...

Info

Model: https://huggingface.co/Kwai-Kolors/Kolors

https://github.com/Kwai-Kolors/Kolors

https://kolors.kuaishou.com/

Hardware used

HW1: Intel core i7 1355U Intel Xe Graphics iGPU, 96GB DDR5 5600 CL46 RAM (OpenVino CPU)

HW2: Intel core ultra 185H Intel Arc  iGPU, 128GB DDR5 5600 CL46 RAM (IPEX)

Default guidance

The pipeline uses the Euler Discrete Scheduler by default. We recommend using this scheduler with guidance scale=5.0 and num_inference_steps=50.
The pipeline also supports the EDMDPM Solver Multistep Scheduler. guidance scale=5.0 and num_inference_steps=25 is a good default for this scheduler.

...

Time: 1m 50.86s | total 121.98 pipeline 104.95 callback 8.30 decode 5.87 preview 1.38 te 1.12 gc 0.30 | GPU 19720 MB 15% | RAM 35.99 GB 29%

Part 1 - Bookshop

OpenVINO CPU

...

Is there way to draw legs correct?

1. trying several random seeds - may get a better result
2. trying different resolutions
3. trying different sampler
4. trying negative prompts

1. trying several random seeds - may get a better result
2. trying different resolutions
3. trying different sampler
4. trying negative prompts

Prompt: Generate a photo of a woman's legs, with her feet crossed and wearing white high-heeled shoes with ribbons tied around her ankles. The shoes should have a pointed toe and a stiletto heel. The woman's legs should be smooth and tanned, with a slight sheen to them. The background should be a Prompt: Generate a photo of a woman's legs, with her feet crossed and wearing white high-heeled shoes with ribbons tied around her ankles. The shoes should have a pointed toe and a stiletto heel. The woman's legs should be smooth and tanned, with a slight sheen to them. The background should be a light gray color. The photo should be taken from a low angle, looking up at the woman's legs. The ribbons should be tied in a bow shape around the ankles. The shoes should have a red sole. The woman's legs should be slightly bent at the knee.

...

Part 4 - Other prompts (IPEX)

Mostly borrowed from 

https://civitai.com/collections/10716337

...

from Test 42 - All models cover image

Image AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage Added

Art prompts

Image AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage Added

System Info

OpenVINO

app: sdnext updated: 2025-07-04 hash: 1a3b6e3b url: https://github.com/vladmandic/sdnext/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) Iris(R) Xe Graphics (iGPU) openvino: 2025.2.0
ram: free:31.06 used:62.91 total:93.97 gpu: total:93.97: sdnext updated: 2025-07-04 hash: 1a3b6e3b url: https://github.com/vladmandic/sdnext/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) Iris(R) Xe Graphics (iGPU) openvino: 2025.2.0
ram: free:31.06 used:62.91 total:93.97 gpu: total:93.97
xformers: diffusers: 0.35.0.dev0 transformers: 4.53.0
active: cpu dtype: torch.float32 vae: torch.float32 unet: torch.float32
base: Diffusers/Kwai-Kolors/Kolors-diffusers [7e091c7519] refiner: none vae: none te: none unet: none

IPEX

app: sdnext.git updated: 2025-10-02 hash: ef6563376 url: https://github.com/liutyi/sdnext.git/tree/ipex
arch: x86_64 cpu: x86_64 system: Linux release: 6.14.0-32-generic python: 3.12.3
Torch 2.7.1+xpu
device: Intel(R) Arc(TM) Graphics (1) ipex: 2.7.10+xpu
ram: free:116.15 used:9.18 total:125.33 gpu: free:106.42 used:18.91 total:125.33 gpu-active: current:16.89 peak:18.15 gpu-allocated: current:16.89 peak:18.15 gpu-reserved: current:18.91 peak:19.26 gpu-inactive: current:0.75 peak:0.79
events: retries:0 oom:0 utilization: 0 
xformers: diffusers: 0.3536.0.dev0 transformers: 4.5356.02
active: cpuxpu dtype: torch.float32bfloat16 vae: torch.float32bfloat16 unet: torch.float32bfloat16
base: Diffusers/Kwai-Kolors/Kolors-diffusers [7e091c7519] refiner: none vae: none te: none unet: none

...