SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.03485 · CVPR · 2024

NoiseCollage: A Layout-Aware Text-to-Image Diffusion Model Based on Noise Cropping and Merging

Seiichi Uchida, Takahiro Shirakawa

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 9 functions out of this paper's own repositories and ran 5 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
univ-esuty/noisecollage canonical 5 of 9
FunctionStatusWhere it lives
batch_per_cosine_similarity Ran univ-esuty/noisecollage/evaluation/model.py
pointer only (licence: NONE) · get_code("01ff60f53da84692")
batch_per_mse Ran univ-esuty/noisecollage/evaluation/model.py
pointer only (licence: NONE) · get_code("1bd79f01f560a239")
eval_result Ran univ-esuty/noisecollage/gen_img_by_noisecollage-with-controlnet.py
pointer only (licence: NONE) · get_code("06c26d7b1073325f")
get_activation Ran univ-esuty/noisecollage/diffusers/models/activations.py
pointer only (licence: NONE) · get_code("125f7ee5f275ed2a")
rescale_noise_cfg Ran univ-esuty/noisecollage/pipeline_custom/pipeline_noise_collage_controlnet.py
pointer only (licence: NONE) · get_code("bea2d776a332f2b0")
mse Not yet run univ-esuty/noisecollage/evaluation/model.py
pointer only (licence: NONE) · get_code("edf5d54bc7a50c95")
text_encoder_attn_modules Not yet run univ-esuty/noisecollage/diffusers/loaders.py
pointer only (licence: NONE) · get_code("f4ac91315a94774b")
text_encoder_lora_state_dict Not yet run univ-esuty/noisecollage/diffusers/loaders.py
pointer only (licence: NONE) · get_code("2c476d130bd89887")
text_encoder_mlp_modules Not yet run univ-esuty/noisecollage/diffusers/loaders.py
pointer only (licence: NONE) · get_code("ccca296c90beae91")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Layout-aware text-to-image generation is a task to generate multi-object images that reflect layout conditions in addition to text conditions. The current layout-aware textto-image diffusion models still have several issues, including mismatches between the text and layout conditions and quality degradation of generated images. This paper proposes a novel layout-aware text-to-image diffusion model called NoiseCollage to tackle these issues. During the denoising process, NoiseCollage independently estimates noises for individual objects and then crops and merges them into a single noise. This operation helps avoid condition mismatches; in other words, it can put the right objects in the right places. Qualitative and quantitative evaluations show that NoiseCollage outperforms several state-of-theart models. These successful results indicate that the cropand-merge operation of noises is a reasonable strategy to control image generation. We also show that NoiseCollage can be integrated with ControlNet to use edges, sketches, and pose skeletons as additional conditions. Experimental results show that this integration boosts the layout accuracy of ControlNet. The code is available at https: //github.com/univ-esuty/noisecollage.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2403.03485")
get_code_for_paper("2403.03485")
have("2403.03485")

Connect an agent — have() is free.