Trained upon Microsoft's FluentUI's 3D Emoji asset collection. Trained with captions where each caption was the original file name with 'emoji' appended to it. So use emoji in your prompts to trigger the style. I'm aware that Flux is already very good with generating. emoji but I wanted to see how it will adapt to MS's FluentUI's style:

For reasons I could not figure (or solve), it will generate a very blurry result on occasion. I was not able to find any solution to this other than simply trying again with a different seed. Sorry for that

Trigger words

You should use emoji 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

device = "cuda" if torch.cuda.is_available() else "cpu"

pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.bfloat16).to(device)
pipeline.load_lora_weights('Norod78/ms-fluentui-style-emoji-flux', weight_name='ms-fluentui_emoji_flux_lora_000001750.safetensors')
image = pipeline('Rick Sanchez emoji ').images[0]

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