Info

Test 0 - Different seed variations

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

...

https://civitai.com/models/1157409/tempest-by-vlad

Flexible SDXL model with custom encoder and finetuned for larger landscape resolutions with high details and high contrast.

Recommended to use medium-low step count and guidance,
For example: steps=15-20 guidance=3-4
Model can generate consistent images up to 1920x1080.

Model is not censored, but its tuned for general content and not overly aggressive.

Examples: Tempest-by-Vlad - v0.1 Showcase | Civitai

Test 0 - Different seed variations

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

Parameters: Steps: 18| Size: 1024x1024| Seed: 2736029172| CFG scale: 3.5| App: SD.Next| Version: 0c1d347| Pipeline: StableDiffusionXLPipeline| Operations: txt2img| Model: tempestByVlad_baseV01| Model hash: 8bfad17222

Time: 1m 40.57s | total 114.58 pipeline 94.35 callback 7.47 preview 6.24 decode 6.18 gc 0.30 | GPU 9438 MB 8% | RAM 7.9 GB 6%

Test 0.5 - FullHD

Prompt: Create a close-up photograph of a woman's face and hand, with her hand raised to her chin. She is wearing a white blazer and has a gold ring on her finger. Her nails are neatly manicured and her hair is pulled back into a low bun. She is smiling and has a radiant expression on her face. The background is a plain light gray color. The overall mood of the photo is elegant and sophisticated. The photo should have a soft, natural light and a slight warmth to it. The woman's hair is dark brown and pulled back into a low bun, with a few loose strands framing her face.

Parameters: Steps: 18| Size: 1920x1080| Seed: 1620085323| CFG scale: 3.5| App: SD.Next| Version: 0c1d347| Pipeline: StableDiffusionXLPipeline| Operations: txt2img| Model: tempestByVlad_baseV01| Model hash: 8bfad17222

Time: 3m 44.02s | total 246.59 pipeline 214.83 callback 13.51 decode 9.14 preview 8.75 gc 0.30 | GPU 13304 MB 11% | RAM 7.97 GB 6%

Test 1 - Bookshop

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

Test 2 - Face and hand

Prompt: Create a close-up photograph of a woman's face and hand, with her hand raised to her chin. She is wearing a white blazer and has a gold ring on her finger. Her nails are neatly manicured and her hair is pulled back into a low bun. She is smiling and has a radiant expression on her face. The background is a plain light gray color. The overall mood of the photo is elegant and sophisticated. The photo should have a soft, natural light and a slight warmth to it. The woman's hair is dark brown and pulled back into a low bun, with a few loose strands framing her face.

...

Test 1 - Bookshop

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

...

CFG1

...

CFG2

...

CFG3

...

CFG4

...

CFG5

...

...

CFG8

Test 2 - Face and hand

...

CFG1

...

CFG2

...

CFG3

...

CFG3.5

...

CFG4

...

CFG5

...

CFG6

...

CFG8

Test 3 - Legs

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.

...

.

...

CFG1

...

CFG2

...

CFG3

...

CFG3.5

...

CFG4

...

CFG5

...

CFG6

...

CFG8

Test 5 Different samplers

Prompt: photo of a cute female teal robot, walking on water surface with rocks and mountains visible in background, during sunset, rich details

...

Sampler: Default Sampler: DPM2 FlowMatch Sampler: DPM2a FlowMatch Sampler: DPM2++ 2M FlowMatch Sampler: DPM2++ SDE FlowMatch Sampler: DPM2++ 2M SDE FlowMatch Sampler: DPM2++ 3M SDE FlowMatch Sampler: PeRFlow Sampler: Euler EDM	Sampler: DPM++ Sampler: DPM++ 2M Sampler: DPM++ 3M	Sampler: DPM++ SDE Sampler: DPM++ 2M SDE	Sampler: DDPM
Sampler: Euler	Sampler: Euler a
Sampler: DPM SDE	Sampler: DPM++ 1S	Sampler: DDIM
Sampler: UniPC	Sampler: Heun	Sampler: DEIS
Sampler: PNDM	Sampler: DC Solver	Sampler: SA Solver	Sampler: LMSD
Sampler: LCM	Sampler: TCD	Sampler: TDD
Sampler: KDPM2	Sampler: KDPM2 a

Test 5 CFG 6 vs CFG 3.5

Test 6 - base vs hyper

System info

Mon Sep 29 13:03:03 2025
app: sdnext.git updated: 2025-09-27 hash: 57fdc0ad url: https://github.com/vladmandic/sdnext.git/tree/dev
arch: x86_64 cpu: x86_64 system: Linux release: 6.14.0-29-generic python: 3.12.3

Torch: 2.7.1+xpu device: Intel(R) Arc(TM) Graphics (1) ipex: 2.7.10+xpu

ram: free:121.5 used:3.83 total:125.33
gpu: free:106.91 used:10.46 total:117.37
gpu-active: current:6.71 peak:8.0
gpu-allocated: current:6.71 peak:8.0
gpu-reserved: current:10.46 peak:10.46
gpu-inactive: current:0.5 peak:0.83
events: retries:0 oom:0
utilization: 0

xformers: diffusers: 0.36.0.dev0 transformers: 4.56.2
active: xpu dtype: torch.bfloat16 vae: torch.bfloat16 unet: torch.bfloat16
base: tempestByVlad_baseV01 [8bfad17222] refiner: none vae: none te: none unet: none
Backend: ipex Cross-attention: Scaled-Dot-Product

Config

{
  "theme_type": "Standard",
  "diffusers_version": "1448b035859dd57bbb565239dcdd79a025a85422",
  "diffusers_offload_mode": "none",
  "ui_request_timeout": 300000,
  "huggingface_token": "hf_xxx",
  "samples_filename_pattern": "[date]-[seq]-[model_name]-[height]x[width]-Seed[seed]-CFG[cfg]-AG[pag]-STEP[steps]",
  "sd_model_checkpoint": "tempestByVlad_baseV01 [8bfad17222]",
  "sd_checkpoint_hash": "8bfad1722243955b3f94103c69079c280d348b14729251e86824972c1063b616",
  "hf_transfer_mode": "xet",
  "extra_networks_sort": "sort: no cards",
  "schedulers_solver_order": 1,
  "cuda_compile_backend": "none",
  "diffusers_to_gpu": true,
  "device_map": "gpu"
}

Model info

{
modelspec.usage_hint: "Flexible SDXL model with custom encoder and finetuned for larger landscape resolutions with high details and high contrast. Recommended to use medium-low step count and guidance.",
modelspec.implementation: "diffusers",
modelspec.license: "CC-BY-SA-4.0",
modelspec.date: "2025-01-17T16:03",
modelspec.title: "tempest-by-vlad",
modelspec.dtype: "float16",
recipe: {
         base: "TempestV0.1-Artistic.safetensors",
         unet: "default",
         vae: "sdxl-vae-fp16-fix.safetensors",
         te1: "ViT-L-14-TEXT-detail-improved-hiT-GmP-TE-only-HF.safetensors",
         te2: "default",
         scheduler: "UniPCMultistepScheduler",
         lora: [
                 0: "offset-example-1.0.safetensors:0.25",
                 1: "hyper-sdxl-8step.safetensors:0.25",
                 2: "add-detail-xl.safetensors:2.0"
               ]
        },
modelspec.prediction_type: "epsilon",
modelspec.thumbnail: "data",
modelspec.sai_model_spec: "1.0.0",
modelspec.version: "0.1",
modelspec.hash_sha256: "ce49361cbf77bc591552ca3efa3b29ea10539aa4ba7741cf966f6b9ea7be7c1f",
modelspec.author: "vladmandic",
modelspec.description: "Tempest by VladMandic",
modelspec.architecture: "stable-diffusion-xl-v1-base"
}

...