--- license: other license_name: bespoke-lora-trained-license license_link: https://multimodal.art/civitai-licenses?allowNoCredit=True&allowCommercialUse=RentCivit&allowDerivatives=False&allowDifferentLicense=True tags: - text-to-image - stable-diffusion - lora - diffusers - template:sd-lora - migrated - character - photorealistic - selene - underworld - woman - realistic - kate beckinsale - flux1.d base_model: black-forest-labs/FLUX.1-dev instance_prompt: s3l3n3 widget: - text: ' ' output: url: >- 26297452.jpeg - text: ' ' output: url: >- 26297463.jpeg - text: ' ' output: url: >- 26297461.jpeg - text: ' ' output: url: >- 26297447.jpeg - text: ' ' output: url: >- 26297450.jpeg - text: ' ' output: url: >- 26297451.jpeg - text: ' ' output: url: >- 26297462.jpeg - text: ' ' output: url: >- 26297449.jpeg --- # Selene - Underworld (Kate Beckinsale) - Flux Lora TEST <Gallery /> ([CivitAI](https://civitai.com/models/)) ## Model description <h3 id="selene-underworld-(kate-beckinsale)-9c6eb7ami">Selene - Underworld (Kate Beckinsale)</h3><p>Note: <span style="color:rgb(130, 201, 30)">Hires fix and/or Face Detailer highly recommended.</span></p><p>Trigger: s3l3n3<br /><br />This is a quick test to see how quick I can train on my 4060Ti 16Gb.<br />Quality is not super great, but generally better than my SDXL tests.<br /><br />Trained for 60 epochs, 1 repeat for a total of 600 steps, 512x512, Kohya Gui SD3-Flux branch using flux preset and adjusting to network/alpha of 4. About 32mins for 10 low quality pictures of different resolutions and aspect ratios.<br /></p><p>Better likeness can be achieved by describing her look in the film, some words to help: Black hair, black leather suit.</p><p>Really amazed by Flux's capabilities.</p> ## Trigger words You should use `s3l3n3` to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](/Keltezaa/selene-underworld-kate-beckinsale-flux-lora-test/tree/main) them in the Files & versions tab. ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers) ```py from diffusers import AutoPipelineForText2Image import torch device = "cuda" if torch.cuda.is_available() else "cpu" pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.bfloat16).to(device) pipeline.load_lora_weights('Keltezaa/selene-underworld-kate-beckinsale-flux-lora-test', weight_name='Selene Underworld (s3l3n3) - Flux test-000060.safetensors') image = pipeline('`s3l3n3`').images[0] ``` For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)