Instructions to use oshtz/flux-plastic3d with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use oshtz/flux-plastic3d 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("oshtz/flux-plastic3d") prompt = "plastic3d style, time-traveling jazz band performing for dinosaurs in a prehistoric jungle" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
flux-plastic3d
.jpg)
- Prompt
- plastic3d style, time-traveling jazz band performing for dinosaurs in a prehistoric jungle
.jpg)
- Prompt
- plastic3d style, post-apocalyptic greenhouse thriving on the moon's surface, tended by alien botanists
.jpg)
- Prompt
- plastic3d style, robotic chef preparing a gourmet meal in a kitchen made entirely of candy
.jpg)
- Prompt
- plastic3d style, surreal treehouse library floating in a cosmic nebula with books orbiting like planets
.jpg)
- Prompt
- plastic3d style, steampunk octopus operating a vintage submarine in an underwater Victorian city

- Prompt
- plastic3d style, cyberpunk samurai riding a neon-lit hoverboard through a futuristic Tokyo
Model description
flux.1 'plastic3d' lora
trigger words [plastic3d style] used in dataset, but [plastic3d] is enough at times. trained on dev but also works on schnell, enjoy.
Trigger words
You should use plastic3d style 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
- 5
Model tree for oshtz/flux-plastic3d
Base model
black-forest-labs/FLUX.1-dev