This model is trained on the concept of tilt shift, which is an old camera trick that makes the subject of photos look very tiny by manipulating blur on the upper and lower half of the image to make it look like depth of field blur. Anyway, it makes everything look really tiny. The trigger word is "tilt-shift".

Trigger words

You should use tilt-shift to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.

Use it with the 🧨 diffusers library

from diffusers import AutoPipelineForText2Image
import torch

pipeline = AutoPipelineForText2Image.from_pretrained('stabilityai/stable-diffusion-xl-base-1.0', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('e-n-v-y/envy-tiny-worlds-xl-01', weight_name='EnvyTinyWorldsXL01.safetensors')
image = pipeline('tilt-shift, digital painting, scifiParadoxical fantasy metropolis beyond the end of the universe').images[0]

For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers