Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

C3Net: Compound Conditioned ControlNet for Multimodal Content Generation

About

We present Compound Conditioned ControlNet, C3Net, a novel generative neural architecture taking conditions from multiple modalities and synthesizing multimodal contents simultaneously (e.g., image, text, audio). C3Net adapts the ControlNet architecture to jointly train and make inferences on a production-ready diffusion model and its trainable copies. Specifically, C3Net first aligns the conditions from multi-modalities to the same semantic latent space using modality-specific encoders based on contrastive training. Then, it generates multimodal outputs based on the aligned latent space, whose semantic information is combined using a ControlNet-like architecture called Control C3-UNet. Correspondingly, with this system design, our model offers an improved solution for joint-modality generation through learning and explaining multimodal conditions instead of simply taking linear interpolations on the latent space. Meanwhile, as we align conditions to a unified latent space, C3Net only requires one trainable Control C3-UNet to work on multimodal semantic information. Furthermore, our model employs unimodal pretraining on the condition alignment stage, outperforming the non-pretrained alignment even on relatively scarce training data and thus demonstrating high-quality compound condition generation. We contribute the first high-quality tri-modal validation set to validate quantitatively that C3Net outperforms or is on par with first and contemporary state-of-the-art multimodal generation. Our codes and tri-modal dataset will be released.

Juntao Zhang, Yuehuai Liu, Yu-Wing Tai, Chi-Keung Tang• 2023

Related benchmarks

TaskDatasetResultRank
Audio ClassificationESC-50
Accuracy23.25
325
Audio SynthesisTri-modality (test)
OVL Score63.25
3
Compound conditioned image synthesisTri-modality (test)
FID10.97
2
Text SynthesisTri-modality (test)
BLEU-111.04
2
Showing 4 of 4 rows

Other info

Follow for update