Pith. sign in

REVIEW 1 cited by

Directed Diffusion: Direct Control of Object Placement through Attention Guidance

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2302.13153 v3 pith:5R6MXNRN submitted 2023-02-25 cs.CV cs.GRcs.LG

classification cs.CVcs.GRcs.LG
keywords diffusionimagesobjectsmodelsapproachcharacterscontrolcross-attention
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Text-guided diffusion models such as DALLE-2, Imagen, eDiff-I, and Stable Diffusion are able to generate an effectively endless variety of images given only a short text prompt describing the desired image content. In many cases the images are of very high quality. However, these models often struggle to compose scenes containing several key objects such as characters in specified positional relationships. The missing capability to ``direct'' the placement of characters and objects both within and across images is crucial in storytelling, as recognized in the literature on film and animation theory. In this work, we take a particularly straightforward approach to providing the needed direction. Drawing on the observation that the cross-attention maps for prompt words reflect the spatial layout of objects denoted by those words, we introduce an optimization objective that produces ``activation'' at desired positions in these cross-attention maps. The resulting approach is a step toward generalizing the applicability of text-guided diffusion models beyond single images to collections of related images, as in storybooks. Directed Diffusion provides easy high-level positional control over multiple objects, while making use of an existing pre-trained model and maintaining a coherent blend between the positioned objects and the background. Moreover, it requires only a few lines to implement.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. TokenFlow: Consistent Diffusion Features for Consistent Video Editing

    cs.CV 2023-07 conditional novelty 6.0 of 10

    TokenFlow produces consistent text-driven video edits by propagating diffusion features according to inter-frame correspondences extracted from the source video.

Pith tools