---
license: other
license_name: bespoke-lora-trained-license
license_link: https://multimodal.art/civitai-licenses?allowNoCredit=True&allowCommercialUse=Image&allowDerivatives=True&allowDifferentLicense=True
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
- migrated
- concept
- lollipop
- candy
- sweets
- purz
- flux1.d
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: c4ndy
widget:
- text: 'c4ndy, a close up of a basket filled with colorful gummy bears on a pink surface. the basket is made up of different colored candies'
output:
url: >-
33721998.jpeg
- text: 'c4ndy, a pile of colorful lollipops sitting on top of each other
'
output:
url: >-
33721994.jpeg
- text: 'c4ndy, adorable kitten made out of licorice
'
output:
url: >-
33721995.jpeg
- text: ' '
output:
url: >-
33722603.jpeg
- text: 'c4ndy, purz_face, a man made of candy wearing candy glasses'
output:
url: >-
33722608.jpeg
---
# Candy
Candy - LoRA (Flux.1 D)
Trained on images of large piles of delicious candy.
Mixes well with other LoRAs around 0.4 -> 0.6 strength.
"c4ndy, a pile of colorful candies sitting on top of each other on a white surface. the candies come in a variety of colors"
Purz
Website: https://www.purz.xyz/
Creative Exploration /w Purz: https://www.youtube.com/@PurzBeats
Patreon: https://www.patreon.com/Purz
Twitter/X: https://x.com/PurzBeats
Instagram: https://www.instagram.com/purzbeats/
## Trigger words You should use `c4ndy` to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](/Purz/candy/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('Purz/candy', weight_name='purz-c4ndy.safetensors') image = pipeline('c4ndy, purz_face, a man made of candy wearing candy glasses').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)