Instructions to use dx8152/Qwen-Edit-2509-Multiple-angles with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use dx8152/Qwen-Edit-2509-Multiple-angles with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Qwen/Qwen-Image-Edit-2509", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("dx8152/Qwen-Edit-2509-Multiple-angles") prompt = "Turn this cat into a dog" input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png") image = pipe(image=input_image, prompt=prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
3d stereo image generation ?
With this interesting lora from you, we could be very close to generating 3d stereo AI photos if you add a camera view disparity between eyes.
Just an idea. What do you think? Would it be possible to push QWEN to generate stereo images. Your Lora seems to be doing something very similar, but
3d stereo would need an exact camera positioning by a nn to a side, like 64mm or so.
With this interesting lora from you, we could be very close to generating 3d stereo AI photos if you add a camera view disparity between eyes.
Just an idea. What do you think? Would it be possible to push QWEN to generate stereo images. Your Lora seems to be doing something very similar, but
3d stereo would need an exact camera positioning by a nn to a side, like 64mm or so.
I have this idea, but a single image definitely won't work. I estimate I'll need three images to control the image, similar to a three-view drawing, so the product can be rotated freely.