Instructions to use p4ss3r2/wan22_Pupil_Transition_LoRa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use p4ss3r2/wan22_Pupil_Transition_LoRa with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Wan-AI/Wan2.2-I2V-A14B", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("p4ss3r2/wan22_Pupil_Transition_LoRa") prompt = "-" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
wan_22_high_noise_pupil_transition

- Prompt
- -

- Prompt
- -

- Prompt
- -

- Prompt
- -
Model description
It's a wan2.2 LoRA for pupil transition effect which achieves good performance beyond my expectations with low training cost using only one RTX4090.
Extremely suitable for first-last-frame case / Seems to well adapt to lightx2v accelerating lora / Support both realistic and anime style
I trained it only on high-noise model using musubi-tuner released by kohya-ss, which is enough to achieve good dynamics, so just load it in conjunction with the high-noise model.
Trigger words: "skyrimprey pupil transition" Could be described like "skyrimprey pupil transition, a medium close-up of an Asian woman, with a blurred garden in the background. The camera zooms in to complete a pupil transition, shifting the scene to a wide-angle aerial shot, showing misty mountains with a coastal port town at the foot of the mountains."
Trigger words
You should use skyrimprey pupil transition to trigger the image generation.
Download model
Download them in the Files & versions tab.
- Downloads last month
- 24
Model tree for p4ss3r2/wan22_Pupil_Transition_LoRa
Base model
Wan-AI/Wan2.2-I2V-A14B