--- 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 - neon - concept - text - sign - neon signs - purz - flux1.d base_model: black-forest-labs/FLUX.1-dev instance_prompt: n30n_51gn widget: - text: 'n30n_51gn, a neon sign that says "Civitai"' output: url: >- 33944768.jpeg - text: 'n30n_51gn, a yellow neon sign that says "Stack That Buzz"' output: url: >- 33944776.jpeg - text: 'n30n_51gn, a neon sign that says "Civitai"' output: url: >- 33944786.jpeg - text: 'n30n_51gn, a neon sign of a donut with sprinkles' output: url: >- 33944916.jpeg - text: 'n30n_51gn, a neon sign an uzi' output: url: >- 33944921.jpeg - text: 'n30n_51gn, a neon sign of red lips kissing ' output: url: >- 33944982.jpeg - text: 'n30n_51gn, a neon sign of a donut with sprinkles, sign that says "The Donut Hole"' output: url: >- 33945041.jpeg --- # Neon Sign ## Model description

Neon Sign - LoRA (Flux.1 D)

Trained on images of piped neon signs, it's great at text but can also do icons and emojis.

" n30n_51gn, a yellow neon sign that says "Stack That Buzz" "

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 `n30n_51gn` to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](/Purz/neon-sign/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/neon-sign', weight_name='purz-n30n_51gn.safetensors') image = pipeline('n30n_51gn, a neon sign of a donut with sprinkles, sign that says "The Donut Hole"').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)