feat: qwen-image-edit-2509 lightning support (#728)

* update

* add qwen-image-edit-2509-lightning

* avoid test for now

.github/workflows/pr-test.yaml

 name: PR Tests
 on:
   pull_request:
-    types: [opened, synchronize, reopened, ready_for_review]
+    types: [opened, synchronize, reopened]
     paths:
       - "nunchaku/**"
       - "src/**"

README.md

@@ -15,17 +15,18 @@ Join our user groups on [**Discord**](https://discord.gg/Wk6PnwX9Sm) and [**WeCh
 
 ## News
 
+- **[2025-08-27]** 🔥 Release **4-bit [4/8-step lightning Qwen-Image-Edit-2509](https://huggingface.co/lightx2v/Qwen-Image-Lightning)**! Download on [Hugging Face](https://huggingface.co/nunchaku-tech/nunchaku-qwen-image-edit-2509) or [ModelScope](https://modelscope.cn/models/nunchaku-tech/nunchaku-qwen-image-edit-2509), and try it with our [example script](examples/v1/qwen-image-edit-2509-lightning.py).
 - **[2025-09-24]** 🔥 Released [**4-bit Qwen-Image-Edit-2509**](https://huggingface.co/Qwen/Qwen-Image-Edit-2509)! Models are available on [Hugging Face](https://huggingface.co/nunchaku-tech/nunchaku-qwen-image-edit-2509). Try them out with our [example script](examples/v1/qwen-image-edit-2509.py). Lightning models will follow up!
 - **[2025-09-09]** 🔥 Released [**4-bit Qwen-Image-Edit**](https://huggingface.co/Qwen/Qwen-Image-Edit) together with the [4/8-step Lightning](https://huggingface.co/lightx2v/Qwen-Image-Lightning) variants! Models are available on [Hugging Face](https://huggingface.co/nunchaku-tech/nunchaku-qwen-image-edit). Try them out with our [example script](examples/v1/qwen-image-edit.py).
 - **[2025-09-04]** 🚀 Official release of **Nunchaku v1.0.0**! Qwen-Image now supports **asynchronous offloading**, reducing VRAM usage to as little as **3 GiB** with no performance loss. Check out the [tutorial](https://nunchaku.tech/docs/nunchaku/usage/qwenimage.html) to get started.
 - **[2025-08-27]** 🔥 Release **4-bit [4/8-step lightning Qwen-Image](https://huggingface.co/lightx2v/Qwen-Image-Lightning)**! Download on [Hugging Face](https://huggingface.co/nunchaku-tech/nunchaku-qwen-image) or [ModelScope](https://modelscope.cn/models/nunchaku-tech/nunchaku-qwen-image), and try it with our [example script](examples/v1/qwen-image-lightning.py).
 - **[2025-08-15]** 🔥 Our **4-bit Qwen-Image** models are now live on [Hugging Face](https://huggingface.co/nunchaku-tech/nunchaku-qwen-image)! Get started with our [example script](examples/v1/qwen-image.py). *ComfyUI, LoRA, and CPU offloading support are coming soon!*
 - **[2025-08-15]** 🚀 The **Python backend** is now available! Explore our Pythonic FLUX models [here](nunchaku/models/transformers/transformer_flux_v2.py) and see the modular **4-bit linear layer** [here](nunchaku/models/linear.py).
-- **[2025-07-31]** 🚀 **[FLUX.1-Krea-dev](https://www.krea.ai/blog/flux-krea-open-source-release) is now supported!** Check out our new [example script](./examples/flux.1-krea-dev.py) to get started.
 
 <details>
 <summary>More</summary>
 
+- **[2025-07-31]** 🚀 **[FLUX.1-Krea-dev](https://www.krea.ai/blog/flux-krea-open-source-release) is now supported!** Check out our new [example script](./examples/flux.1-krea-dev.py) to get started.
 - **[2025-07-13]** 🚀 The official [**Nunchaku documentation**](https://nunchaku.tech/docs/nunchaku/) is now live! Explore comprehensive guides and resources to help you get started.
 - **[2025-06-29]** 🔥 Support **FLUX.1-Kontext**! Try out our [example script](./examples/flux.1-kontext-dev.py) to see it in action! Our demo is available at this [link](https://svdquant.mit.edu/kontext/)!
 - **[2025-06-01]** 🚀 **Release v0.3.0!** This update adds support for multiple-batch inference, [**ControlNet-Union-Pro 2.0**](https://huggingface.co/Shakker-Labs/FLUX.1-dev-ControlNet-Union-Pro-2.0), initial integration of [**PuLID**](https://github.com/ToTheBeginning/PuLID), and introduces [**Double FB Cache**](examples/flux.1-dev-double_cache.py). You can now load Nunchaku FLUX models as a single file, and our upgraded [**4-bit T5 encoder**](https://huggingface.co/nunchaku-tech/nunchaku-t5) now matches **FP8 T5** in quality!

examples/v1/qwen-image-edit-2509-lightning.py

+import math
+
+import torch
+from diffusers import FlowMatchEulerDiscreteScheduler, QwenImageEditPlusPipeline
+from diffusers.utils import load_image
+
+from nunchaku import NunchakuQwenImageTransformer2DModel
+from nunchaku.utils import get_gpu_memory, get_precision
+
+# From https://github.com/ModelTC/Qwen-Image-Lightning/blob/342260e8f5468d2f24d084ce04f55e101007118b/generate_with_diffusers.py#L82C9-L97C10
+scheduler_config = {
+    "base_image_seq_len": 256,
+    "base_shift": math.log(3),  # We use shift=3 in distillation
+    "invert_sigmas": False,
+    "max_image_seq_len": 8192,
+    "max_shift": math.log(3),  # We use shift=3 in distillation
+    "num_train_timesteps": 1000,
+    "shift": 1.0,
+    "shift_terminal": None,  # set shift_terminal to None
+    "stochastic_sampling": False,
+    "time_shift_type": "exponential",
+    "use_beta_sigmas": False,
+    "use_dynamic_shifting": True,
+    "use_exponential_sigmas": False,
+    "use_karras_sigmas": False,
+}
+scheduler = FlowMatchEulerDiscreteScheduler.from_config(scheduler_config)
+
+num_inference_steps = 4  # you can also use the 8-step model to improve the quality
+rank = 32  # you can also use the rank=128 model to improve the quality
+model_path = f"nunchaku-tech/nunchaku-qwen-image-edit-2509-lightning/svdq-{get_precision()}_r{rank}-qwen-image-edit-2509-lightningv2.0-{num_inference_steps}steps.safetensors"
+
+# Load the model
+transformer = NunchakuQwenImageTransformer2DModel.from_pretrained(model_path)
+
+pipeline = QwenImageEditPlusPipeline.from_pretrained(
+    "Qwen/Qwen-Image-Edit-2509", transformer=transformer, torch_dtype=torch.bfloat16
+)
+
+if get_gpu_memory() > 18:
+    pipeline.enable_model_cpu_offload()
+else:
+    # use per-layer offloading for low VRAM. This only requires 3-4GB of VRAM.
+    transformer.set_offload(
+        True, use_pin_memory=False, num_blocks_on_gpu=1
+    )  # increase num_blocks_on_gpu if you have more VRAM
+    pipeline._exclude_from_cpu_offload.append("transformer")
+    pipeline.enable_sequential_cpu_offload()
+
+image1 = load_image("https://huggingface.co/datasets/nunchaku-tech/test-data/resolve/main/inputs/man.png")
+image1 = image1.convert("RGB")
+image2 = load_image("https://huggingface.co/datasets/nunchaku-tech/test-data/resolve/main/inputs/puppy.png")
+image2 = image2.convert("RGB")
+image3 = load_image("https://huggingface.co/datasets/nunchaku-tech/test-data/resolve/main/inputs/sofa.png")
+image3 = image3.convert("RGB")
+
+prompt = "Let the man in image 1 lie on the sofa in image 3, and let the puppy in image 2 lie on the floor to sleep."
+inputs = {
+    "image": [image1, image2, image3],
+    "prompt": prompt,
+    "true_cfg_scale": 1.0,
+    "num_inference_steps": num_inference_steps,
+}
+
+output = pipeline(**inputs)
+output_image = output.images[0]
+output_image.save(f"qwen-image-edit-2509-lightning-r{rank}-{num_inference_steps}steps.png")

examples/v1/qwen-image-edit-lightning.py

@@ -26,8 +26,8 @@ scheduler_config = {
 }
 scheduler = FlowMatchEulerDiscreteScheduler.from_config(scheduler_config)
 
-num_inference_steps = 8  # you can also use the 8-step model to improve the quality
-rank = 128  # you can also use the rank=128 model to improve the quality
+num_inference_steps = 4  # you can also use the 8-step model to improve the quality
+rank = 32  # you can also use the rank=128 model to improve the quality
 model_paths = {
     4: f"nunchaku-tech/nunchaku-qwen-image-edit/svdq-{get_precision()}_r{rank}-qwen-image-edit-lightningv1.0-4steps.safetensors",
     8: f"nunchaku-tech/nunchaku-qwen-image-edit/svdq-{get_precision()}_r{rank}-qwen-image-edit-lightningv1.0-8steps.safetensors",