Model Library

Chooses the best model for your prompt & plan automatically.

Very intelligent model. Best for logos.

Smart powerful model for editing.

Fast model. Best for LoRAs.

Advanced yet efficent model from BFL.

BFL's highest quality text to image model.

Medium quality model for rendering text.

Fast lightweight Flux 2 model with reference image support

Frontier model by Black Forest Labs.

Medium quality model by Black Forest.

Black Forest Labs' multimodal FLUX model spanning image, video, and audio. Coming soon to Krea.

OpenAI image model available in Krea Image.

Open image model focused on design and text rendering.

Google's previous generation image model.

Google's current generation image model

Google's fastest image model

Google's best image model

Frontier model for complex image references.

Most creative model with LoRA's.

Krea image model for expressive, controllable visual generation.

Fastest medium quality Krea 2 model.

Reasoning image model for prompt-faithful text to image.

Most versatile intelligent model.

Cheaper quality version of Nano Banana.

Fast Google image model.

World's most intelligent model.

Affordable medium quality model.

Sharp, detailed images from Recraft with Standard and Pro modes.

Detail-rich image model with strong prompt adherence and text rendering.

Medium quality model for photorealism.

Medium quality model with reasoning and web search.

ByteDance's flagship image model with interactive editing, layer separation, and precise color control.

Fastest model. Realistic, low diversity.

Multimodal video with native audio.

Fast, high-quality video generation by xAI.

Text and image-to-video with native audio by xAI.

Cheapest medium-quality model.

MiniMax's next-generation Hailuo video model for cinematic, physics-aware motion.

Native audio and reference-guided generation.

Coming-soon Kling video model prepared for faster creative iteration workflows.

Frontier model with audio and up to 15s.

Fast text and image-to-video model with up to 15s outputs.

Intelligent model that thinks before generating.

Advanced reasoning model with references.

Advanced reasoning model, high-quality 1080p.

Affordable audio-video model from Lightricks.

High-quality audio-video model from Lightricks.

Frontier model with native text-to-video.

Medium-quality model with audio.

Flagship video model with native audio, references, and frame animation.

Faster Seedance 2 with native audio, references, and frame animation.

Cost-efficient Seedance 2 model for scalable video production.

ByteDance's most advanced AI video model with 30-second clips, 4K output, and up to 50 references.

Best video model. Highest quality with audio.

Faster, affordable Veo 3.1.

New model excelling at anime.

Fastest low-quality model with LoRA.

Fast, lower-quality model from Alibaba.

Medium-quality with multi-shot support.

Krea's custom video restyling model with a focus on control