[Bug] Qwen-image-edit didn't work with multiple latent_image

[hubentu]

Checklist

• 1. I have searched for related issues and FAQs (https://github.com/mit-han-lab/nunchaku/blob/main/docs/faq.md) but was unable to find a solution.
• 2. The issue persists in the latest version.
• 3. Please note that without environment information and a minimal reproducible example, it will be difficult for us to reproduce and address the issue, which may delay our response.
• 4. If your report is a question rather than a bug, please submit it as a discussion at https://github.com/mit-han-lab/ComfyUI-nunchaku/discussions/new/choose. Otherwise, this issue will be closed.
• 5. I will do my best to describe the issue in English.

Describe the Bug

Current nunchaku works great for qwen-image-edit with one latent_image as input. HoweverWhen multiple latent images were provided for laten_image of ksampler (for example, Repeat Laten Batch node from comfy_core), it gave this error:

!!! Exception during processing !!! view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(...) instead.
Traceback (most recent call last):
...
RuntimeError: view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(...) instead.

Environment

Ubuntu 24.04.2 LTS
python 3.12.3
pytorch version: 2.8.0
cuda 13.0
Nunchaku version: 1.0.0.dev20250823
ComfyUI-nunchaku version: 1.0.0dev1

Reproduction Steps

Add "Repeat Latent Batch" between VAE Encode and KSampler. Works with size of 1, but not work with size > 1.

[lmxyy]

fixed in nunchaku-ai/nunchaku#673