alizee-lora-flux-sdxl-pony-sd15

Alizee LoRA (Flux/SDXL/Pony/SD15)

<Gallery />

Model description

<h2 id="alizee-lora-(fluxponysdxlsd-1.5)-nbrxpa6cy"><strong><span style="color:rgb(34, 139, 230)">Alizee LoRA (Flux/Pony/SDXL/SD-1.5)</span></strong></h2><p>This is a collection of Flux, Pony, SDXL, &amp; SD-1.5 version LoRA models of <strong>Alizee</strong> (Alizee Lyonnet), an award-winning French singer and dancer, recognized as one of the best selling French artists in the 21st century.</p><p>Use trigger work: <strong><span style="color:rgb(253, 126, 20)">41izee</span></strong></p><p>These LoRA models were trained on 40 publicly accessible images using Kohya_ss (<a target="_blank" rel="ugc" href="https://github.com/kohya-ss/sd-scripts">https://github.com/kohya-ss/sd-scripts</a>) webui (<a target="_blank" rel="ugc" href="https://github.com/bmaltais/kohya_ss">https://github.com/bmaltais/kohya_ss</a>). Sample images were rendered using A1111 (<a target="_blank" rel="ugc" href="https://github.com/AUTOMATIC1111/stable-diffusion-webui">https://github.com/AUTOMATIC1111/stable-diffusion-webui</a>) and Forge (<a target="_blank" rel="ugc" href="https://github.com/lllyasviel/stable-diffusion-webui-forge">https://github.com/lllyasviel/stable-diffusion-webui-forge</a>).</p><p>Models were trained on the following checkpoints:</p><p>Flux: Flux.1-dev</p><p>Pony: ponyDiffusionV6XL</p><p>SDXL: sdXL_v10VAEFix</p><p>SD1.5: v1-5-pruned</p><p>No additional LoRAs, embeddings, inpainting, ADetailer, or other enhancements were used in the generation of sample images in order to demonstrate the specific capabilities of these models. Your personal tuning and enhancement will produce further exceptional results.</p><p>This collection of Flux, SDXL, Pony, and SD-1.5 models are published exclusively to <strong>Civit<span style="color:rgb(76, 110, 245)">AI</span></strong> for your use, enjoyment, and 'research'.</p><p>If you are pleased with the models provided, we would be grateful for your support with a Like, Follow, or Review. We greatly appreciate your comments, feedback, and images which help us continue to improve our model research, testing, workflow, and image generation.</p><p>We are also extremely grateful for tips if you appreciate our work, (<a target="_blank" rel="ugc" href="https://buymeacoffee.com/Signalytix">https://buymeacoffee.com/Signalytix</a>), as it helps significantly to offset our costs and effort, allowing us to devote more time to research, create, contribute, and share our work with the community. Suggestions posted to our <a target="_blank" rel="ugc" href="https://buymeacoffee.com/Signalytix">tips page</a> and <strong>Civit<span style="color:rgb(76, 110, 245)">AI </span></strong>reviews garner our utmost attention for new and improved models. We currently focus on development of LoRAs and embeddings for Flux, Pony, SDXL, and V1.5. Your generous <strong><span style="color:rgb(250, 176, 5)">Buzz</span></strong> and <a rel="ugc" href="https://buymeacoffee.com/Signalytix">Tips</a> would help us expand our support of Flux in addition to other models.</p><p>These model were trained with images but depending on the checkpoint selected may trend toward risqué without careful prompting. You should ALWAYS include '<strong><span style="color:rgb(250, 82, 82)">NSFW</span></strong>' as a negative prompt to be respectful and safe. Use of this model should always abide by <strong>Civit<span style="color:rgb(76, 110, 245)">AI</span></strong>'s Content Rules. Use for generating illegal, sexual, violent, or other non-consensual content and themes is expressly discouraged.</p><p>------------------------------------------------------</p><p><em><span style="color:rgb(64, 192, 87)">ARTIFICIAL HUMANS ASSOCIATION (AHA) CERTIFICATION:</span></em></p><p><em><span style="color:rgb(64, 192, 87)">No WAIFUS were harmed, exploited, or compromised in the training of these models or creation of images.</span></em></p>

Trigger words

You should use 41izee to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.

Use it with the 🧨 diffusers library

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/alizee-lora-flux-sdxl-pony-sd15', weight_name='41izee_F1D_SGX.safetensors')
image = pipeline(',a (close up) photograph of(beautiful 24 year old) (41izee:1.2) woman with dark hair,as a librarian,wearing a red plaid dress and glasses,standing in a (library at Oxford University:1.3),holding an leather bound book,with long rows of bookshelves in the background,multi-level with (high arched ceiling:1.2),(smile),dark lips,makeup and mascara, face focus,(bokeh),facing viewer,rich details,clear shadows and highlights,realistic,highly detailed,sfw,(no visible cleavage),').images[0]

For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers