Version 2V2 was trained on more than 30x as many images as V1, so its understanding of Hu Tao's appearance is much better. Unfortunately it seems that training Flux models on Danbooru tags leads to some weird prompting issues, so I will look into using more natural tagging for V3.
Input
Per image generation will cost 0.0047$
For premium plan image generation will cost 0.00$ i.e Free.
Output
Idle
Unknown content type
Related Models
Discover similar models you might be interested in
Free for Premium Users
ModelsLab
Flux.2 Dev Text to Image
Jim Daly Art Style (Unofficial) - Flux - version 1.0
Sausage Dishes - White Sausage-Dev v1.0
![Gamebook illustration [Flux + IL] - Flux](https://images.modelslab.com/?Image=https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/a3d7d0f8-2b1d-4248-ba54-c5406ffca31f/width=832/100131022.jpeg)
Gamebook illustration [Flux + IL] - Flux
Dreamy and Colorful - v1.0
Athena - Athena-V1
fantasy-tree - v1.0
Sanai Mahbub Viral Style - v1.0
Defaced - V1
Milo Manara - V1
Underflowered - V1
Ringbrothers Octavia - 2025 - v1.0 FLUX