<h3 id="kiria-jef-from-kangoku-senkan-3-is-on-pony-noobai-xl-(illustrious)-and-sd1.5-now!-5geopb8n2">Kiria Jef from Kangoku Senkan 3 is on Pony, NoobAI-XL (Illustrious) and SD1.5 now!</h3>For NoobAI-XL V-pred:Check my <a target="_blank" rel="ugc" href="https://civarchive.com/articles/10226">guide</a> about V-pred image generating!The best model to use V-pred is <a target="_blank" rel="ugc" href="https://civarchive.com/models/1080969/noobai-cyberfix-v2perpendicular-cyberfix-v2-vpred">Cyberfix</a>! But pure <a target="_blank" rel="ugc" href="https://civarchive.com/models/833294?modelVersionId=1190596">NoobAI-XL V-pred</a> is also good.For Illustrious mixes and NoobAI-XL Epsilon: use NoobAI-Xl Epsilon (especially mixes based on NoobAI-XL Epsilon!).<a target="_blank" rel="ugc" href="https://civarchive.com/articles/8709/noobai-xl-10-epsilon-optimal-settings-and-loras-announcement">Guide</a> about NoobAI-XL Epsilon.PonyXL / NoobAI-XL and SD 1.5 tags:Main:kiria jef, 1girl, mature female, dark-skinned female, white hair, short hair, blue eyes, outfit: black coat, strapless bra, miniskirt, knee boots optional:body writing, highleg panties<h3 id="noobai-xl-quality-prompt:-3xyioy9ra">NoobAI-XL quality prompt:</h3>Put "masterpiece, best quality, good quality" in positive and put "low quality, worst quality" in negative.Use euler, cfg 4-5. Don't use higher CFG!If you have over-constrasted picture and cfg 4-5 didn't help you can try to put in negative "colorful".<a target="_blank" rel="ugc" href="https://civarchive.com/user/Enigmata/articles">More in my articles</a><a target="_blank" rel="ugc" href="https://civarchive.com/articles/8709">.</a><h3 id="ponydiffusion-v6-(xl)-settings:-8fn8ujp00">PonyDiffusion v6 (XL) settings:</h3>Style settings (very important):score_9, score_8_up, score_7_up, score_6_up, score_5_up,Negative prompt (recommended):dutch angle, censored, mosaic censoring, jpeg artifacts, muscularUpscaler / adetailer settings:Hires.fix: Upscaler foolhardy_remacri (download and put in "ESRGAN" folder in "models" if you are using automatic1111 or forge).Hires steps: 16-18Denoising strength: 0.3Adetailer: denoising strength 0.3. Detection model confident threshhold: 0.7-0.8.Best sampling method is euler / euler a, 25-40 sampling steps, You don't need any DPM++Don't forget to like LoRA model :3<a target="_blank" rel="ugc" href="https://tensor.art/u/604375505701151021">https://tensor.art/u/604375505701151021</a>

Kiria Jef (Kangoku senkan 2) PonyXL / NoobAI EPS Illustrious / V-pred / SD 1.5

NOOB-AI XL V-PREDICTION TYPE MODEL! PLEASE READ NOTE ABOUT V-PRED BEFORE USE!

Kiria Jef3216 NoobAI-XL V-pred.safetensors

NoobAI-XL V-PRED

NoobAIXL EPS Illustrious

v1.0 (SD1.5 anime)

v1.0 (PonyDiffusionV6 XL)

<h3 id="kiria-jef-from-kangoku-senkan-3-is-on-pony-noobai-xl-(illustrious)-and-sd1.5-now!-5geopb8n2">Kiria Jef from Kangoku Senkan 3 is on Pony, NoobAI-XL (Illustrious) and SD1.5 now!</h3>For NoobAI-XL V-pred:Check my <a target="_blank" rel="ugc" href="https://civitai.com/articles/10226">guide</a> about V-pred image generating!The best model to use V-pred is <a target="_blank" rel="ugc" href="https://civitai.com/models/1080969/noobai-cyberfix-v2perpendicular-cyberfix-v2-vpred">Cyberfix</a>! But pure <a target="_blank" rel="ugc" href="https://civitai.com/models/833294?modelVersionId=1190596">NoobAI-XL V-pred</a> is also good.For Illustrious mixes and NoobAI-XL Epsilon: use NoobAI-Xl Epsilon (especially mixes based on NoobAI-XL Epsilon!).<a target="_blank" rel="ugc" href="https://civitai.com/articles/8709/noobai-xl-10-epsilon-optimal-settings-and-loras-announcement">Guide</a> about NoobAI-XL Epsilon.PonyXL / NoobAI-XL and SD 1.5 tags:Main:kiria jef, 1girl, mature female, dark-skinned female, white hair, short hair, blue eyes, outfit: black coat, strapless bra, miniskirt, knee boots optional:body writing, highleg panties<h3 id="noobai-xl-quality-prompt:-3xyioy9ra">NoobAI-XL quality prompt:</h3>Put "masterpiece, best quality, good quality" in positive and put "low quality, worst quality" in negative.Use euler, cfg 4-5. Don't use higher CFG!If you have over-constrasted picture and cfg 4-5 didn't help you can try to put in negative "colorful".<a target="_blank" rel="ugc" href="https://civitai.com/user/Enigmata/articles">More in my articles</a><a target="_blank" rel="ugc" href="https://civitai.com/articles/8709">.</a><h3 id="ponydiffusion-v6-(xl)-settings:-8fn8ujp00">PonyDiffusion v6 (XL) settings:</h3>Style settings (very important):score_9, score_8_up, score_7_up, score_6_up, score_5_up,Negative prompt (recommended):dutch angle, censored, mosaic censoring, jpeg artifacts, muscularUpscaler / adetailer settings:Hires.fix: Upscaler foolhardy_remacri (download and put in "ESRGAN" folder in "models" if you are using automatic1111 or forge).Hires steps: 16-18Denoising strength: 0.3Adetailer: denoising strength 0.3. Detection model confident threshhold: 0.7-0.8.Best sampling method is euler / euler a, 25-40 sampling steps, You don't need any DPM++Don't forget to like LoRA model :3<a target="_blank" rel="ugc" href="https://tensor.art/u/604375505701151021">https://tensor.art/u/604375505701151021</a>

Files with SHA256: fab8c69baba2a15c9206ea663dbdbfa26ac0d454598c4b32e3fc022cded065d4