Closed vuongminh1907 closed 1 week ago
Hi, @vuongminh1907 start_merge_step is used to balance the influence of image token conditions and text prompt conditions during the inference process, details are list in the appendix of our paper.
Here, null_prompt_embeds represents negative prompt embedding (refer to L474), augmented_prompt_embeds represents the embedding of mixed image tokens and text prompts, and text_prompt_embeds represents the embedding of separate text prompts (refer to L505).
In this code: ( null_prompt_embeds, augmented_prompt_embeds, text_prompt_embeds, ) = prompt_embeds.chunk(3) You use start_merge_step to use two of them for prompt_embeds in this code:
All code in pipline_StableDiffusion_ConsistentID.py My question is : What are null_prompt_embeds, augmented_prompt_embeds, text_prompt_embeds meaning? And why you use start_merge_step ? Thanks so much <3