by linoyts
Open source · 5k downloads · 26 likes
The Flux2 Klein Delight LoRA model is a fine-tuned version of Flux.2-klein-base-9B, specifically designed to generate high-quality images from text descriptions. It employs DreamBooth to refine the base model’s capabilities, delivering more precise and stylized outputs. This model excels at producing detailed and coherent images, making it ideal for creative applications such as digital art or visual design. Its neutral trigger ("None") allows for intuitive use without requiring specific keywords. It is particularly well-suited for users looking to leverage the power of Flux.2 in custom projects with minimal technical constraints.
These are linoyts/Flux2-Klein-Delight-LoRA DreamBooth LoRA weights for black-forest-labs/FLUX.2-klein-base-9B.
The weights were trained using DreamBooth with the Flux2 diffusers trainer.
FP8 training? True
You should use None to trigger the image generation.
Download the *.safetensors LoRA in the Files & versions tab.
from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained("black-forest-labs/FLUX.2", torch_dtype=torch.bfloat16).to('cuda')
pipeline.load_lora_weights('linoyts/Flux2-Klein-Delight-LoRA', weight_name='pytorch_lora_weights.safetensors')
image = pipeline('Relight the image to remove all existing lighting conditions and replace them with neutral, uniform illumination. Apply soft, evenly distributed lighting with no directional shadows, no harsh highlights, and no dramatic contrast. Maintain the original identity of all subjects exactly—preserve facial structure, skin tone, proportions, expressions, hair, clothing, and textures. Do not alter pose, camera angle, background geometry, or image composition. Lighting should appear balanced, and studio-neutral, similar to diffuse overcast or a soft lightbox setup. Ensure consistent exposure across the entire image with realistic depth and subtle shading only where necessary for form.').images[0]
For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers
Please adhere to the licensing terms as described here.
# TODO: add an example code snippet for running this diffusion pipeline
[TODO: provide examples of latent issues and potential remediations]
[TODO: describe the data used to train the model]