Akshan Krithick

+1

Hey @sayakpaul, I would like to claim https://github.com/huggingface/diffusers/issues/12458 ([Qwen-image-edit] Batch Inference Issue / Feature Request). I have reviewed the previous failed PR attempts and posted a new RFC on the...

did you try ```python import os os.environ["PYTORCH_CUDA_ALLOC_CONF"] = "expandable_segments:True" ``` at the beginning of the notebook then ```python import torch ``` --- Also did you consider ```python import gc gc.collect()...

Hi @sayakpaul and @yiyixuxu, I’d like to tackle this for the MVP program. I’ve analyzed the tracebacks and the previous discussion in PR #12467. It seems the core issue is...

Hi @sayakpaul and @yiyixuxu, I would like to reiterate my interest in this issue. I have been working extensively on fine-tuning Qwen-Image-Edit(for synthetic data production), and I believe I have...

Hi @Django-Jiang, I dug into the reproduction script and found the cause of the specific AttributeError: 'tuple' object has no attribute 'size'. It is a small syntax typo in the...

Hi @Django-Jiang, I have opened a fix for this in PR #12698. It resolves the crash you were seeing by: 1. **Fixing the Tuple Bug:** The pipeline now properly handles...

**Update on PR #12698** Just pushed a logic update. While the 5D tensor fix handled the immediate architecture mismatch, I refined how we handle mixed-resolution batches to be cleaner. Overall:...

Hey @sayakpaul, it would be great if my PR could be reviewed! Also, can I consider this as having been assigned to me

Hi @yiyixuxu, I’ve fixed the variant prompt length issue by padding in this PR, and batching now works correctly. I also validated it in a notebook and can share the...