Edit model card

Voxel

The Voxel Art model merged with SQUEE! to create a 768x768 model that responds well even if you don't add VoxelArt to the prompt and doesn't rely as much on negative prompts. It has the MoistMixV2VAE baked in.

Coparison:

Free Ai Image Generator Voxel Comparison

(Click for larger)

Samples and prompts:

Free Ai text to image voxel samples

(Click for larger)

Top left: VoxelArt. anime little girl with blonde messy hair, school uniform skirt, nose blush, beautiful eyes, sitting on her desk, front view, solo, full body

Top right: kreatif, low poly, isometric art, 3d art, high detail, artstation, concept art, behance, ray tracing, smooth, sharp focus, ethereal lighting

Bottom left: voxel venec fox pet closeup in convenience store. VoxelArt pixel chibi disney pixar, Voxel style, the perfect hero, Masterpiece photography, in hero pose, carrying, villains lair background, hyperrealistic, award winning photography, intricate textures, soft lighting,

Bottom right: VoxelArt,1girl,long gray hair,girl sitting inside a long crystal bottle,bottle with stopper,water in bottle,grass, background,extremely detailed,natural lighting,film grain,

Original pages:

https://huggingface.co/Fictiverse/Stable_Diffusion_VoxelArt_Model

https://huggingface.co/Yntec/SQUEE

Recipes:

  • SuperMerger Add Difference Train Difference Alpha 1

Model A: VoxelArt

Model B: SQUEE

Model C: Stable Diffusion 1.5

Output: SQUEEXEL

  • SuperMerger Weight sum MBW 0,0,0,0,0,0,0,0,0,0,1,1,1,0,0,0,0,0,0,0,0,0,0,0,0,0

Model A: SQUEEXEL

Model B: VoxelArt

Output: Voxel

Bake in MoistMixV2VAE

Output: VoxelVAE

Downloads last month
999
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Spaces using Yntec/Voxel 27