You are viewing an old version of this page. View the current version.

Compare with Current View Page History

« Previous Version 2 Next »

Part 1 - Bookshop

Prompt: photorealistic girl in bookshop choosing the book in romantic stories shelf. smiling

Parameters: Steps: 50| Size: 1024x1024| Seed: 2544969645| CFG scale: 9| Model: Lumina-Image-2.0| App: SD.Next| Version: e657cf7| Operations: txt2img| Pipeline: Lumina2Pipeline

Execution: Time: 21m 50.30s | pipeline 1305.16 decode 5.10 te 3.53 offload 0.32 gc 0.31 | GPU 13060 MB 10% | RAM 3.18 GB 3%


CFG=0CFG=1CFG=2CFG=3CFG=4CFG=5CFG=6CFG=7CFG=8CFG=9
2

4

6

8

12

16

20

35

Part 2 - Face and hand



CFG=0CFG=1CFG=2CFG=3CFG=4CFG=5CFG=6CFG=7CFG=8CFG=9
2









4









6









8









12









20









35









50









100









Part 3 - Legs and ribbon



CFG=0CFG=1CFG=2CFG=3CFG=4CFG=5CFG=6CFG=7CFG=8CFG=9
2









4









6









8









12









20









35









50









100









System

app: sdnext.git updated: 2025-06-16 hash: 72eb0132 url: https://github.com/vladmandic/sdnext.git/tree/master
arch: x86_64 cpu: x86_64 system: Linux release: 6.11.0-26-generic
python: 3.12.3 2.7.1+xpu
device: Intel(R) Arc(TM) Graphics (1) ipex: 
ram: free:121.93 used:3.4 total:125.33
xformers:  diffusers: 0.34.0.dev0 transformers: 4.52.4
active: xpu
dtype: torch.bfloat16 vae: torch.bfloat16 unet: torch.bfloat16
base: Diffusers/Alpha-VLLM/Lumina-Image-2.0 [53504abd81] refiner: none vae: none te: none unet: none


  • No labels