Krea 2
Free Krea 2 Turbo image generator online
Krea 2 is Krea AI’s own image model, trained from scratch for pictures that don’t look AI-made: film photography, fashion, anime and painterly illustration. The open Turbo version draws in 8 steps at up to 2K. Run it here with no ComfyUI and no GPU, then animate the result in the same box.
- Open weights
- About 12B single-stream DiT
- 8-step Turbo
- 1K and 2K output
- Krea 2 Large too
- Image to video in one click
Sexually explicit (NSFW) content is strictly prohibited.
Krea 2 Turbo is selected. Short prompts are expanded into a detailed caption first, the way Krea’s own workflow does it. Krea 2 Large and the other image and video models are in the same list.
What is Krea 2?
Krea 2 is the first image foundation model Krea AI trained entirely in-house. It arrived in two steps. On May 12, 2026 Krea launched the hosted models on krea.ai: Krea 2 Large, the most detailed and photographic, and Krea 2 Medium, faster and leaning towards illustration, later joined by Medium Turbo. In late June 2026 Krea released open weights: Krea 2 RAW and Krea 2 Turbo.
Under the hood it is a single-stream diffusion transformer of about 12 billion parameters (12.9B by ComfyUI’s count), reading prompts through a Qwen3-VL text encoder and decoding with the Qwen Image VAE. Krea says no AI-generated images went into its pre-training data, which is part of why its pictures avoid the glossy, over-smoothed look.
Its strengths are taste and range: believable skin and film grain, fashion editorials, anime and cel art, ink, gouache and collage. It also takes style references and style LoRAs. Testers note it can miss details in crowded multi-object prompts, and it is not an editing model.
Krea 2 is not FLUX
It was trained from scratch, not built on FLUX. It is also unrelated to FLUX.1 Krea, the model Krea made with Black Forest Labs in 2025.
Large and Medium are not open
Only RAW and Turbo have downloadable weights. Large and Medium run on krea.ai and through API partners such as fal, which is how Dolai serves Large.
Text to image only
The open release makes images from text. “Krea 2 edit” searches are about community LoRAs or Krea’s newer tools, not an official edit model.
Krea 2 examples with prompts
Forty-six images Krea AI and its API partners published with their prompts: Krea’s own prompting guide, its nine style LoRAs, and Large and Medium examples. Copy a prompt, or press Use this prompt to load it into the box above.
immense rocket launch exhaust as seen from extremely close up
Source: Krea AI on GitHub
3D rendered matte black designer toy figure, stylized round anthropomorphic shape, backward black baseball cap, oversized gold-rimmed aviator sunglasses, white traditional line-art tattoos of tiger and bird on torso, black studded belt with gold buckle, smooth vinyl texture, studio lighting, solid vibrant blue background, high contrast minimal composition
Source: Krea AI on GitHub
vintage analog collage, central irregularly shaped snowy mountain range with a section featuring distinct wavy edges, structured within a 12x16 grid of square tiles, composition fragments the subject by alternating tiles with solid azure blue background squares, thin white grid lines, grainy paper texture, retro aesthetic of mid-century print, vibrant cyan and warm neutral tones, experimental layout, tactile quality, high-contrast graphic composition
Source: Krea AI on GitHub
close-up anime portrait of a young woman, large amber-brown eyes with intricate sparkling reflections, index finger delicately touching a subtle smile, messy dark blue hair with loose strands crossing her face, white and navy school uniform, bright high-key lighting, luminous shadows with cool blue undertones, detailed digital painting, dynamic tilted framing, shallow depth of field on hand
Source: Krea AI on GitHub
A minimalist flat-color illustration of a person wading through expansive shallow ocean waves beneath a pale peach sky. The dark-skinned figure, wearing an orange swim cap, light blue top, and bright green shorts, steps carefully through knee-deep water. The ocean is rendered in muted mint green with delicate, thin black linework detailing the continuous ripples and gentle whitecaps. Soft pinkish-peach reflections echo the sky on the water's surface. A dark, jagged rock rests in the lower left foreground near a pale grey shoreline. The horizon features a solid purplish-blue landmass and a stylized, layered yellow and blue cloud. The high-angle wide perspective emphasizes the vast negative space of the water, utilizing a clean ligne claire drawing aesthetic with a subtle paper texture.
Source: Krea AI on GitHub
A tiny figure and a small white dog sit side-by-side in the deep green shadow of a massive tree on a sloping grassy hill. The enormous tree canopy dominates the upper composition, textured with thousands of stippled, light blue and yellow dabs representing leaves. A sharp diagonal line divides the vibrant, sunlit yellow-green grass in the foreground from the dark shade sheltering the pair. The stylized, painterly landscape features flattened perspective, visible brushstrokes, and intense color contrast.
Source: Krea AI on GitHub
A close-up portrait of a young East Asian woman with straight black hair, loose strands sweeping across her fair skin, and an intense gaze. She wears a light grey collared shirt with a black tie. A vibrant bouquet of pink and orange lilies with lush green leaves sits in the blurred right foreground. The background is a solid, striking crimson red. Soft, directional studio lighting highlights her facial features, creating a high-contrast composition with a shallow depth of field.
Source: Krea AI on GitHub
A tiny, russet-brown harvest mouse clings to a slender diagonal branch amid vibrant green lobed leaves and small round buds. The mouse has soft textured fur, glossy black eyes, a pink nose, fine whiskers, and delicate pink paws firmly gripping the wood. In this macro photograph, an extremely shallow depth of field sharply focuses on the animal's face. The deep green background dissolves into a smooth, creamy bokeh, illuminated by soft, diffused natural lighting that highlights the intricate details of the fur and foliage.
Source: Krea AI on GitHub
A dynamic digital painting of a joyful girl in a sailor uniform stretching her arms high against a solid vibrant blue background. She has short dark windblown hair, amber eyes, and a bright smile. She wears a white shirt, striped blue collar, flowing red neckerchief, and a billowing blue pleated skirt. Expressive thick brushstrokes and bold shading emphasize energetic motion.
Source: Krea AI on GitHub
stylized digital painting of a dark convertible on a winding coastal cliff road, high-angle perspective, blocky painterly brushstrokes, golden hour sunlight hitting rocky orange terrain and green vegetation, flock of white abstract birds flying in foreground, blinding bright sun reflection on vast ocean, vibrant warm color palette, sharp graphic shadows
Source: Krea AI on GitHub
An extreme low-angle close-up captures a colossal, weathered stone and bronze guardian towering in a dark, cavernous ruin. The foreground is dominated by a massive circular shield, deeply engraved with intricate spiral motifs, geometric borders, and a central star emblem. To the right, a massive gauntlet grips a textured staff. Cinematic shafts of light pierce the dusty gloom, highlighting the rough, aged textures of the ancient armor while the background fades into deep shadows through a shallow depth of field.
Source: Krea AI on GitHub
A stylized jungle illustration densely packed with oversized flora and surreal characters, rendered with smooth geometric shapes and granular stippled shading. Two pale figures with flowing, star-speckled black hair navigate the lush environment in blue garments. On the left, a figure grasps a vine as a white, long-beaked bird perches on their outstretched hand. On the right, the second figure reclines beside a sleek, pinkish-orange fox. The dense surroundings feature sweeping green stalks and colossal blooms in brilliant golden yellow, coral pink, and deep red. A second white bird emerges from the lower foliage. The vibrant composition forms a seamless tapestry, utilizing rich colors and volumetric grain to create a dreamlike, textured depth.
Source: Krea AI on GitHub
A surreal retro-futuristic space scene features liquid chrome forming an abstract face merging with a glowing planetary horizon. The foreground is dominated by swirling, highly reflective metallic fluid that distorts into a stylized, melting facial profile with deep shadows and bright silver highlights. This undulating chrome form rests against the curved, atmospheric edge of a massive planet bathed in a soft electric blue and purple glow. Above the primary planet, a smaller eclipsed celestial sphere sits in the upper center, crowned by a sharp, cross-shaped starburst flare. Two additional radiant flares burst from the left and right edges of the horizon. Set against a deep black starfield, the artwork employs a vintage 1980s airbrush aesthetic with smooth gradients, ethereal lighting, and high-contrast metallic rendering.
Source: Krea AI on GitHub
An extreme close-up portrait featuring pale, freckled skin and a single blue eye wrapped in reflective metallic gold ribbons. Thin gold strips crisscross diagonally over the cheek and forehead, casting sharp, hard shadows onto the face. Strands of copper hair frame the top edge while the left ear softly blurs out of focus. Harsh, direct lighting highlights intricate skin pores and bright golden reflections, isolating the brightly lit features against a pitch-black background in a bold, high-contrast macro editorial style.
Source: Krea AI on GitHub
Stylized digital painting of a menacing jester figure rendered with bold, expressive brushstrokes and a vibrant, almost psychedelic color palette against a pitch-black background. Dynamic low-angle perspective forces a dramatic, imposing composition as the character leans forward, one leg raised high. The jester wears a classic multi-pointed hat with bells, a ruffled collar, puffed sleeves, harlequin-patterned shorts in muted gold and dark brown, and striped tights in alternating shades of purple, blue, and chartreuse. A heavily textured, flowing cape billows outward to the left, decorated with abstract, fluid patterns of saturated purples, greens, and iridescent hues resembling oil slicks or marbled paper. The figure's face is completely obscured, appearing as a smooth, faceless, pale mauve mask with a single, glowing bright white point of light in the center. In its right hand, clad in a grey-blue gauntlet, the jester grips a massive, ornate sword with a wide, glowing, ethereal white blade, its crossguard intricately sculpted. Lighting is dramatic and theatrical, casting strong shadows and highlighting the painterly texture, giving the artwork a dark fantasy, surreal aesthetic reminiscent of concept art.
Source: Krea AI on GitHub
high-fashion editorial portrait of a young East Asian woman, short choppy platinum blonde bob with heavy bangs, looking over her bare shoulder to the right, lips playfully pursed, wearing a structured black top with an architectural protruding bust detail and thin straps, delicate gold hoop earrings, arm bent with hand resting on hip, warm skin tones, solid striking crimson red background, soft directional studio lighting, cinematic color palette, medium close-up shot
Source: Krea AI on GitHub
A surreal black-and-white ink illustration of three interlocking, heavily wrinkled elderly faces merging into a landscape. The top face covers one eye, crowned by dense leaves, a live bird, and a skeletal bird. It flows into a profile face and a third face featuring a solid black eye and a hand on its cheek. The bottom neck plunges into a cross-section of earth, morphing into swirling subterranean roots, buried bones, and abstract organic forms. Above ground, weathered wooden cabins and tall grass flank the facial monolith. Meticulous stippling and cross-hatching define the high-contrast, intricate vertical composition.
Source: Krea AI on GitHub
1990s vintage anime style cel animation, densely packed crowd of teenagers in summer uniforms, central boy with short black hair raising a clenched right fist, squinting one eye with a determined expression, wearing a white short-sleeve shirt and solid green necktie, surrounding students looking in various directions, girls in white sailor blouses with green striped collars and neckerchiefs, light blue skirts and trousers, tightly framed medium shot, flat shading, soft muted retro.
Source: Krea AI on GitHub
young woman looking over her right shoulder, anime-style illustration, messy black hair blowing dynamically in the wind, striking green eyes, subtle neutral expression, oversized white button-down collared shirt with soft blue shadows, vibrant deep blue sky background, bright fluffy white cumulus clouds, silhouetted utility poles with power lines, low angle portrait, cinematic sunlight, crisp cel-shaded aesthetic
Source: Krea AI on GitHub
extreme close-up of a woman's face partially obscured by tousled dark brown hair, soft parted lips, smooth skin on lower cheek and jawline, stray hair strands falling loosely across the nose, deep moody shadows enveloping the left frame, cinematic warm lighting, delicate highlights on the mouth, muted earthy color palette, sepia-toned warmth, intimate portrait photography, macro lens, shallow depth of field, distinct film grain texture, vintage atmospheric aesthetic
Source: Krea AI on GitHub
two samurais in flowing robes doing a muay thai fight, one throws a high kick while the other leans back. monochrome ink wash style
Source: Krea AI on Hugging Face
A sorcerer in flowing midnight robes stands atop a cliff edge, arms raised as crackling energy gathers between his palms. The sky roils with energy, flowing down from the sky. monochrome ink wash style
Source: Krea AI on Hugging Face
two samurais in flowing robes doing a muay thai fight, one throws a high kick while the other leans back. Monochrome stippling style
Source: Krea AI on Hugging Face
A sunset over snowy mountains. Monochrome stippling style
Source: Krea AI on Hugging Face
two samurais in flowing robes doing a muay thai fight, one throws a high kick while the other leans back. naive expressive sketch style
Source: Krea AI on Hugging Face
A skateboarder doing a kickflip at blue hour, a puddle reflects the skateboarder. naive expressive sketch style
Source: Krea AI on Hugging Face
two samurais in flowing robes doing a muay thai fight, one throws a high kick while the other leans back. Textured abstract style
Source: Krea AI on Hugging Face
A close-up portrait of a woman, glowing neon highlights and vivid paint dripping down her face. Textured abstract style
Source: Krea AI on Hugging Face
two samurais in flowing robes doing a muay thai fight, one throws a high kick while the other leans back. rainy window style
Source: Krea AI on Hugging Face
A skateboarder doing a kickflip at blue hour, a puddle reflects the skateboarder. rainy window style
Source: Krea AI on Hugging Face
two samurais in flowing robes doing a muay thai fight, one throws a high kick while the other leans back. Purple retro anime style
Source: Krea AI on Hugging Face
A sorcerer in flowing midnight robes stands atop a cliff edge, arms raised as crackling energy gathers between his palms. The sky roils with energy, flowing down from the sky. Purple retro anime style
Source: Krea AI on Hugging Face
two samurais in flowing robes doing a muay thai fight, one throws a high kick while the other leans back. Art Deco watercolor style
Source: Krea AI on Hugging Face
an angel with metallic wings and a crown of flowers. Art Deco watercolor style
Source: Krea AI on Hugging Face
two samurais in flowing robes doing a muay thai fight, one throws a high kick while the other leans back. ethereal motion blur style
Source: Krea AI on Hugging Face
A sunset over snowy mountains. ethereal motion blur style
Source: Krea AI on Hugging Face
two samurais in flowing robes doing a muay thai fight, one throws a high kick while the other leans back. vintage tarot style
Source: Krea AI on Hugging Face
A sorcerer in flowing midnight robes stands atop a cliff edge, arms raised as crackling energy gathers between his palms. The sky roils with energy, flowing down from the sky. vintage tarot style
Source: Krea AI on Hugging Face
Expressive street portrait of a model in vintage layering and bold accessories against a colorful wall, celebratory aesthetic, saturated palette, warm lighting, joyful contemporary energy, dynamic editorial portraiture, vibrant presence
Source: fal.ai
a corgi puppy sipping coffee at a parisian cafe
Source: fal.ai
Playful avant-garde editorial of a model in a balloon-like inflated nylon suit against a bright monochrome backdrop, bold aesthetic, glossy lighting, vivid palette, surreal pop futurism, immaculate graphic composition, witty fashion innovation
Source: fal.ai
Over-the-shoulder tracking shot of a model walking with exaggerated runway gait — torso twisted unnaturally to look directly back at the camera, fur coat trailing, one arm wrapped around their own neck, platform boots planted wide, sickly green fluorescents, magenta shadows, hypnotic motion blur
Source: fal.ai
The text "Krea 2 Large" in the center middle in large serif font. A color film-inspired portrait of a young woman looking to the left, shallow depth of field. She is looking out a school bus window. The fine grain and cast suggest a high ISO film stock, while the wide aperture lens creates a motion blur effect, enhancing the candid and natural documentary style.
Source: Replicate
The text "Krea 2 Medium" positioned in the dead center, in large helvetica font. An authentic, candid film portrait of a young woman, captured on high-ISO analog stock. Rich textures, fine film grain, and a subtle vintage color cast. A wide-open aperture creates a shallow depth of field, dissolving the background into creamy bokeh and pulling all focus to the expression in her eyes.
Source: Replicate
The text "Krea 2" positioned in the dead center, in large helvetica font. An authentic, candid film portrait of a young woman, captured on high-ISO analog stock. Rich textures, fine film grain, and a subtle vintage color cast. A wide-open aperture creates a shallow depth of field, dissolving the background into creamy bokeh and pulling all focus to the expression in her eyes. There is a golden hour glow with glints of rainbow bokeh.
Source: Replicate
The text "Krea 2 Medium" positioned in the dead center, in large helvetica font. An authentic, candid film portrait of a young woman, captured on high-ISO analog stock. Rich textures, fine film grain, and a subtle vintage color cast. A wide-open aperture creates a shallow depth of field, dissolving the background into creamy bokeh and pulling all focus to the expression in her eyes.
Source: ReplicateStyle LoRA samples end with the LoRA’s trigger phrase, such as “monochrome ink wash style”. On Dolai the prompt runs on plain Krea 2 Turbo, so the trigger phrase steers the look in words rather than loading the LoRA.
One prompt, thirteen styles
Krea 2’s other talent is borrowing a look. Every image in this strip comes from the same prompt, “Male cowboy riding horse through the desert, close up shot”, with a different style reference image each time: flat graphics, line art, watercolour, painterly brushwork and film.
The open Turbo model takes up to three reference images through Krea’s style reference adapter, and Krea publishes nine style LoRAs (Dark Brush, Dot Matrix, Kids Drawing, Neon Drip, Rainy Window, Retro Anime, Soft Watercolor, Sunset Blur and Vintage Tarot). The box on this page runs Krea 2 as text to image: describe the style in your prompt and Krea 2 follows it closely.
Krea 2 Turbo, RAW, Medium and Large
Four versions share the name. Two are open weights, two are Krea’s hosted models, and each has its job.
| Krea 2 Turbo | Krea 2 RAW | Krea 2 Medium | Krea 2 Large | |
|---|---|---|---|---|
| Weights | Open download | Open download | Hosted only | Hosted only |
| What it is | Distilled, 8 steps, no CFG | Undistilled base, about 52 steps, CFG 3.5 | Faster hosted model | Flagship hosted model |
| Best for | Everyday images | Training LoRAs and fine-tunes | Illustration and anime | Photographic detail |
| Output | 1K to 2K | Up to about 1K | 1K | 1K |
| On Dolai | Available | Not served | Not served | Available |
Krea’s motto for the open pair is “train on RAW, run on Turbo”: a LoRA trained on RAW is meant to be used with Turbo. On Dolai, Krea 2 Turbo costs 5 credits per image at 1K and 17 at 2K; Krea 2 Large costs 30.
How to write Krea 2 prompts
Write sentences, not tags
Krea 2 was trained on long natural-language captions. Say what is in the frame, where, in what light, and through what camera or medium, as in the guide prompts above.
Short prompts are fine here
Under about 300 characters, Dolai has the prompt expanded into a full caption before Krea 2 draws, as Krea’s ComfyUI template does. Long prompts go in as written.
Quote the words to show
Put any text that should appear in the image in quotes and say where it goes, like the “Krea 2 Large” film portraits.
Skip negative prompts
Turbo runs without classifier-free guidance, so negative prompts do nothing. Say what you want instead.
Running Krea 2 locally
The open weights are on Hugging Face (krea/Krea-2-Turbo and krea/Krea-2-Raw) and ComfyUI supports them natively from version 0.25.0: download the Turbo model, the Qwen3-VL 4B text encoder and the Qwen Image VAE, open the Krea 2 template and sample at 8 steps. Community figures put the full BF16 model at about 24 GB of VRAM and the FP8 or INT8 builds at about 12 GB, with GGUF files going lower.
No GPU, or no time to set it up? The box at the top of this page runs Krea 2 Turbo in the cloud. Create with Krea 2
From a Krea 2 image to a video
Krea 2 makes stills. To make one move, switch the box above to Video, attach the image as the first frame and describe the motion. Seedance 2.5 keeps the face, outfit and grain of the still and adds camera movement and sound.
Krea 2’s film portraits and fashion frames make strong first frames: the look is already there, so the video only has to move it.
What people make with Krea 2
Fashion and editorial
Lookbook frames, campaign moods and editorial portraits with real fabric and skin.
Film-look photography
Grain, halation and muted colour that read as analog, not as AI.
Anime and illustration
Cel-shaded scenes, character close-ups, ink, gouache and flat colour.
Product and 3D
Designer toys, packaging and studio product shots for listings and pitches.
Concept art and mood boards
Fast 8-step drafts to explore a look before a shoot or a build.
Short videos
A Krea 2 still as the first frame of a Seedance clip, in the same box.
How to use Krea 2 online
- 1
Describe the image
Write what you want to see, or press Use this prompt on any example above.
- 2
Pick a model and size
Krea 2 Turbo is selected, at 1K or 2K; switch to Krea 2 Large for the hosted flagship. The price is on the button.
- 3
Create, then animate
The image opens in the studio, where you can download it, adjust the prompt, or bring it back here as the first frame of a video.
Krea 2 FAQ
What is Krea 2?
Krea 2 is Krea AI’s own text-to-image model, trained from scratch. The hosted Large and Medium versions launched on krea.ai on May 12, 2026, and the open-weight RAW and Turbo versions followed in late June 2026.
Can I use Krea 2 online for free?
Yes. The box at the top of this page runs Krea 2 Turbo in the cloud, with nothing to install. An image costs 5 credits at 1K and 17 at 2K, and new accounts get 100 free credits to start.
Do I need ComfyUI or a GPU to use Krea 2?
Not on Dolai: the model runs on hosted GPUs and you only write the prompt. To run the open weights yourself you need ComfyUI 0.25.0 or later and an NVIDIA GPU; community figures suggest about 12 GB of VRAM for the FP8 or INT8 builds.
What is the difference between Krea 2 Turbo and RAW?
Turbo is distilled to draw in 8 steps without guidance and is the one for making images, at 1K to 2K. RAW is the undistilled base, slow at about 52 steps, and meant for training LoRAs and fine-tunes. Krea sums it up as “train on RAW, run on Turbo”.
Is Krea 2 Large open source?
No. Large and Medium are Krea’s hosted models; only RAW and Turbo are open weights. Dolai runs Large through an API partner, at 30 credits per 1K image.
Can I use Krea 2 images commercially?
Krea does not claim copyright in what the model makes. The open weights come under the Krea 2 Community License, which allows commercial use but requires companies with US$1 million or more in annual revenue, affiliates included, to buy an enterprise license from Krea. Check the license for your own case.
Is Krea 2 based on FLUX?
No. Krea trained Krea 2 from scratch, with a Qwen3-VL text encoder and the Qwen Image VAE. It is a different model from FLUX.1 Krea, which Krea built with Black Forest Labs in 2025.
Can Krea 2 edit images?
The open release is text to image only. It can borrow the style of reference images, but it does not change an existing photo. Community editing LoRAs exist for RAW.
Can I turn a Krea 2 image into a video?
Yes. Switch the box at the top of this page to Video, attach your Krea 2 image as the first frame and describe the motion. Seedance 2.5 animates it with camera movement and sound.
Is Dolai made by Krea AI?
No. Dolai is an independent AI studio that runs Krea 2 through a hosted API, alongside image and video models from Google, OpenAI, ByteDance, Black Forest Labs and others. Krea 2 is developed and released by Krea AI.
Try Krea 2 now
Film-grade looks in 8 steps, with nothing to install, and a video one click away.
Create with Krea 2Dolai is not affiliated with Krea AI. Krea 2 is developed and released by Krea AI. The examples on this page were published by Krea AI, fal.ai and Replicate, and link to their sources.
Related tools
Other Dolai pages that open the same studio, set up for a different job.
- FLUX.3 KleinRun Black Forest Labs’ FLUX 3 Image Klein online, up to 4K.
- MOSS ImageRun OpenMOSS’s open-source image model online, no ComfyUI needed.
- Dola AI Image to VideoTurn one photo into a Seedance 2.5 video.
- Seedream 5.5Preview ByteDance’s next image model and create with Seedream today.
- AI video modelsEvery video model on Dolai, with what it costs.