Instructions to use prithivMLmods/Qwen-Image-Edit-2511-Object-Adder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use prithivMLmods/Qwen-Image-Edit-2511-Object-Adder 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("prithivMLmods/Qwen-Image-Edit-2511-Object-Adder") 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
an additional target image is not required?
#1
by suruchiarora - opened
This object-editing pipeline does not take an additional target image as an input alongside the original image to perform the replacement?Right?
You're right. The adapter is trained on both the original and target designs, specified as text (e.g., “Add a Batman design here” or “Make her wear tinted goggles”). A reference image is optional.
If you need an object to be added with high confidence that the output will match the reference image, you can use multi-image editing within the same pipeline, if needed.
prithivMLmods changed discussion status to closed