Add model card metadata: base_model, license, pipeline_tag, tags

README.md

@@ -0,0 +1,57 @@
+---
+base_model: Qwen/Qwen-Image-Edit
+library_name: diffusers
+license: apache-2.0
+pipeline_tag: image-to-image
+tags:
+- qwen-image
+- image-to-image
+- image-editing
+- quantized
+- fp8
+- e4m3
+- diffusers
+base_model_relation: quantized
+---
+# Qwen-Image-Edit-e4m3
+
+FP8 (e4m3) dynamically-quantized [Qwen-Image-Edit](https://huggingface.co/Qwen/Qwen-Image-Edit),
+saved as a complete `QwenImageEditPipeline`.
+
+## What was changed
+
+All 60 blocks of the `QwenImageTransformer2DModel` are quantized to
+`e4m3_e4m3_dynamic` — `float8_e4m3fn` weights with dynamically scaled
+`float8_e4m3fn` activations. The Qwen2.5-VL text encoder, the processor, the
+VAE and the transformer's non-block tensors are untouched and stay in bf16. The
+transformer drops from ~40.9 GB to ~20.5 GB.
+
+Quantization was done with WaveSpeed's `xelerate.ao.quantize`. Weights are
+stored as pickled `.bin` shards, so loading requires `use_safetensors=False`.
+FP8 matmul needs Hopper (H100/H200) or newer to actually be faster than bf16.
+
+## Usage
+
+```python
+import torch
+from diffusers import QwenImageEditPipeline
+from diffusers.utils import load_image
+
+pipe = QwenImageEditPipeline.from_pretrained(
+    "wavespeed/Qwen-Image-Edit-e4m3",
+    torch_dtype=torch.bfloat16,
+    use_safetensors=False,
+).to("cuda")
+
+image = load_image("input.png")
+out = pipe(image=image, prompt="make it a winter scene").images[0]
+```
+
+## Related
+
+- [`wavespeed/Qwen-Image-Edit-l8v1.1-e4m3`](https://huggingface.co/wavespeed/Qwen-Image-Edit-l8v1.1-e4m3)
+  — the same quantization with an 8-step Lightning LoRA fused in.
+
+## License
+
+Apache-2.0, inherited from Qwen-Image-Edit.