Purz/soft-sculpture

Soft Sculpture

<Gallery />

Model description

<p>Soft Sculpture - LoRA (Flux.1 D)</p><p></p><p>Trained on photography of soft-lit sculptures, works well with colour definitions.</p><p></p><p>"50ft5cu7pt, a cyan and orange sculpture of a man dancing, sitting atop a white pedestal"</p><p></p><p>Purz</p><p>Website: <a target="blank" rel="ugc" href="https://www.purz.xyz/">https://www.purz.xyz/</a><br />Creative Exploration /w Purz: <a target="blank" rel="ugc" href="https://www.youtube.com/@PurzBeats">https://www.youtube.com/@PurzBeats</a><br />Patreon: <a target="blank" rel="ugc" href="https://www.patreon.com/Purz">https://www.patreon.com/Purz</a><br />Twitter/X: <a target="blank" rel="ugc" href="https://x.com/PurzBeats">https://x.com/PurzBeats</a><br />Instagram: <a target="blank" rel="ugc" href="https://www.instagram.com/purzbeats/">https://www.instagram.com/purzbeats/</a></p>

Trigger words

You should use 50ft_5cu7pt 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('Purz/soft-sculpture', weight_name='purz-50ft_5cu7pt-soft_sculpture.safetensors')
image = pipeline('50ft_5cu7pt, a sculpture of a man's face stuck in honey, sitting atop a yellow lucite pedestal').images[0]

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