Instructions to use ujouy/FLUXULTRAREAL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ujouy/FLUXULTRAREAL with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("ujouy/FLUXULTRAREAL") prompt = "-" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Please note this is just a copy to port to huggingface, all rights reserved to the original creator.
Flux 1.D

- Prompt
- -

- Prompt
- -
Model description
The main goal was to make more 'live' images with livelier emotions and more dynamic poses and slightly amateurish quality (also can produce high quality images).
Trigger words
You should use amateurish photo to trigger the image generation.
You should use low lighting to trigger the image generation.
You should use in motion to trigger the image generation.
You should use overexposed to trigger the image generation.
You should use underexposed to trigger the image generation.
You should use GoPro to trigger the image generation.
You should use lens to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
- Downloads last month
- 4
Model tree for ujouy/FLUXULTRAREAL
Base model
black-forest-labs/FLUX.1-dev