metadata
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
language:
- en
tags:
- flux
- diffusers
- lora
- replicate
base_model: black-forest-labs/FLUX.1-dev
pipeline_tag: text-to-image
instance_prompt: ANM
widget:
- text: >-
A ANM style photorealistic street scene during a vibrant sunset, with
power lines and utility poles silhouetted against the sky. The sky is
painted in rich hues of orange, pink, and purple, with clouds spread
across it in intricate patterns. Residential buildings line the street,
illuminated by warm, golden light from small shop windows. Cars and
pedestrians add life to the urban landscape.
output:
url: images/example_5asi7pzht.png
- text: >-
A ANM style cyberpunk cityscape at sunset with towering utility poles and
dense power lines silhouetted against a neon-hued sky of oranges, purples,
and pinks. The scene features low-rise buildings with illuminated signs
and neon lights, creating a moody, futuristic urban atmosphere. A few
sleek cars and pedestrians in futuristic attire add life to the scene.
output:
url: images/example_15byrppzj.png
Animewallpaper
Trained on Replicate using:
https://replicate.com/ostris/flux-dev-lora-trainer/train
Trigger words
You should use ANM
to trigger the image generation.
Use it with the 🧨 diffusers library
from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('FounderFeed/animewallpaper', weight_name='lora.safetensors')
image = pipeline('your prompt').images[0]
For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers