Conversation
The default system template sent to the Qwen text encoder misspelled 'prompt engineer' as 'promt engineer' (4 pipelines). Note: this changes the token sequence of the default template, so default outputs will differ numerically from before / from the upstream Kandinsky5 reference. If exact parity with the reference repo is preferred, the reference itself would need the same fix.
|
Hi @simpleqt, thanks for the PR! It does not appear to link an issue it fixes. If this PR addresses an existing issue, please add a closing keyword (e.g. Please note that PRs without a linked issue are likely to be automatically closed 10 days after this notice. Once the PR links an issue (or gets the |
|
Can you group multiple of these PRs together, please? |
|
Closing — pooled into #14715 combined docs PR to reduce review overhead. All fixes are preserved in the combined branch. |
The kandinsky5 default system templates misspelled "prompt engineer" as "promt engineer" (
pipeline_kandinsky_t2i.py,pipeline_kandinsky_i2i.py,pipeline_kandinsky_i2v.py,pipeline_kandinsky.py— the string is sent verbatim to the Qwen text encoder on every default generation).Heads-up: fixing the spelling changes the token sequence of the default template, so default outputs will differ numerically from before / from the upstream Kandinsky5 reference. If exact parity with the reference repo matters more than the typo, feel free to close this — but the reference upstream spells it "prompt" too, so I believe this is the intended text.