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

Compare with Current View Page History

« Previous Version 4 Next »

Part 1 - Bookshop

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

Parameters: Steps: 20| Size: 1024x1024| Seed: 3286438823| CFG scale: 7| Model: Cosmos-Predict2-14B-Text2Image| App: SD.Next| Version: bcea748| Operations: txt2img| Pipeline: Cosmos2TextToImagePipeline

Execution: Time: 23m 33.78s | total 1433.89 pipeline 1399.03 offload 14.71 move 7.36 decode 7.36 te 5.40 | GPU 41668 MB 32% | RAM 29.59 GB 24%


STEPS: 2STEPS: 4STEPS: 6STEPS: 8STEPS: 12STEPS: 16STEPS: 20STEPS: 32
CFG0

CFG1
=
CFG0

CGF2

CFG3

CFG4

CFG5

CFG6

CFG7

Part 2 - Face and hand



CFG=1CFG=2CFG=6CFG=8
8



16



20



32



Part 3 - Legs and ribbon



CFG=1CFG=2CFG=6CFG=8
8



16



20



32



System Info

app: sdnext.git updated: 2025-06-28 hash: bcea748d url: https://github.com/vladmandic/sdnext.git/tree/dev
arch: x86_64 cpu: x86_64 system: Linux release: 6.11.0-28-generic
python: 3.12.3 Torch 2.7.1+xpu
device: Intel(R) Arc(TM) Graphics (1) ipex: 
ram: free:96.45 used:28.88 total:125.33
xformers: diffusers: 0.35.0.dev0 transformers: 4.53.0
active: xpu dtype: torch.bfloat16 vae: torch.bfloat16 unet: torch.bfloat16
base: Diffusers/nvidia/Cosmos-Predict2-14B-Text2Image [015332720f] refiner: none vae: none te: noneunet: none


  • No labels