Tianrui Huang comments

Results 6 comments of


                                            Tianrui Huang

[Feature] Support Style-Based Global Appearance Flow for Virtual Try-On

> BTW, may I close PR #1781? Sure it's okay to close it~ > Hey @FerryHuang F, thanks for this great work. Since `MMEdit` has changed it's name to `MMagic`,...

Question about Attention

Maybe it works fine too, without chunking for u and c? I checked it and it turns out to be the same value with the [current algorithm](https://github.com/TencentARC/MasaCtrl/blob/f4476b0adeb6d111a532aca5111457fc5b6e9f88/masactrl/masactrl.py#L53C1-L56C37).

Issues on resume training

0.6.1.post1

Issues on resume training

> Same here. Could you let me know if you have solved this issue? [@FerryHuang](https://github.com/FerryHuang) [@hijkzzz](https://github.com/hijkzzz) Not solved yet...Pending now

Prebuild flash attention wheels for linux!

Same with the latest flash_attn-2.7.4.post1+pt270cu128cxx11abiTRUE-cp310-cp310-linux_x86_64.whl

[Bug]: qwen2-vl 7b, on vllm 0.8.1 & 0.8.2, sometimes (not deterministically but depends on data) I got: ValueError: Attempted to assign 702 = 702 multimodal tokens to 703 placeholders

Any fix or workaround until now? Fix here (https://github.com/vllm-project/vllm/pull/16229) seems to be not completed yet.