jiuntian/interactdiffusion

generated image not follow the defined bounding boxes with SD1.5 and interactdiff_v1.2.pth

zzhang2816 opened this issue · 0 comments

Thanks for the impressive work. I try the webui implementation but I find the generated image cannot follow the defined bounding boxes. How should I fix this issue.
Prompt: a photo of teddy holding briefcase
Grounding instruction: teddy=holding=briefcase
Screenshot 2024-01-14 at 18 23 33