Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

linoyts
/
Flux2-Klein-Delight-LoRA

Text-to-Image
Diffusers
TensorBoard
diffusers-training
lora
flux2
flux2-diffusers
template:sd-lora
Model card Files Files and versions
xet
Metrics Training metrics Community
3

Instructions to use linoyts/Flux2-Klein-Delight-LoRA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Diffusers

    How to use linoyts/Flux2-Klein-Delight-LoRA with Diffusers:

    pip install -U diffusers transformers accelerate
    import torch
    from diffusers import DiffusionPipeline
    
    # switch to "mps" for apple devices
    pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.2-klein-base-9B", dtype=torch.bfloat16, device_map="cuda")
    pipe.load_lora_weights("linoyts/Flux2-Klein-Delight-LoRA")
    
    prompt = "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."
    image = pipe(prompt).images[0]
  • Notebooks
  • Google Colab
  • Kaggle
  • Local Apps Settings
  • Draw Things
  • DiffusionBee
Flux2-Klein-Delight-LoRA
318 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 4 commits
linoyts's picture
linoyts HF Staff
End of training
371ae49 verified 4 months ago
  • checkpoint-1000
    End of training 4 months ago
  • checkpoint-1500
    End of training 4 months ago
  • checkpoint-500
    End of training 4 months ago
  • logs
    End of training 4 months ago
  • .gitattributes
    1.71 kB
    End of training 4 months ago
  • README.md
    5.93 kB
    End of training 4 months ago
  • image_0.png
    1.43 MB
    xet
    End of training 4 months ago
  • image_1.png
    1.36 MB
    xet
    End of training 4 months ago
  • image_2.png
    1.3 MB
    xet
    End of training 4 months ago
  • image_3.png
    1.46 MB
    xet
    End of training 4 months ago
  • pytorch_lora_weights.safetensors
    33.6 MB
    xet
    End of training 4 months ago
  • pytorch_lora_weights_v2.safetensors
    127 MB
    xet
    Upload pytorch_lora_weights_v2.safetensors 4 months ago