Download
1 variant available
The FLUX.1 [dev] Model is licensed by Black Forest Labs. Inc. under the FLUX.1 [dev] Non-Commercial License. Copyright Black Forest Labs. Inc.
IN NO EVENT SHALL BLACK FOREST LABS, INC. BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.
A high-quality LoRA model trained on the complete poster works of the 20th-century Art Nouveau master, Alphonse Mucha. Trained on the Flux-2-Klein-9B-base and fully compatible with Flux-2-Klein-9B-turbo.
All training images were meticulously restored manually (including color correction, damage repair, and text removal) to ensure the highest quality brushstrokes and color reproduction while maintaining excellent generalization.
It excels at both Text-to-Image generation and Image-to-Image style transfer tasks, leveraging the strong editing capabilities of the Flux-2-Klein architecture.
### ⚙️ Recommended Settings
Base Model: Flux-2-Klein-9B (Base or Turbo)
1. Text-to-Image:
* Trigger Words: Paintings in the Art Nouveau style,mucha_style.
* LoRA Weight: 0.95 - 1.5 (Recommended: 1.0. Higher weight brings a stronger style but increases the risk of structure breaking).
2. Image-to-Image (Style Transfer/Edit):
* Trigger Words: Convert the artistic style of this picture to the Mucha_style found in New Art paintings
* LoRA Weight: 0.85 - 1.0 (Recommended: 1.0 or below).
For beginners using ComfyUI, you can refer to my workflow on RunningHub:https://www.runninghub.cn/post/2017972394081652738/?inviteCode=rh-v1251