Instructions to use TheRaf7/ultra-real-wan2.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use TheRaf7/ultra-real-wan2.2 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Qwen/Qwen-Image", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("TheRaf7/ultra-real-wan2.2") prompt = "l3n0v0. underexposed outdoor scene, teenager girl, casual style, wearing dark trench coat, long wavy brown hair cascading over her shoulders, looking direct at the viewer, gothic heavy makeup, outdoors in the dark forest, autumn, smoking cigarette with smoke, showing middle finger not point finger, sunlight filtering through the trees. amateur quality, low resolution, candid style" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Ultra-Real

- Prompt
- l3n0v0. underexposed outdoor scene, teenager girl, casual style, wearing dark trench coat, long wavy brown hair cascading over her shoulders, looking direct at the viewer, gothic heavy makeup, outdoors in the dark forest, autumn, smoking cigarette with smoke, showing middle finger not point finger, sunlight filtering through the trees. amateur quality, low resolution, candid style
- Negative Prompt
- 8k, UHD, hyper-realism, cinematic, glossy finish, shallow depth of field, cinematic bokeh, plastic skin, uncanny anatomy, frame-perfect symmetry, blurred background, fat, old, milf, big lips, asian
Download model
Download them in the Files & versions tab.
- Downloads last month
- 1,324