AI tools for Photo Editing

Pexo is an AI video agent that turns natural language descriptions into polished, ready-to-post videos, interpreting intent, suggesting creative directions and selecting the bes

Readdy is an AI website builder and business platform that turns natural-language descriptions into professional, production-ready websites. Users generate business sites, portf

NitroFusion2 is a text-to-image checkpoint designed to render a result in one or two diffusion steps. It builds on Z-Image-Turbo and targets sharp visual detail, including text

Inkling 2 Small is Thinking Machines Lab's multimodal language model for general assistance, coding and tool-using applications. It accepts text and images and generates text, w

P-H3-Image is Pruna AI's open-weight image generator and editor derived from MiniMax-H3. It supports text-to-image work and edits conditioned on several reference images, with a

P-JiT 21K is Linum's released research checkpoint for text-to-image generation. The two-billion-parameter model was trained on 660 million samples to investigate what a smaller

Gemini Omni 1.2 Flash generates and edits short audiovisual clips from text and visual references. The model supports up to 15 seconds of generated video with synchronized nativ

HairDeck turns a character image into stylized 3D hair cards for animation and avatar workflows. It produces a set of textured strips that follow the overall silhouette and the

GPT-6 Cyber is OpenAI's restricted model for authorized security research and defense. It can assist with investigating vulnerabilities, reproducing findings in approved test en

GPT Image 2.6 is OpenAI's model family for generating and editing visual assets. It accepts text instructions and reference images for work such as designing posters, creating p

Ling-3.2-Flash is Ant Group's hosted multimodal model for reasoning over text, images and video. Its model overview describes applications in visual understanding, spatial inter

CoLa3D reconstructs an object-composed 3D scene from a single image. It outputs individual meshes that share a coordinate frame so the resulting objects can be inspected and man

Tencent Hy4 is the final hosted release of Tencent's flagship model for long-running agent tasks. It adds visual understanding to the earlier preview's text capabilities and sup

LongCat-2.5 is Meituan's hosted multimodal model for extended agentic work. It combines image understanding with code generation for tasks such as working across complex project

Cactus Mirage is a compact vision model for local image understanding and structured extraction. It can describe a scene, locate objects, read text and produce masks or structur

Unlimited OCR 2 is Baidu's document-parsing model for long and multi-page material. It reads ordered page images in one request, preserving cross-page context while producing te

SenseNova-Loop-9B-Preview is an open multimodal language model for long-context and agentic workflows. It accepts text and images and generates text, supporting document interpr

PhysAg3D turns an object image into a detailed 3D asset with object-specific interactions. It combines generated appearance and geometry with reasoning about parts, joints, and

IDOL converts a single object image into a three-dimensional Gaussian splat. It accepts photographs, rendered objects, and generated images, reconstructing a viewable asset that

GPT-6.1 Terra is OpenAI's model for efficient visual reasoning, computer use, and written work. It accepts text and images and generates text, supporting applications that inter

CozyGPU lets you run open image and video models — including Minimax H3, LTX, Z-Image-Turbo, Qwen 2.1 and Krea 2 — from any computer in about five minutes, without owning a GPU.

PURE reconstructs depth, camera poses, and colored 3D point clouds from video clips or image sequences. Its unlabeled post-training approach improves feed-forward reconstruction