Qwen-Image long prompt will cause error

[akk-123]

When the token length is greater than 1024, it will be truncated to 1024. However, the length of RoPE is fixed at 1024 because the image takes up 32 len (for a 1024 width and height image). This causes the length of txt_freqs to be less than 1024. Therefore, x_rotated * freqs_cis will generate an error due to dimension mismatch.

RuntimeError: The size of tensor a (1024) must match the size of tensor b (983) at non-singleton dimension 2

[akk-123]

@mi804 diffusers has a PR (huggingface/diffusers#12087) to fix it, can you fix it in DiffSynth

[Artiprocher]

@akk-123 Thank you for your feedback. We will fix this issue.

[akk-123]

@Artiprocher When will this issue be fixed?

[mi804]

@akk-123 fixed in #791