Images

Models 111

• WaitlistGen 3 FLUX
  FLUX 3

  By Black Forest Labs

  FLUX 3 is a multimodal foundation model from Black Forest Labs that jointly learns from images, video, and audio within one unified architecture. It generates and edits video with native synchronized audio up to 20 seconds, supports image and video conditioning, keyframe control, and multilingual dialogue, and produces a wide range of visual styles. Image synthesis and action-prediction capabilities are being rolled out in later early access phases.

  🎥Videos📽️Image to video🔊Sound effects📷Images🎬Animations
  NewMultimodal

  Released 5d ago
• Research previewGen 4 MAI
  MAI-Image-2.5-Pro

  By Microsoft

  Text-to-image generation and image-to-image editing model from Microsoft. Uses a diffusion-based approach to produce high-fidelity, design-ready images from natural language prompts, with precise in-image text rendering and controllable, targeted edits.

  📷Images🖌️Image editing🖌️Image restoration🎨Image text overlay📸Photorealistic images
  NewImage

  Released 5d ago
• Gen 3 Gemini
  Gemini 3.6 Flash

  By Google

  Gemini 3.6 Flash is Google's workhorse model in the Gemini 3 series, a natively multimodal reasoning model built on Gemini 3.5 Flash. It improves coding, knowledge work, and multimodal performance while using fewer output tokens and running at a lower cost per task than its predecessor.

  💬Chatting📊Data analysis💻Coding📷Images🎥Videos
  NewMultimodal

  Released 7d ago
• Gen 4
  Mage Flow

  By Microsoft

  Mage-Flow is a compact 4B-parameter text-to-image diffusion model from Microsoft, built on a Native-Resolution Multimodal Diffusion Transformer (NR-MMDiT) paired with the Mage-VAE tokenizer. It generates images natively from 512 to 2048 pixels at any aspect ratio using rectified flow matching, reaching quality competitive with much larger open models while running efficiently.

  📷Images🎨Illustrations🎨Visual arts generation📸Photorealistic images
  NewImage

  Released 7d ago
• Gen 4 Qwen
  Qwen Image 3.0

  By Alibaba

  Qwen Image 3.0 is Alibaba's third generation image generation model, built to produce information dense images such as infographics, newspaper layouts, and documents with legible small text and mathematical notation. It accepts prompts of up to 4,500 tokens, renders text natively in 12 languages, and can incorporate live web data such as weather graphics. No benchmarks, parameter counts, or downloadable weights have been released for this version.

  📷Images🖌️Image editing📊Data visualization📊Infographics🎨Graphic design🎨UI design
  NewImage

  Released 7d ago
• Gen 3
  Bonsai 27B AWQ 4bit

  By PrismML

  Bonsai 27B AWQ 4bit is a 4-bit AWQ quantized release of Prism ML's Bonsai 27B, a 27 billion parameter multimodal model that accepts image and text input. It supports multi-step reasoning, tool calling, and agentic workflows, and is built for efficient deployment on inference engines like vLLM and SGLang.

  💬Chatting📷Images🔍Image analysis
  NewMultimodal

  Released 13d ago
• Gen 3 Qwen
  Ternary Bonsai 27B Unpacked

  By PrismML

  Ternary Bonsai 27B is a 27B parameter multimodal language model from PrismML, built on a hybrid linear and full attention (Qwen3.5 based) architecture with a 262,144 token context window. This repository provides the full size FP16 safetensors weights, an alternative to the natively packed 2 bit ternary format for use with standard model-serving tooling.

  💬Chatting📷Images🤖Agents
  NewMultimodal

  Released 14d ago
• Gen 3
  MOSS VL Realtime

  By OpenMOSS

  MOSS-VL-Realtime is an 11B parameter vision language model built for continuous video streams. It perceives incoming frames and generates text in parallel, answers questions asked at any point in the stream, and can stay silent or revise earlier answers as new visual evidence arrives. It uses a cross attention architecture with timestamp aware frame encoding and a 256K context window.

  🎥Video analysis📷Images🎥Videos🔍Image analysis🔍Visual analysis
  NewMultimodal

  Released 14d ago
• Gen 4 Gemini
  Gemini 3.1 Flash Lite Image

  By Google DeepMind

  Gemini 3.1 Flash-Lite Image, also known as Nano Banana 2 Lite, is Google DeepMinds fastest and most cost-efficient Gemini image model. It generates and edits images at high speed and low cost while preserving the accuracy and character consistency of the larger Nano Banana models.

  📷Images🖌️Image editing⚖️Character consistency
  NewImage

  Released 28d ago
• Gen 4 Krea
  Krea 2 Turbo

  By Krea.ai

  Krea 2 Turbo is Krea’s faster image-generation model variant for producing high-quality Krea 2 images in about 2 seconds.

  📷Images🎨Illustrations🎨Graphic design
  NewImage

  Released 1mo ago
• Gen 3 Ideogram
  Ideogram 4

  By Ideogram AI

  Ideogram 4.0 is Ideogram’s open-weight image-generation model for design work, multilingual text rendering, precise layout control, editable elements, and realistic 2K images.

  📷Images🖌️Image editing🎨Graphic design🔲Background removal⚖️Character consistency🔤Typography
  NewMultimodal

  Released 1mo ago
• Gen 4 MAI
  MAI Image 2.5 Flash

  By Microsoft

  MAI-Image-2.5 Flash is Microsoft AI’s ultra-efficient variant of MAI-Image-2.5 for lower-cost image generation and editing.

  📷Images🖌️Image editing✨Image enhancement
  NewImage

  Released 1mo ago
• Gen 4 MAI
  MAI Image 2.5

  By Microsoft

  MAI-Image-2.5 is Microsoft AI’s image model for text-to-image generation and image editing with strong design-ready output quality.

  📷Images🖌️Image editing✨Image enhancement🎨Graphic design
  NewImage

  Released 1mo ago
• Gen 3
  Lens

  By Microsoft

  Microsoft Lens is an open-source 3.8B text-to-image model focused on efficient training, fast high-resolution image generation, and strong prompt following.

  📷Images📸Photorealistic images
  NewMultimodal

  Released 2mo ago
• Gen 3
  Lance

  By ByteDance

  Lance is ByteDance’s open-source 3B active-parameter unified multimodal model for image and video understanding, generation, and editing.

  📷Images🖌️Image editing🎥Videos🔍Image interpretation
  NewMultimodal

  Released 2mo ago
• Gen 3
  T2I L2P

  By Tencent

  T2I-L2P is Tencent Youtu Research’s open-source pixel-space diffusion transfer method for turning latent text-to-image models into high-quality pixel-generation models.

  📷Images📸Photorealistic images
  NewMultimodal

  Released 2mo ago
• Gen 3 Krea
  Krea 2

  By Krea.ai

  Krea 2 is Krea AI’s real-time generative image model for highly controllable visual creation and editing. It is designed for instant iterative workflows, allowing users to guide style, composition, structure, and visual identity interactively rather than relying on one-shot prompt generation.

  📷Images🎨Visual imagery assistance🎨Art style exploration
  NewMultimodal

  Released 2mo ago
• Gen 3
  HiDream O1 Image Dev

  By HiDream.ai

  HiDream O1 Image Dev is fal’s developer-focused image generation model for high-quality visual synthesis and editing workflows. It is exposed through fal’s API infrastructure and positioned for controllable text-to-image generation, iterative creation, and integration into production creative pipelines.

  📷Images🖌️Image editing🎨Artistic image recreation
  NewMultimodal

  Released 2mo ago
• Gen 3
  Uni 1.1

  By Luma AI

  Uni-1.1 API is Luma’s closed-source REST API for image generation and natural-language image editing using its Unified Intelligence model.

  📷Images🖌️Image editing🔍Image interpretation
  NewMultimodal

  Released 2mo ago
• Gen 3 Step
  Step Image Edit 2

  By StepFun

  Step Image Edit 2 is StepFun’s lightweight unified image generation and editing model. It supports both text-to-image and image editing through API endpoints, runs with under 6B parameters, and is designed for fast 1 to 2 second responses in generation and editing workflows.

  📷Images🖼️Image generation🎨Visual imagery assistance
  NewMultimodal

  Released 2mo ago
• Gen 3
  SenseNova U1 8B MoT

  By SenseTime

  SenseNova-U1-8B-MoT is SenseNova’s open native multimodal model for unified image understanding, reasoning, generation, and editing. It is built on the NEO-Unify architecture, uses an 8B dense MoT backbone, and supports text-to-image, image-to-text, image editing, and interleaved image-text generation in one model.

  📷Images🖌️Image editing📊Infographics🤖Agents🔍Image interpretation
  Multimodal

  Released 3mo ago
• Gen 7
  LLaDA2.0 Uni

  By AntGroup

  LLaDA2.0-Uni is Inclusion AI’s unified multimodal diffusion MoE model for both image understanding and image generation. It is built on a dLLM backbone and supports text-to-image, image understanding, image editing, interleaved reasoning, and “thinking mode” image generation in one system.

  📷Images🖌️Image editing🔍Image interpretation
  Text

  Released 3mo ago
• Gen 3 GPT
  GPT Image 2.0

  By OpenAI

  ChatGPT Images 2.0 is OpenAI’s upgraded image generation and editing system in ChatGPT, powered by a new flagship image model. It is designed for faster, more precise image creation and photo editing, with stronger detail consistency, better intent matching, and support for preset styles and creative exploration directly inside ChatGPT.

  📷Images🖌️Image editing📊Infographics🔤Typography
  Multimodal

  Released 3mo ago
• Gen 4
  ImagineArt 2.0

  By ImagineArt

  ImagineArt 2.0 is ImagineArt’s latest proprietary image model, positioned as its top-tier option for photorealistic image generation. It is described as offering stronger prompt understanding, better composition control, higher detail fidelity, and more realistic results than the 1.5 family, with marketing also emphasizing working text rendering and fast concept-to-final generation.

  📷Images🖌️Image editing🖼️Portraits📸Photorealistic images🎥Cinematic photography
  Image

  Released 3mo ago
• Gen 4
  Anima Preview 3

  By CircleStone Labs

  Anima preview is a 2B text-to-image model from CircleStone Labs and Comfy Org focused on anime characters, anime styles, and other non-photorealistic illustration work. It is positioned as an intermediate preview checkpoint rather than a finished final release.

  🎨Anime images📷Images🎨Illustrations
  Image

  Released 3mo ago
• Gen 3 GLM
  GLM 5V Turbo

  By Z.ai

  Multimodal coding foundation model from Z.AI that natively processes images, video, and text. Built for vision-based coding tasks including frontend recreation, GUI autonomous exploration, and code debugging. Supports long-horizon planning, function calling, and agent workflows with a 200K context window and optional thinking mode.

  ‍💻Code generation📷Images🎥Videos💻Vibe coding❓Question answering
  Multimodal

  Released 3mo ago
• Gen 3 GPT
  GPT 5.4

  By OpenAI

  GPT-5.4 is OpenAI’s closed-source frontier model for professional work, focused on coding, reasoning, computer use, tool use, and long-context workflows. It supports up to about 1M tokens of context and is available through ChatGPT, API, and Codex.

  💬Chatting💻Coding📷Images
  Multimodal

  Released 4mo ago
• Gen 4
  Arrow 1

  By Quiver AI

  QuiverAI is a vector-graphics generation platform that creates editable SVG assets through an API, including text-to-SVG generation and image-to-SVG vectorization.

  📷Images🖼️Image generation
  Image

  Released 5mo ago
• Gen 3 Qwen
  Qwen 3.5 27B

  By Alibaba

  Qwen3.5-27B is a dense Qwen3.5 model size aimed at strong general performance in a smaller footprint than the flagship MoE variants.

  🖼️Image generation📷Images
  Multimodal

  Released 5mo ago
• Gen 3 Qwen
  Qwen 3.5 122B A10B

  By Alibaba

  Qwen3.5-122B-A10B is a larger Mixture-of-Experts Qwen3.5 model with 122B total parameters and 10B active per token, targeting higher peak capability while staying compute-efficient at inference.

  📷Images🎥Videos📚Stories
  Multimodal

  Released 5mo ago
• Gen 3 Qwen
  Qwen 3.5 35B A3B

  By Alibaba

  wen3.5-35B-A3B is a Mixture-of-Experts Qwen3.5 model with 35B total parameters and 3B active per token, built for strong capability with much lower active compute.

  🖼️Image generation💻Coding📝Writing📷Images
  Multimodal

  Released 5mo ago
• Gen 3 Qwen
  Qwen 3.5 Flash

  By Alibaba

  Qwen3.5-Flash is the speed and cost optimized Qwen3.5 variant designed for high-throughput chat and multimodal prompting with a very long context window.

  💬Chatting📷Images🎥Videos
  Multimodal

  Released 5mo ago
• Gen 3 Grok
  Grok 4.2

  By xAI

  Grok 4.2 is referenced as a Grok 4-series update for xAI’s Grok assistant, focused on general-purpose help across reasoning, coding, and real-time info retrieval inside the Grok experience.

  📷Images💻Coding📚Learning👗Fashion
  Multimodal

  Released 5mo ago
• Gen 3 Qwen
  Qwen3.5 397B A17B

  By Alibaba

  Qwen3.5-397B-A17B is a native vision-language model from Alibaba's Qwen team with 397B parameters (17B active per token). In the Qwen3.5-Plus hosted variant it supports up to 1M-token multimodal context, with strong reasoning, coding, and agentic tool use for large-scale deployment.

  🖼️Image generation💻Coding📷Images💬Chatting
  Multimodal

  Released 5mo ago
• Gen 4
  Ring 2.5 1T

  By InclusionAI

  Trillion-parameter “thinking” model described as using a hybrid linear attention architecture for long-horizon reasoning and exploration.

  📷Images
  Text

  Released 5mo ago
• Gen 4 Qwen
  Qwen Image 2.0 Pro

  By Alibaba

  Qwen-Image-2.0-Pro is Qwen’s higher-fidelity image generation and editing model for professional visual workflows. It is positioned as the premium tier of Qwen Image 2.0, focusing on richer detail, stronger prompt adherence, better structured text rendering, and higher-quality editing than the standard tier.

  📷Images🖌️Image editing
  Image

  Released 5mo ago
• Gen 2
  Ming Flash Omni 2.0

  By InclusionAI

  Ming-flash-omni 2.0 is an open sparse MoE omni-modal model that unifies text, image, video and audio understanding and generation, using a Ling-2.0 Mixture-of-Experts backbone with 100B parameters and about 6B active per token.

  🖼️Image generation🎵Music📷Images🎥Videos
  Multimodal

  Released 5mo ago
• Gen 3 Kling
  Kling 3.0

  By Kuaishou Technology

  Kling Video 3.0 is Kuaishou's newest AI video model that unifies text, image, audio and reference video in one engine, generating up to 15 second photorealistic clips with native multi-language audio and strong consistency across shots.

  🎥Videos📷Images📚Stories
  Multimodal

  Released 5mo ago
• Gen 3LongCat
  LongCat Flash Omni

  By Meituan

  560B parameter omni-modal MoE model (about 27B active) for real time audio-visual interaction, built on LongCat-Flash with multimodal perception and speech modules.

  🏋️Fitness📷Images💬Chatting🎥Videos
  Multimodal

  Released 5mo ago
• Gen 4 Grok
  Grok Imagine 1

  By xAI

  Grok Imagine is xAI’s video-audio generative model, exposed through the Imagine API, that turns text or images into cinematic videos and supports text-to-image, text-to-video, image-to-video and rich video editing with strong instruction following, latency and cost performance.

  🎥Videos📢Prompts📷Images👗Fashion
  Video

  Released 6mo ago
• Gen 4Earth
  Earth 2 Medium Range (Atlas architecture)

  By NVIDIA

  Earth-2 Medium Range is NVIDIA’s Atlas-based global forecast model that predicts over 70 weather variables up to 15 days ahead, outperforming leading open models like GenCast while running efficiently on GPUs.

  🌤️Weather forecasting🍔Food images📷Images📚Learning
  Image

  Released 6mo ago
• Gen 3 Kimi
  Kimi K2.5

  By Moonshot AI

  Kimi K2.5 is Moonshot’s native multimodal open model, trained on about 15T vision-text tokens to power advanced coding and visual reasoning and to orchestrate self-directed agent swarms with up to 100 sub-agents and 1,500 tool calls.

  💻Coding📝Writing📷Images🎥Videos
  Multimodal

  Released 6mo ago
• Gen 4 PixVerse
  PixVerse v5.6

  By Pixverse

  PixVerse V5.6 is PixVerse’s latest video model, upgrading V5.5 with cinema level visuals, more natural multilingual voices, smoother physics aware motion and less warping, while keeping generation speed and cost roughly the same as earlier V5 models.

  🎥Videos📷Images🔧Code optimization
  Video

  Released 6mo ago
• Gen 4
  Niji V7

  By Midjourney

  Niji V7 is Midjourney’s newest anime-first image model with improved anime coherence, prompt following, text rendering and reference-based character consistency for professional-grade illustrations and manga.

  🎨Anime images📷Images🧝‍♀️Fantasy images
  Image

  Released 6mo ago
• Gen 3
  Yuan 3.0 40B

  By YuanLab

  Yuan 3.0 Flash is a 40B MoE multimodal foundation model from YuanLab that activates about 3.7B parameters per token, targeting enterprise reasoning with lower compute per token.

  📷Images📞Customer support💻Coding📚Stories
  Multimodal

  Released 6mo ago
• Gen 4 FLUX
  FLUX.2 [dev] Turbo

  By Black Forest Labs

  FLUX.2 [dev] Turbo is Fal AI’s distilled Turbo LoRA for the FLUX.2-dev image model, cutting sampling to about 2-8 steps while preserving quality for fast text-to-image and image-edit generation.

  🖼️Image generation🖌️Image editing📷Images
  Image

  Released 6mo ago
• Gen 4
  Chenkin Noob XL

  By ChenkinNoob Team

  Chenkin Noob XL (CKXL) is a Stable Diffusion XL-class anime image checkpoint built on the Noob XL / noobai-XL-1.1 backbone, retrained on an extended Danbooru dataset through late 2025 to improve texture, lighting and style consistency.

  🎨Anime images📚Summaries📷Images🎨Cartoon images
  Image

  Released 7mo ago
• Gen 3 Seed
  Seed 1.8

  By ByteDance

  General-purpose agentic model that unifies LLM and VLM abilities with search, code execution and GUI control, designed to perceive text and images, reason over long contexts and autonomously carry out multi-step tasks.

  🤖Task automation💻Coding📷Images🎥Videos
  Multimodal

  Released 7mo ago
• Gen 7Gemma
  T5Gemma 2

  By Google DeepMind

  T5Gemma 2 is Google’s encoder-decoder Gemma model collection for input-heavy tasks such as summarization, translation, and deep text understanding.

  📷Images
  Text

  Released 7mo ago
• Gen 3 Wan
  Wan 2.6

  By Alibaba

  Wan 2.6 is Alibaba’s latest Wan AI multimodal video model, turning text, images, audio and short reference clips into up to 15 s 1080p videos with native audio sync, multi-shot storytelling, and strong character and style consistency.

  🎥Videos🖼️Image generation📷Images
  Multimodal

  Released 7mo ago