Create README.md

README.md

@@ -0,0 +1,99 @@
+---
+license: apache-2.0
+base_model:
+- black-forest-labs/FLUX.1-dev
+- Qwen/Qwen-Image
+---
+# ArcFlow
+ArcFlow: Unleashing 2-Step Text-to-Image Generation via High-Precision Non-Linear Flow Distillation
+<br/>
+Zihan Yang<sup>1</sup>, 
+[Shuyuan Tu](https://github.com/Francis-Rings)<sup>1</sup>, 
+Licheng Zhang<sup>1</sup>, 
+[Qi Dai](https://scholar.google.com/citations?hl=en&user=NSJY12IAAAAJ)<sup>2</sup>, 
+[Yu-Gang Jiang](https://scholar.google.com/citations?hl=en&user=f3_FP8AAAAAJ)<sup>1</sup>, 
+[Zuxuan Wu](https://zxwu.azurewebsites.net/)<sup>1</sup>
+<br/>
+[<sup>1</sup>Fudan University; <sup>2</sup>Microsoft Research Asia]
+## Usage
+
+Please first install the [official code repository](https://github.com/pnotp/ArcFlow).
+
+We provide diffusers pipelines for easy inference. The following code demonstrates how to sample images from the distilled FLUX.2 models.
+
+### 4-NFE/2-NFE Arc-Qwen (Distilled from Qwen-Image-20B)
+
+```python
+import torch
+from diffusers import FlowMatchEulerDiscreteScheduler
+from lakonlab.pipelines.arcqwen_pipeline import ArcQwenImagePipeline
+
+pipe = ArcQwenImagePipeline.from_pretrained(
+    'Qwen/Qwen-Image',
+    torch_dtype=torch.bfloat16)
+adapter_name = pipe.load_arcflow_adapter(  
+    'ymyy307/ArcFlow',
+    subfolder='arcflow-qwen-2steps',
+    target_module_name='transformer')
+pipe.scheduler = FlowMatchEulerDiscreteScheduler.from_config(  # use fixed shift=3.2
+    pipe.scheduler.config, shift=3.2, shift_terminal=None, use_dynamic_shifting=False)
+pipe = pipe.to('cuda')
+
+nfe = 4
+# nfe = 2
+out = pipe(
+    prompt = 'A semi-realistic fantasy illustration featuring a split composition of two young men in profile, facing away from each other. On the left, a pale man with sharp features and slicked-back black hair wears a dark coat. On the right, a tan man with messy wavy hair wears a blue tunic. The ornate, 3D metallic gold title "Sultan\'s Game" overlays the bottom center. The background is divided into distinct sections: vibrant red abstract shapes in the upper half and deep teal textures in the lower half, creating a sharp color contrast. Painterly brushstrokes.',
+    num_images_per_prompt=1,
+    width=1024,
+    height=1024,
+    num_inference_steps=nfe,
+    generator=torch.Generator(device="cuda").manual_seed(42),
+    timestep_ratio=1.0,
+).images[0]
+out.save(f'arcqwen_{nfe}nfe.png')
+```
+
+### 4-NFE/2-NFE Arc-FLUX (Distilled from FLUX.1-dev)
+
+```python
+import torch
+from diffusers import FlowMatchEulerDiscreteScheduler
+from lakonlab.pipelines.arcflux_pipeline import ArcFluxPipeline
+
+pipe = ArcFluxPipeline.from_pretrained(
+    'black-forest-labs/FLUX.1-dev',
+    torch_dtype=torch.bfloat16)
+adapter_name = pipe.load_arcflow_adapter(  # you may later call `pipe.set_adapters([adapter_name, ...])` to combine other adapters (e.g., style LoRAs)
+    'ymyy307/ArcFlow',
+    subfolder='arcflow-flux-2steps',
+    target_module_name='transformer')
+pipe.scheduler = FlowMatchEulerDiscreteScheduler.from_config(  # use fixed shift=3.2
+    pipe.scheduler.config, shift=3.2, shift_terminal=None, use_dynamic_shifting=False)
+pipe = pipe.to('cuda')
+
+nfe = 4
+# nfe = 2
+out = pipe(
+    prompt = 'A portrait photo of a kangaroo wearing an orange hoodie and blue sunglasses standing in front of the Sydney Opera House holding a sign on the chest that says "Welcome Friends"',
+    num_images_per_prompt=1,
+    width=1024,
+    height=1024,
+    num_inference_steps=nfe,
+    generator=torch.Generator(device="cuda").manual_seed(42),
+    timestep_ratio=1.0,
+).images[0]
+out.save(f'arcflux_{nfe}nfe.png')
+```
+
+## Citation
+```
+@misc{yang2026arcflowunleashing2steptexttoimage,
+      title={ArcFlow: Unleashing 2-Step Text-to-Image Generation via High-Precision Non-Linear Flow Distillation}, 
+      author={Zihan Yang and Shuyuan Tu and Licheng Zhang and Qi Dai and Yu-Gang Jiang and Zuxuan Wu},
+      year={2026},
+      eprint={2602.09014},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV},
+      url={https://arxiv.org/abs/2602.09014}, 
+}
+```