Sign In

Tempest-by-Vlad

33
363
11
Updated: Jan 31, 2025
base model
Verified:
SafeTensor
Type
Checkpoint Merge
Stats
312
0
Reviews
Published
Jan 19, 2025
Base Model
SDXL 1.0
Hash
AutoV2
8BFAD17222
default creator card background decoration
vmandic's Avatar
vmandic

Base version

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.

All example images are first roll-of-dice with text-to-image and no postprocessing.
Full information on components is embedded in model metadata.

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

Hyper version

Goal was to get as-normal-as-possible model that works with low steps and guidance-free

I've experimented with few time-distillation methods: LCM, Turbo, Lightning, Flash, PCM, TCD, TDD, SPO, DMD

Finally settled down with custom Hyper method, it seems pretty stable with any number of different parameters

For example: steps=3-4 guidance=1 (disabled)

Sampler can be anything

Note that standard samplers such as Euler a, UniPC or DPM++ 2M will give vastly different results than fast-optimized samplers such as TCD and TDD

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