AI Technology & Industry Review
In a new paper Edify Image: High-Quality Image Generation with Pixel Space Laplacian Diffusion Models, an NVIDIA research team introduces Edify Image—a suite of pixel-based diffusion models that achieve high-resolution image synthesis with exceptional control and precision.
In a new paper Imagine Flash: Accelerating Emu Diffusion Models with Backward Distillation, a Meta GenAI research team introduces an innovative distillation framework aimed at enabling high-fidelity, diverse sample generation within just one to three steps. This framework surpasses existing competitors in both quantitative metrics and human evaluations.
A recent paper from Tencent’s research team introduces a novel identity-preserving synthesis approach, with a specific focus on human images. The proposed model adopts a direct feed-forward mechanism, eliminating the need for intensive fine-tuning and streamlining the image generation process.
In the new paper Hierarchical Text-Conditional Image Generation with CLIP Latents, an OpenAI research team combines the advantages of contrastive and diffusion models for text-conditional image generation tasks. Their proposed unCLIP model improves image diversity with minimal loss in photorealism and caption similarity, and produces image quality comparable to the state-of-the-art text-to-image system GLIDE.
A Google Research team proposes Masked Generative Image Transformer (MaskGIT), a novel image synthesis paradigm that uses a bidirectional transformer decoder. MaskGIT significantly outperforms state-of-the-art transformer models on the ImageNet dataset and accelerates autoregressive decoding by up to 64x.
Synced has identified a few significant technical advancements in the 3D photo field that we believe may be of interest to our readers.
A Seoul National University Master’s student and developer has trained a face generating model to transfer normal face photographs into cartoon images in the distinctive style of Lee Mal-nyeon.
Large transformer-based language models trained on pixel sequences can generate coherent images without the use of labels.
South Korea’s Naver Clova AI Research is one of the institutions behind the unsupervised generative network U-GAT-IT. The tech hasContinue Reading
Researchers have proposed a new image generative model that leverages the hierarchical space of deep features learned by pretrained classification networks and provides a unified and versatile framework for image generation and manipulation tasks.
Leading UK AI research company DeepMind has now proposed “BigBiGAN” (not BigBigGAN, but BigBiGAN), which achieves state-of-the-art results in both unsupervised representation learning on ImageNet and in unconditional image generation.
Generative adversarial networks (GANs) have become AI researchers’ “go-to” technique for generating photo-realistic synthetic images. Now, DeepMind researchers say that there may be a better option.