All updates

Text-to-image (T2I) systems serve users across languages and cultural contexts. However, evaluations of cultural representation focus mainly on recognizable elements such as landmarks, clothing, and activities, overlooking the cultural values that generated images convey. To…

EDGAR is a conditional diffusion framework with a fusion block and Mixture-of-Experts that refines degraded Gaussian head avatars by injecting self-supervised identity features, using refined multi-view renderings as pseudo-targets to optimize a single avatar.

Large-scale identity-labeled face datasets are essential for training modern face recognition models, yet collecting and annotating such data is costly and raises privacy and ethical concerns. Existing synthetic face generation methods typically derive identities from predefined…

Text-guided image editing with diffusion models struggles with spatial edits (e.g. manipulating objects, changing viewpoints, manipulating occlusions) that depend on the 3D structure understanding of a scene. Marigold and follow-up work demonstrate that a pretrained diffusion…

An image editing service records which user requests each edit, but the edited image itself does not contain this account information. Once the image is downloaded and shared, the service cannot identify the requesting user from the image alone. Embedding a user-specific…

Text "Gemini Introducing Gemini Omni 1.2 Flash" surroudned by images of a beehive, animals in conversation, a squid, and a woman walking down a street

In this video of ComfyUI Nodes Explained, you will learn how ComfyUI sets the size of your image: what the empty latent is, how width and height work, why the same seed gives a new image at a new size, why a bigger image is not always better, why 1080 becomes 1088, how aspect…

We present \textbf{WeLM-Image}, a unified image foundation model that integrates multimodal understanding into text-to-image generation, instruction-guided editing, and multi-reference synthesis. Designed for single-GPU deployment in WeChat's large-scale consumer applications…

Text to image and image editing · up to 16 reference images · $30.00 per 1M output image tokens

Text to image and image editing · up to 16 reference images · $30.00 per 1M output image tokens

We present an automated method for auditing text-to-image generators for representational bias against ground-truth demographic benchmarks. Our approach adapts the racial proxy variables used in U.S. antidiscrimination law to provide a fine-grained comparative analysis of…

OpenAI is adding a GIF feature to ChatGPT. With the new Images 2.6 model, users can create animated GIFs from text prompts or photos and then adjust speed and individual frames. The model's image consistency is strong enough to keep characters recognizable across frames, making…

Skin lesion segmentation without annotated masks requires the target to be specified through other cues. Existing approaches rely on dermoscopy-specific rules, annotation-derived model priors, or user-selected regions. A general text-to-image diffusion transformer offers a text…

We introduce LongBanana, to our knowledge the first expert-designed and expert-verified benchmark for long-context multi-reference image synthesis in the age of agent-driven image generation. The task requires retrieving dispersed visual evidence, rejecting distractors, binding…

Autoregressive image generation has recently emerged as a competitive visual generation paradigm, yet its generation order is often predefined or heuristic, such as next-patch prediction, random-order prediction, or one-step generation for specific scales. We observe that these…

Strong single-turn editing performance does not guarantee reliable multi-turn interaction: as edited outputs are repeatedly reused, small unintended changes can accumulate into severe visual drift. This long-term drift is often mitigated through training on multi-turn data or…

Images 2.6 brings faster image generation, GIF creation, more precise editing, and new API controls across ChatGPT, Codex, and the API.

Text-to-image (T2I) systems serve users across languages and cultural contexts. However, evaluations of cultural representation focus mainly on recognizable elements such as landmarks, clothing, and activities, overlooking the cultural values that generated images convey. To…

In this episode, we test MiniMax H3 in ComfyUI with 25 free workflows, plus 2 bonus workflows. H3 is a video model that makes video with sound, from your images, videos and audio. We test them all, and see what H3 does well and where it struggles. Part 1, change your video: a…

Test-time scaling (TTS) improves generative models by allocating additional inference-time computation to sampling, search, and verification. Existing image generation approaches, however, typically rank completed images or image-centric intermediate states. We study TTS for…

In-image machine translation (IIMT) replaces text in an image with its translation while preserving the surrounding visual context. Existing task-specific models achieve convincing performance but require massive paired training images before and after translation. As advanced…

Diffusion-based data augmentation has emerged as a powerful strategy for addressing data-scarce image classification. Recent pipelines typically adapt a pretrained text-to-image diffusion model to a limited number of class examples and subsequently sample synthetic images using…

Understanding how neurons respond to visual stimulus is an important question in both deep learning and neuroscience. It has significant implications for enhancing the interpretability of black-box artificial neural networks and for understanding the visual representation in the…

PLANET HELL is an AI Sci-FI Short Film expanding on the original AI Film trailer made in Veo-3.1 This is an ongoing series about a prison planet where every inmate gets one bullet. This latest film was made with Seedance 2.5, GPT Image 2 and 2.5, Nano Banana and Midjourney, and…

Many manipulation goals are easier to visualize than to specify numerically through explicit geometric constraints. We present VerifLM, a framework that converts image-edited goal configurations into physically verified 6-DoF object poses for planning. Using an edited image…

Prompt engineering is commonly used to encourage text-to-image models to generate more detailed images. However, it does not provide reliable, continuous, or disentangled control. We analyze feature tokens produced with and without detail-enhancing prompts across six diffusion…

Diffusion Transformer (DiT)-based text-to-image models have recently achieved remarkable success in image synthesis. However, when directly applied beyond their training resolution, these models often suffer from severe semantic degradation, where meaningful semantic content…

The scarcity of diverse, high-quality medical images remains a significant bottleneck in advancing AI-driven medical diagnostics and treatment planning. Traditional datasets often suffer from class imbalances, limited disease coverage, and insufficient variations in imaging…

Multi-object image generation in text-to-image diffusion models remains challenging, as existing approaches struggle to reliably generate all objects specified in a prompt. Compositional approaches that generate objects independently often fail to capture the interactions among…

This will turn a single image of an object into a full 3D Gaussian Splat in seconds. ComfyUI-Idol adds native support for Speridlabs’ open Idol model. This model is optimized for LOW Vram I will also show a way to convert it with MeshLab (free) and Blender (free) into a OBJ ####…

Your AI characters can now stand in your actual room, and react to what's in it! Simulon is back: turn a character image into a 3D "neural asset," place it in the real world through your phone's camera, act out the scene with your own camera move, and the app regenerates the…

Text to image and image editing · 1K, 2K, 4K · up to 10 reference images · from $0.13 per image

In this episode, we test MOSS Image, a free text to image model from OpenMOSS, in ComfyUI with 9 free workflows. It follows long, detailed prompts well, and it is very good at words in images. We start with text to image: photos and illustrations from a prompt, a prompt helper…

MOSS-Image is now support in ComfyUI for you to run an home, on your own computer! The Apache 2.0 license means is it proper FOSS - unlike some releases we've seen recently which limit your freedoms. With a small model size and a turbo LoRA, you'll be generating images in…