Trained upon <a rel="ugc" href="https://github.com/microsoft/fluentui-emoji/tree/main">Microsoft's FluentUI</a>'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:<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/e053dc92-42ee-4cdc-9740-94c5a8afd0ff/width=525/e053dc92-42ee-4cdc-9740-94c5a8afd0ff.jpeg" />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

ms fluentui style Emoji [FLUX]

Rank 16 Flux Dev LoRA, trained with AI-Toolkit

Files with SHA256: 4a66924f8432103cc0d0fa121b09b734e5de229a3bc1d7a5bbfd67f342822058