luisap-not-dalle2-27mb

[LuisaP❤️]NOT DALLE2 [27MB]

<Gallery />

Model description

<h1 id="sdxl-1.0-base-only-higly-recomended.-d57lx1zpt"><strong><span style="color:#fa5252">SDXL 1.0 BASE ONLY, HIGLY RECOMENDED.</span></strong></h1><p><strong>About: Trained on selected dataset of <s>dalle-2 </s>images, need the default model to work.</strong></p><p>Default model: <a target="_blank" rel="ugc" href="https://civitai.com/models/101055/sd-xl?modelVersionId=128078">https://civitai.com/models/101055/sd-xl?modelVersionId=128078</a></p><p><strong>For Foocus, styles can improve your image look, more description is better.</strong></p><p>❤️❤️❤️❤️❤️❤️❤️❤️❤️❤️❤️❤️❤️❤️❤️❤️❤️❤️❤️❤️❤️❤️❤️❤️❤️❤️❤️❤️<br /><strong>Do and tips: </strong>1 weight for generation / 1.2/1.5 weight for img2img</p><p><strong>Keyword: oil painting and fantasy can bring back some esque for different models.</strong></p>

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

pipeline = AutoPipelineForText2Image.from_pretrained('stabilityai/stable-diffusion-xl-base-1.0', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('multimodalart/luisap-not-dalle2-27mb', weight_name='DARRE2.safetensors')
image = pipeline('Your custom prompt').images[0]

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