair, testicles, erection, feet out of frame, short hair, tail, armpits, arms behind head, armpit hair, veinsPrompt (Negative)bad quality, worst quality, worst detail, sketch, censor, high heels, platform heels, platform footwear, 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-generatedPONY (v1.0)ModelPrefect Pony XL (v3)LoraNoSWIFT Style Lora - 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)score_9, score_8_up, score_7_up, by noswift, male focus, penis, 1boy, bara, muscular male, solo, muscular, pectorals, nude, stomach, navel, nipples, thick thighs, thighs, completely nude, horns, flaccid, large pectorals, scar, abs, furry male, foreskin, testicles, short hair, dragon boy, colored skin, furry, monster boy, cum, rocket, forestPrompt (Negative)zPDXL3, 3D, 2D, monochrome, greyscale, sketch, humanAs 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 (https://civitai.com/models/332646/pony-pdxl-negative-embeddings).General Observations:If possible, give credit to the author NoSWIFT while using this LoRA.Do not sell or commercialize this LoRADo not remove metadata from images generated by LoRA.
