Image-to-Image
Diffusers
English
qwen
qwen-image-edit
qwen-image-edit-2511
lora
multi-angle
camera-angles
camera-control
image-editing
gaussian-splatting
fal
Instructions to use fal/Qwen-Image-Edit-2511-Multiple-Angles-LoRA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use fal/Qwen-Image-Edit-2511-Multiple-Angles-LoRA 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-2511", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("fal/Qwen-Image-Edit-2511-Multiple-Angles-LoRA") 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
training details
#8
by bloombm - opened
Great work! I was wondering if you could share some details about the training process? You mentioned using over 3,000 synthetic 3D renders. My understanding is that these renders are usually background-free. Did you add backgrounds during training, or does the model naturally generalize to tasks with backgrounds even when trained on isolated objects?
3000 gaussian splatting. This is not synthetic data.
What is the composition of the splatting data? Exterior enviroments? people? pets? Any chance on giving more info/releasing the training set so people can build on top of it?
@lovis93