KI-Modelle
auf Morphic

Kling 4.0

Kling

Kuaishou's next Kling video model, expected within weeks. Longer clips and higher fidelity than before, in the next major Kling release.

Seedream 5.0 Pro

ByteDance

Seedream 5.0 Pro is ByteDance's image model for grounded, region-precise editing, multi-layer separation, high-density infographics, and native text in 14 languages.

Nano Banana 2 Lite

Google DeepMind

Google DeepMind's Gemini 3.1 Flash-Lite Image on Morphic. Nano Banana 2 Lite generates 1K images in about four seconds, with character consistency, legible in-image text, world knowledge for layouts, edits, and multi-image composition.

Seed Audio 1.0

ByteDance

ByteDance's all-in-one audio model: generates voice, instrumental music, and sound effects together in a single pass, with zero-shot voice cloning and multi-speaker dialogue.

Seedance 2.0 4K

ByteDance

ByteDance's Seedance 2.0 now generates at native 4K on Morphic. Crisp detail and clean texture held across motion, plus multimodal input, native audio, and controllable camera moves.

Seedance 2.5

ByteDance

Seedance 2.5 is ByteDance's next-generation video model: up to 30 seconds of native single-shot video, up to 50 multimodal references, stronger in-clip editing, and 720p to 4K output.

Happy Horse 1.1

Alibaba

Alibaba's joint audio-video model on Morphic. Happy Horse 1.1 generates video and synchronized audio in a single pass, with native multilingual lip-sync, reference-to-video for up to 9 subjects, and nine aspect ratios.

Kling 3.0 Turbo

Kling

Kuaishou's speed-tuned Kling video model on Morphic. Kling 3.0 Turbo keeps strong prompt adherence and multi-shot consistency while generating quickly at 720p and 1080p.

Seedance 2.0 Mini

ByteDance

ByteDance's lightweight Seedance 2.0 tier. Multimodal image, video and audio references, up to 1080p, at about half the price of Seedance 2.0.

Ideogram 4.0

Ideogram

Ideogram's open-weight image model. Frontier in-image text, bounding-box layout control, structured JSON prompts, and 2K output under a commercial license.

Reve 2.0

Reve AI

Reve AI's layout-first image model, also called Reve Image 2. Place elements by hand, edit a result like a design file, and render crisp text at up to 4K.

Bernini

ByteDance

ByteDance's open-source unified model for AI video editing and generation. Add, remove, or restyle elements in a clip with locked consistency, plus subject-to-video that holds identity.

Grok Imagine v1.5

xAI

xAI's image-to-video model on Morphic. Turn a still image into a clip with native synchronized audio, lip-synced dialogue, sound effects, and music, plus strong prompt following and video extension.

Veo 4

Google DeepMind

Google DeepMind's next-generation video model. Veo 4 pushes past the 8-second window of Veo 3.1 with longer native 4K clips, locked multi-shot characters, storyboard sequencing, cinematic camera language, and multi-speaker native audio.

MAI-Image-2.5

Microsoft

Microsoft's text-to-image model on Morphic. MAI-Image-2.5 launches at No. 3 on the Arena text-to-image leaderboard with sharper text rendering, stylized illustration, and commercial imagery built for design and brand work.

Gemini Omni

Google DeepMind

Google's any-to-any multimodal model on Morphic. Gemini Omni Flash turns text, images, audio, and video into a single video, with consistent characters, accurate physics, conversational editing, and SynthID watermarking.

Recraft V4.1 Pro

Recraft

Recraft's flagship raster tier, rebuilt around quieter photoreal, dreamier gradients, and a model that reads short prompts the way a creative director would. 2K native output, design-grade composition.

Krea 2

Krea AI

Krea AI's first foundation image model on Morphic, built from scratch for aesthetics and creative control. Style transfer from references, moodboards, creativity control, and a range that runs from grainy film to clean studio photoreal.

Happy Horse 1.0

Alibaba

Alibaba's video model that generates joint video and audio in a single pass. Native lip-sync across 7 languages, 1080p output, reference-driven control, and #1 Elo on the Artificial Analysis Video Arena at launch.

ChatGPT Images 2.0

OpenAI

OpenAI's image model with native reasoning, up to 2K output, multi-image batches with character continuity, and strong multilingual text rendering for diagrams, posters, and design work.

Gemini 3.1 Flash TTS

Google DeepMind

Google's most expressive text-to-speech model on Morphic. Gemini 3.1 Flash TTS turns text into natural, directable narration with inline audio tags, multi-speaker dialogue, and SynthID watermarking across many languages.

Sync V3

Sync

Sync's flagship lip-sync model. Sync V3 (sync-3) generates flicker-free 4K lip-sync with shot-level understanding, obstruction handling, and extreme-angle support.

Wan 2.7

Alibaba

Alibaba's flagship Wan video model with Thinking Mode prompt reasoning, cinematic 1080p output, and reference-driven character consistency across shots.

LTX 2.3

Lightricks

Lightricks' open-source audio-visual video model. LTX 2.3 generates synced video and audio in a single pass, with native vertical output up to 4K.

Nano Banana 2

Google DeepMind

Google DeepMind's Gemini 3.1 Flash Image. Pro-level image generation at Flash speed: subject consistency across up to 5 characters and 14 objects, real-time web grounding, accurate text rendering, and resolutions up to 4K.

Kling 3.0

Kling

Kuaishou's prompt-first flagship video model. Kling 3.0 (V3) delivers photorealistic motion, multi-shot Director Mode, and native multilingual audio in native 1080p and 4K at 30fps.

Recraft V4 Pro

Recraft

Recraft's higher-resolution raster image model, rebuilt around design taste, refined anatomy, balanced composition, and editorial detail at 2K native output.

Seedream 5.0 Lite

ByteDance

ByteDance's reasoning-first image model. Seedream 5.0 Lite combines deep-thinking generation with built-in online search so prompts tied to current events render with live context.

Qwen Edit Angles

Alibaba Qwen

Alibaba's Qwen-Image-Edit multi-angle model. Generate the same subject from different camera perspectives with consistent geometry, lighting, and identity, from a single input image.

Seedance 1.5 Pro

ByteDance

ByteDance's native audio-visual video model. Seedance 1.5 Pro generates synced video and audio in one pass with multilingual lip-sync and cinematic camera control.

Seedream 4.5

ByteDance

ByteDance's upgraded image model with stronger prompt adherence, multi-image reference handling, and dense-text rendering, unifying text-to-image and image editing in one model.

Seedance 2.0

ByteDance

ByteDance's next-generation multimodal AI video model, supports images, videos, audio and text inputs simultaneously. Delivers hyper-realistic motion, controllable camera movements, native audio synthesis, music beat sync, and seamless video extension with up to 12 assets per generation.

Flux 2 Pro

Black Forest Labs

Black Forest Labs' premium AI image generation model delivering the highest quality output with superior detail, color accuracy, and prompt adherence for professional applications.

Gemini Image Pro

Google

Google's premium multimodal image generation model with the highest quality output, advanced text rendering, and deep world knowledge for professional-grade AI imagery.

Nano Banana Pro

Google DeepMind

Google DeepMind's Gemini 3 Pro Image. Studio-quality image generation and editing with subject consistency, professional text rendering, web-grounded accuracy, and resolutions up to 4K across 14 aspect ratios.

Hailuo 2.3

MiniMax

MiniMax's latest AI video model with enhanced visual quality, improved motion coherence, and superior prompt understanding, the next evolution of cinematic AI video.

Wan 2.6

Alibaba

Alibaba's open-source AI video generation model delivering high-quality text-to-video and image-to-video with strong prompt adherence and diverse style capabilities.

Veed Fabric 1.0

Veed

Veed's talking-video model. Fabric 1.0 takes one still image plus an audio file and generates a talking video with synced lips, head, body, and hand motion.

Vidu Q3

Shengshu Technology

Shengshu Technology's latest AI video model with enhanced visual quality, improved motion coherence, and superior generation capabilities over Vidu Q2.

Veo 3.1

Google DeepMind

Google DeepMind's state-of-the-art video generation model delivering photorealistic output with industry-leading physics accuracy, native audio synthesis, and 4K resolution.

Sora

OpenAI

OpenAI's groundbreaking AI video generation model capable of creating imaginative, high-quality video from text prompts with strong understanding of 3D space, physics, and creative storytelling.

Kling O3

Kling

Kling's flagship AI video model with the broadest feature set, text-to-video, image-to-video, video-to-video, frames-to-video, motion control, and reference-based generation.

Kling

Kling

Kling's standard AI video model (v2.6 Pro) for text-to-video and image-to-video generation with strong stylization capabilities and reliable quality.

Topaz Image

Topaz Labs

Professional-grade AI image upscaling by Topaz Labs, up to 4x resolution enhancement with intelligent detail recovery, noise reduction, and artifact removal.

Topaz Video

Topaz Labs

Professional-grade AI video upscaling by Topaz Labs, upscale video resolution up to 4x with frame interpolation, stabilization, and detail enhancement.

Gemini Image

Google

Google's multimodal AI model with native image generation capabilities, combining advanced language understanding with high-quality visual output for integrated text-and-image creation.

Crystal Image

Morphic

Fast, efficient AI image upscaling, up to 4x resolution enhancement with excellent quality-to-speed ratio for everyday image enhancement workflows.

Crystal Video

Morphic

Fast, efficient AI video upscaling, enhance video resolution up to 4x with frame interpolation and excellent processing speed for everyday video enhancement.

Z-Image Turbo

fal.ai

Lightning-fast AI image generation optimized for speed, sub-second generation times for rapid prototyping, high-volume workflows, and instant visual exploration.

Grok Imagine

xAI

xAI's powerful cross-modal AI model generating both images and videos from text, with image editing, video transformation, and five distinct generation modes.

Runway Gen-4 Aleph

Runway

Runway's flagship text-to-video AI model delivering cinematic-quality output with exceptional character consistency, emotional performance, and professional storytelling capabilities.

Seedance

ByteDance

ByteDance's AI video model excelling in expressive character animation, dance choreography, and human motion with native audio support and multi-input generation.

Hailuo-02

MiniMax

MiniMax's standard AI video generation model known for cinematic aesthetics, natural motion quality, and strong prompt understanding for text-to-video and image-to-video.

Seedream

ByteDance

ByteDance's high-quality AI image generation model delivering vibrant, detailed output with strong text-to-image and image-to-image capabilities up to 2K resolution.

Kontext

Black Forest Labs

Black Forest Labs' AI image editing model that modifies existing images using natural language, change elements, swap backgrounds, and edit compositions while preserving the original style.

Runway Gen-4 Image

Runway

Runway's latest AI model for generating cinematic-quality video from static images, exceptional character consistency, realistic motion, and professional storytelling.

GPT Image 1.5

OpenAI

OpenAI's advanced AI image generation model with accurate text rendering, exceptional instruction following, and sophisticated image editing capabilities.

Vidu Q2

Shengshu Technology

Shengshu Technology's AI video generation model delivering high-fidelity text-to-video and image-to-video with strong visual coherence and reference-based generation.

Kling Motion Control

Kling

Kling's specialized camera motion control model for AI video, specify precise camera movements, trajectories, and cinematic shots in your generated videos.

Kling O1

Kling

Kling's specialized video-to-video AI model for editing, transforming, and restyling existing footage with AI-powered visual effects and style transfer.

Flux

Black Forest Labs

Black Forest Labs' fast AI image generation model delivering versatile, high-quality images across photorealistic, artistic, and graphic styles with rapid generation times.

Luma Dream Machine

Luma AI

Luma AI's fast and capable video generation model known for speed, visual quality, and consistent scene rendering across diverse styles and subjects.

ElevenLabs

ElevenLabs

Industry-leading AI audio platform, text-to-speech, text-to-music, text-to-sound-effects, and AI dialogue with human-quality voice synthesis and comprehensive audio production.