DarkPhoenix 3D - v1.2
추천 프롬프트
masterpiece,high quality,best quality,Detailed
official art, official wallpaper, (detailed:1.05), (extremely detailed:1.06), sharp focus, (intricate:1.03), (extremely intricate:1.04), (epic scenery:1.09), vibrant colors, (beautiful scenery:1.08), (detailed scenery:1.08), (intricate scenery:1.07), (wonderful scenery:1.05), (beautiful face:1.1), [perfect eyes:0.8], [perfect skin:0.8], [detailed face:0.8], [detailed eyes:0.8], [detailed hair:0.9], [detailed lips:0.8]
추천 네거티브 프롬프트
EasyNegativeV2,low quality,normal quality,worst quality,(bad anatomy)
EasyNegativeV2, (low quality:1.32), (normal quality:1.31), (worst quality:1.33), (bad anatomy), (bad Hands), (mutated limbs:1.2), (mutated hands, mutated fingers:1.2), (deformed hands:1.2), (text:1.5), simple background
추천 매개변수
samplers
steps
cfg
clip skip
resolution
vae
other models
추천 고해상도 매개변수
upscaler
upscale
steps
denoising strength
팁
Don't use Embedding NegfeetV2 as it ruins image quality.
Other combinations of negative prompts also work, including Fastnegative and BadDream, but EasyNegativeV2 performs best without harming image quality.
Use more sampling steps only as a last resort for very complex images, as excessive steps tend to damage image quality.
Adetailer model yolov8n.pt recommended for face detailing with inpaint denoising strength 0.25 - 0.40 and steps 15 - 20.
버전 하이라이트
I made some changes and I think it improved the eyes and colors, and it seems to have more details.
This time I generated all the images without using Lora, my idea was to show the model's capabilities without interference from any Lora.
크리에이터 스폰서
Did you like the content? I would be grateful to receive a coffee
First model merger test I did, credits to the models below.
AbsoluteReality: https://civitai.com/models/81458?modelVersionId=132760
BeautyFool: https://civitai.com/models/101888?modelVersionId=134148
realspice: https://civitai.com/models/158734?modelVersionId=208629
For this model I recommend using some basic prompts like positive and negative.
Positive prompts: masterpiece, high quality, best quality, Detailed
Negative prompts: EasyNegativeV2, low quality, normal quality, worst quality, (bad anatomy)
Other combinations of negative prompts also work, as does using Fastnegative or BadDream (but I strongly recommend using EasynegativeV2, because of all my tests, this is the negative that works best without damaging the image too much in StableDiffusion)
Don't use Embedding NegfeetV2, I don't know why, but it ruins the image if you use this Embedding in this model
Recommended settings
Sampling steps: 15-30 (Only use more steps as a last resort for very complex images, as an excessive number of steps tends to ruin the image)
CFG Scale: 5-12
Hires. Fix
Upscaler: 4xNMKDSuperscale_4xNMKDSuperscale
Hires Steps: 15-20
Denoising Strenght: 0,20-0,40 (The more force, the cleaner the image, but the more the original quality is lost.)
Upscale By: 1,5 - 2,0
Adetailer:
Adetailer Model: face_yolov8n.pt
Inpaint denoising strength: 0,25 - 0,40
ADetailer steps: 15 - 20
Did you like the content? I would be grateful to receive a coffee
https://ko-fi.com/berserkfg
This model is open source for pornography, therefore pornographic images are at the image creators' own risk, and the model will not be held responsible for any image with heinous content.