In text-to-image (T2I) generation, achieving fine-grained control over attributes - such as age or smile - remains challenging, even with detailed text prompts. Slider-based methods offer a solution for precise control of image attributes. Existing approaches typically train individual adapter for each attribute separately, overlooking the entanglement among multiple attributes. As a result, interference occurs among different attributes, preventing precise control of multiple attributes together. To address this challenge, we aim to disentangle multiple attributes in slider-based generation to enbale more reliable and independent attribute manipulation. Our approach, CompSlider, can generate a conditional prior for the T2I foundation model to control multiple attributes simultaneously. Furthermore, we introduce novel disentanglement and structure losses to compose multiple attribute changes while maintaining structural consistency within the image. Since CompSlider operates in the latent space of the conditional prior and does not require retraining the foundation model, it reduces the computational burden for both training and inference. We evaluate our approach on a variety of image attributes and highlight its generality by extending to video generation.

Large text-to-image models have revolutionized the ability to generate imagery using natural language. However, particularly unique or personal visual concepts, such as pets and furniture, will not be captured by the original model. This has led to interest in how to personalize a text-to-image model. Despite significant progress, this task remains a formidable challenge, particularly in preserving the subject's identity. Most researchers attempt to address this issue by modifying model architectures. These methods are capable of keeping the subject structure and color but fail to preserve identity details. Towards this issue, our approach takes a data-centric perspective. We introduce a novel regularization dataset generation strategy on both the text and image level. This strategy enables the model to preserve fine details of the desired subjects, such as text and logos. Our method is architecture-agnostic and can be flexibly applied on various text-to-image models. We show on established benchmarks that our data-centric approach forms the new state of the art in terms of identity preservation and text alignment.

Diffusion models have shown tremendous results in image generation. However, due to the iterative nature of the diffusion process and its reliance on classifier-free guid-ance, inference times are slow. In this paper, we propose a new distillation approach for guided diffusion models in which an external lightweight guide model is trained while the original text-to-image model remains frozen. We show that our method reduces the inference computation of classifier-free guided latent-space diffusion models by almost half, and only requires 1% trainable parameters of the base model. Furthermore, once trained, our guide model can be applied to various fine-tuned, domain-specific versions of the base diffusion model without the need for additional training: this “plug-and-play” functionality drastically improves inference computation while maintaining the visual fidelity of generated images. Empirically, we show that our approach is able to produce visually appealing results and achieve a comparable FID score to the teacher with as few as 8 to 16 steps.

Several recent papers introduced techniques to adjust the attributes of human faces generated by unconditional GANs such as StyleGAN. Despite efforts to disentangle the attributes, a request to change one attribute often triggers unwanted changes to other attributes as well. More importantly, in some cases, a human observer would not recognize the edited face to belong to the same person. We propose an approach where a neural network takes as input the latent encoding of a face and the desired attribute changes and outputs the latent space encoding of the edited image. The network is trained offline using unsupervised data, with training labels generated by an off-the-shelf attribute classifier. The desired attribute changes and conservation laws, such as identity maintenance, are encoded in the training loss. The number of attributes the mapper can simultaneously modify is only limited by the attributes available to the classifier – we trained a network that handles 35 attributes, more than any previous approach. As no optimization is performed at deployment time, the computation time is negligible, allowing real-time attribute editing. Qualitative and quantitative comparisons with the current state-of-the-art show our method is better at conserving the identity of the face and restricting changes to the requested attributes.

Current face image retrieval solutions are limited, since they treat different facial attributes the same and cannot incorporate user’s preference for a subset of attributes in their search criteria. This paper introduces a new face image retrieval framework, where the input face query is augmented by both an adjustment vector that specifies the desired modifications to the facial attributes, and a preference vector that assigns different levels of importance to different attributes. For example, a user can ask for retrieving images similar to a query image, but with a different hair color, and no preference for absence/presence of eyeglasses in the results. To achieve this, we propose to disentangle the semantics, corresponding to various attributes, by learning a set of sparse and orthogonal basis vectors in the latent space of StyleGAN. Such basis vectors are then employed to decompose the dissimilarity between face images in terms of dissimilarity between their attributes, assign preference to the attributes, and adjust the attributes in the query. Enforcing sparsity on the basis vectors helps us to disentangle the latent space and adjust each attribute independently from other attributes, while enforcing orthogonality facilitates preference assignment and the dissimilarity decomposition. The effectiveness of our approach is illustrated by achieving state-of-the-art results for the face image retrieval task.

To make the best use of the underlying structure of faces, the collective information through face datasets and the intermediate estimates during the upsampling process, here we introduce a fully convolutional multi-stage neural network for 4× super-resolution for face images. We implicitly impose facial component-wise attention maps using a segmentation network to allow our network to focus on face-inherent patterns. Each stage of our network is composed of a stem layer, a residual backbone, and spatial upsampling layers. We recurrently apply stages to reconstruct an intermediate image, and then reuse its space-to-depth converted versions to bootstrap and enhance image quality progressively. Our experiments show that our face super-resolution method achieves quantitatively superior and perceptually pleasing results in comparison to state of the art.