Your current browser has compatibility issues. Please switch toChrome for uninterrupted access.

AWPortrait XL

6.6k
67
283
49
Penggunaan komersialRealisticStyle & FilterGirlStyle Boost
Dikemaskini Baru-baru Ini: 24/08/13Diterbitkan Pertama: 24/06/03
Realistic,Style & Filter,Girl,Checkpoint,SDXLImage info
Realistic,Style & Filter,Girl,Checkpoint,SDXLImage info
Realistic,Style & Filter,Girl,Checkpoint,SDXLImage info
Realistic,Style & Filter,Girl,Checkpoint,SDXLImage info
Realistic,Style & Filter,Girl,Checkpoint,SDXLImage info
Realistic,Style & Filter,Girl,Checkpoint,SDXLImage info
Realistic,Style & Filter,Girl,Checkpoint,SDXLImage info
Realistic,Style & Filter,Girl,Checkpoint,SDXLImage info
Realistic,Style & Filter,Girl,Checkpoint,SDXLImage info
Realistic,Style & Filter,Girl,Checkpoint,SDXLImage info
Realistic,Style & Filter,Girl,Checkpoint,SDXLImage info
Realistic,Style & Filter,Girl,Checkpoint,SDXLImage info
Realistic,Style & Filter,Girl,Checkpoint,SDXLImage info
Realistic,Style & Filter,Girl,Checkpoint,SDXLImage info
Realistic,Style & Filter,Girl,Checkpoint,SDXLImage info
Realistic,Style & Filter,Girl,Checkpoint,SDXLImage info
Realistic,Style & Filter,Girl,Checkpoint,SDXLImage info
Realistic,Style & Filter,Girl,Checkpoint,SDXLImage info
Realistic,Style & Filter,Girl,Checkpoint,SDXLImage info
Realistic,Style & Filter,Girl,Checkpoint,SDXLImage info

AWPortraitXL 1.1 has added nearly 2000 high-quality fashion photography images for fine-tuning and training based on 1.0, resulting in significant improvements in composition aesthetics and image details. Compared to version 1.0, 1.1 has a more precise response to different ethnicities, showing more delicate skin textures across different ethnicities, powerful semantic understanding capabilities, and the ability to produce realistic styles in various scenarios with high quality and stability.Added recognition and response to Eastern elements such as cheongsam and hanfu. Compared to other SDXL realistic models, it excels in the aesthetic appeal of East Asian ethnicities. For more model effects, please refer to the example image prompts.


To achieve the best image quality, follow the parameter settings below:

Sampling Recommendations: DPM++ 2M Karras, Restart, Euler a, Step 30

Recommended Resolution: 768*1152

Upscaling Algorithm: Lanczos, Redraw Rate 0.2-0.3

Negative Keywords: (worst quality), (low quality), (normal quality), lowres, bad anatomy, ((bad hands, broken hands)), (many fingers), ((grayscale)) watermark, moles,

Adetailer:

For Close-up situations, you can choose not to enable Adetailer or use a redraw rate of 0.25-0.3.

For UpperBody situations, you can choose not to enable it or use a redraw rate of 0.3-0.35.

For Fullbody situations, please enable it with a redraw rate of 0.35-0.4.


Kembangkan Semua

Perbincangan2

Paling Popular
|
Terkini
Hantar
avatar
Ken
Hi! This is a very nice checkpoint model. Any tips on getting more sharpness and details for hi-res fix or even img2img upscale?
2025/01/16 01:43:01
0Balas
avatar
RLK ARMY FF
A charismatic speaker is captured mid-speech. He has long, slightly wavy blonde hair tied back in a ponytail. His expressive face, adorned with a salt-and-pepper beard and mustache, is animated as he gestures with his left hand, displaying a large ring on his pinky finger. He is holding a black microphone in his right hand, speaking passionately. The man is wearing a dark, textured shirt with unique, slightly shimmering patterns, and a green lanyard with multiple badges and logos hanging around his neck. The lanyard features the "Autodesk" and "V-Ray" logos prominently. Behind him, there is a blurred background with a white banner containing logos and text, indicating a professional or conference setting. The overall scene is vibrant and dynamic, capturing the energy of a live presentation.
2024/09/28 04:17:33
0Balas
Tidak Ada Komen Lagi
DynamicWang
Artis
1.5k
685
999k+
14.9k
Kesukaan
Muat Turun
(6.62GB)
Diverifikasi:2024/08/01
1.1
KhasButiran
Jenis
Checkpoint
Kiraan Penerapan Dalam Talian
2.7k
Muat Turun
66
Algoritma Asas
SDXL
Parameter Disyorkan
Sampler method
DPM++ 2M Karras
CFG
3
VAE
Tiada
Algoritma Penskalaan Resolusi Tinggi
Lanczos
Lesen Kreatif
Boleh dijalankan secara dalam talian
Tidak boleh digabungkan
Imej yang dijana boleh digunakan untuk tujuan komersial (terhad kepada ahli sahaja)Tingkatkan sekarang >>
Model tidak boleh dijual atau digabung sebagai model digabung
*Skop lesen ditetapkan oleh pencipta, pengguna mesti menggunakan mengikut keperluan dan piawaian

Galeri298

Paling Popular
|
Terkini
avatar
DynamicWang
Image info
avatar
DynamicWang
avatar
DynamicWang
Image info
avatar
YeYeYeYeYe
avatar
xiaomeige
Image info
avatar
YeYeYeYeYe
avatar
Nguyễn Tùng Anh
Image info
avatar
DynamicWang
avatar
DynamicWang
Image info
avatar
DynamicWang
Image info
avatar
DynamicWang
Image info
avatar
DynamicWang
Image info
avatar
DynamicWang
Image info
avatar
DynamicWang
Image info
avatar
Muertu
Image info
avatar
DynamicWang