Instructions to use nvidia/Qwen-Image-Edit-NVPCB-OVSL2SL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use nvidia/Qwen-Image-Edit-NVPCB-OVSL2SL 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("nvidia/Qwen-Image-Edit-NVPCB-OVSL2SL", dtype=torch.bfloat16, device_map="cuda") 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] - Notebooks
- Google Colab
- Kaggle
Commit History
-
Upload v2 fused checkpoint: ov_to_nvpcb_solderlight_ic_updated_v2_aug_2511
Verified signatureReplaces v1 at root. v1 retained at tag `v1` (commit f600e88f8512). Base model: Qwen/Qwen-Image-Edit-2511 Source LoRA: ic_landscape_aug_2511_2000_v3 / lora-step-01500 Pipeline class: QwenImageEditPlusPipeline Canonical inference parameters (per qwen-edit-nvpcb-FT/infer_fused_10samples.py): num_inference_steps=30 true_cfg_scale=4.0 negative_prompt=' ' (single space; required to enable CFG) seed=02e2beb9
-
Upload folder using huggingface_hub
Verified signaturef600e88