README.md

---
language:
- en
pipeline_tag: text-to-image
library_name: diffusers
license: other
license_name: krea-2-community-license
license_link: https://huggingface.co/krea/Krea-2-Raw/blob/main/LICENSE.pdf
quantized_by: Abhishek Dujari
base_model_relation: quantized
widget:
- text: >-
    A small, dark-colored cat is captured mid-stride, walking down the center of
    a narrow, abandoned street. The street is paved and appears cracked and
    worn. On either side of the street are tall, dilapidated buildings with
    visible brickwork and windows. A street lamp stands on the right side. The
    entire image is rendered in a monochromatic blue, with a distinct halftone
    dot pattern overlaying the scene, giving it a retro or printed appearance.
    The focus is soft, and the lighting is diffused, creating a hazy,
    atmospheric effect. The perspective is from ground level, looking down the
    length of the street, which narrows into the distance., halftone texture
  output:
    url: images/00.png
- text: >-
    This is a digital illustration with a retro, pixelated aesthetic, depicting
    a young boy and a dog in an abstract indoor setting. The boy, with short
    brown hair and wearing a white t-shirt and dark shorts, is seated at a
    light-colored table. He is leaning over the table, looking down at papers or
    books. His face is rendered with a soft, somewhat blurry effect. To the
    right of the table, a tan, long-haired dog with large ears is lying on a red
    surface, possibly a rug or blanket. The dog's head is resting on the
    surface, and its eyes are closed, suggesting it is asleep. Its face is also
    rendered with a soft, somewhat distorted effect. The background features
    reddish-pink walls and a hint of a window or doorway on the left, with a
    hazy, abstract purple area. Scattered around the scene are various pixelated
    elements: a blue floppy disk icon, a yellow star icon, a green star icon, a
    blue thumbs-up icon, and a small black pixelated object near the boy's feet.
    The overall style is reminiscent of early computer graphics or video games,
    with a limited color palette and a focus on simple, blocky shapes. The
    composition is somewhat chaotic, with elements overlapping and a lack of
    clear spatial depth. The lighting is artificial and creates strong shadows,
    particularly on the table and the boy., low-poly 3D models
  output:
    url: images/03.png
- text: >-
    A young woman with fair skin and blonde hair styled in curls sits on the
    floor of a vast, empty opera hall. She is dressed in a fluffy, light pink
    tutu and a white lace shawl draped over her shoulders. Her legs are extended
    forward, and her hands rest on her lap. The opera hall features rows of
    empty, plush red velvet seats arranged in a circular pattern around a
    central floor area. Ornate balconies with decorative railings line the upper
    levels, and large, elaborate chandeliers hang from the high ceiling, casting
    a soft glow. The image has a soft, romantic, and slightly ethereal
    aesthetic, with a sense of grandeur and emptiness. The composition is
    centered on the woman, with the vastness of the opera hall surrounding her.
    The medium appears to be a painting, rendered with visible brushstrokes and
    a soft focus. The camera angle is a medium shot, slightly elevated, looking
    down towards the woman. The color palette is dominated by pastels,
    especially pinks, whites, and creams, with touches of deep red from the
    seats and gold from the chandeliers and ceiling. The lighting is soft and
    diffused, creating gentle shadows and highlights., impressionist painting,
    visible brushstrokes
  output:
    url: images/05.png
- text: >-
    A black and white photograph captures a male rockstar performing on stage,
    illuminated by a bright spotlight. He is holding a microphone to his open
    mouth, with his head tilted back and his right arm raised in a dynamic pose.
    His figure is rendered in high contrast, with sharp highlights and deep
    shadows. The background depicts a concert setting with a drum set and
    various amplifiers and speakers. The stage is bathed in intense light,
    creating a hazy, abstract effect. Silhouettes of an audience are visible in
    the distance, some with their hands raised. The overall style is gritty and
    energetic, with a dramatic composition focusing on the performer., thermal
    imaging style
  output:
    url: images/06.png
- text: >-
    A black and white photograph captures a solitary man standing on a wooden
    dock, facing away from the viewer and looking out at the vast expanse of the
    sea. He is wearing a full-length coat and a flat-rimmed hat. The man is
    silhouetted against the bright sky and water. The dock occupies the lower
    portion of the frame, with the sea stretching to the horizon. The image is
    composed with a low camera angle, emphasizing the scale of the sea and the
    isolation of the figure. The lighting creates strong contrasts, with the man
    and dock appearing as dark silhouettes against the lighter background.,
    black and white photography
  output:
    url: images/07.png
- text: >-
    An anime illustration depicts a young boy and girl walking through a lush
    forest. The boy, on the left, wears a white short-sleeved shirt, a dark tie,
    and a blue cap. He has short brown hair and looks to his right with a
    curious expression. The girl, on the right, wears a white dress with a blue
    collar and cuffs, and her brown hair is tied back. She carries a woven
    basket over her right shoulder and also looks to her right with an
    inquisitive gaze. The forest background is filled with green foliage and
    trees, with sunlight filtering through the leaves. Large rocks are scattered
    in the foreground, with a small brown bird perched on a rock to the left. To
    the right, a small brown monkey is visible climbing a tree. Red and yellow
    flowers add pops of color to the scene. The overall style is characteristic
    of traditional hand-drawn animation, with soft lighting and a natural color
    palette., whimsical woodland creatures
  output:
    url: images/13.png
- text: >-
    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
  output:
    url: images/18.png
- text: >-
    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.
  output:
    url: images/20.png
- text: >-
    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.
  output:
    url: images/21.png
- text: >-
    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.
  output:
    url: images/22.png
- text: >-
    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.
  output:
    url: images/23.png
- text: >-
    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.
  output:
    url: images/24.png
- text: >-
    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
  output:
    url: images/25.png
- text: >-
    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.
  output:
    url: images/27.png
- text: >-
    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.
  output:
    url: images/28.png
- text: >-
    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.
  output:
    url: images/29.png
- text: >-
    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.
  output:
    url: images/30.png
- text: >-
    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.
  output:
    url: images/32.png
- text: >-
    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.
  output:
    url: images/33.png
- text: >-
    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
  output:
    url: images/35.png
base_model:
- krea/Krea-2-Raw
---

# Krea 2 Text-to-Image Model

This is the Krea 2 Raw checkpoint, its not recommended for inference use. Its a good base for finetuning or post-training for your own needs and domains. For example, one use-case is to train LoRAs on midtrain and directly use them on Krea 2 Turbo. See our collection of in-house trained LoRAs trained on Raw and meant to be used with Turbo: [Krea-2 LoRA Collection](https://huggingface.co/collections/krea/krea-2-loras)

![Krea 2 sample outputs](images/header.jpg)

## Inference with the official codebase

1. Setup the official Krea 2 [codebase](https://github.com/krea-ai/krea-2)
2. Download `raw.safetensors` in this repo
3. `export OSS_RAW=<path-to-raw.safetensors>`
Run inference:
   ```bash
   uv run inference.py "a fox walking in the snow" \
    --checkpoint oss_raw --steps 52 --cfg 3.5 --width 1024 --height 1024
   ```

## Inference with diffusers

Install diffusers from source (for `Krea2Pipeline`):

```bash
pip install git+https://github.com/huggingface/diffusers.git
```

```python
import torch
from diffusers import Krea2Pipeline

pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Raw", torch_dtype=torch.bfloat16).to("cuda")
image = pipe("a fox in the snow", num_inference_steps=52, guidance_scale=3.5).images[0]
image.save("krea2.png")
```

## Inference with SGLang

Install SGLang from source (https://github.com/sgl-project/sglang)

From the CLI:
```bash
sglang generate --model-path krea/Krea-2-Raw \
    --prompt "a red fox sitting in fresh snow, golden hour, photorealistic" \
    --num-inference-steps 52 --height 1024 --width 1024 --guidance-scale 3.5 --save-output
```

See the full SGLang Krea 2 Cookbook [here](https://docs.sglang.io/cookbook/diffusion/Krea/Krea-2)

## Model Overview

- **Model Name:** Krea 2
- **Version:** v1.0
- **Release Date:** June 22, 2026
- **Model Type:** Text-to-image diffusion model
- **Architecture:** Diffusion Transformer with 12 billion parameters
- **License:** Krea 2 Community License
- **Release Format:** Open-weight release and Krea-hosted product integrations
- **Model Developer:** Krea.ai, Inc.

## Model Family and Release Checkpoints

This model card covers the Krea 2 model family, including the following release checkpoints:

- **Krea 2 Raw:** Base release checkpoint, prior to additional post-training and fine-tuning.
- **Krea 2 Turbo:** Post-trained release checkpoint with additional fine-tuning and distillation.

## Capabilities and Intended use

Krea 2 is a text-to-image diffusion model that generates images from natural-language text descriptions. The model is designed to support creative, commercial, developer, and research use cases, including image generation, concepting, design exploration, visual production workflows, and integration into applications and creative tools.

## Out-of-Scope Uses

This model is not intended or designed for uses that violate applicable law or regulations, infringe or misappropriate third-party rights, generate or facilitate unlawful or harmful content (including CSAM, NCII, harassment or defamation), or support fully automated decision-making that adversely affects legal rights of individuals. This summary is non-exhaustive. Use of Krea 2 is subject to the Krea 2 Community License Agreement and must comply with the Acceptable Use Policy. In the event of any conflict, the Krea Acceptable Use Policy and Krea 2 Community License control.

## Training Data

This model was developed using a combination of publicly available data, data licensed from third-party providers, and synthetic data generated through proprietary methods. The training data includes images and their associated captions or text descriptions.

Prior to training, data was filtered to remove certain categories of harmful content and reduce low-quality, duplicative, or irrelevant data. Krea also used curated and synthetic training data selected to improve prompt following, visual quality, and alignment with intended use cases.

## Safety Measures

We implemented safety measures across the full model development lifecycle. We applied targeted fine-tuning techniques to reduce the model's susceptibility to generating harmful content in response to both direct and adversarial prompts, and we conducted multiple rounds of internal and external safety evaluation before release.

For Krea's hosted products incorporating Krea 2, we deploy input and output classifiers using a combination of proprietary and third-party detection tools to flag or block policy-violating prompts and generated images.

Because this is also an open-weights release, Krea does not control downstream deployment of the model. Under the Krea 2 Community License, deployers are required to implement content filtering measures or equivalent review processes to prevent the generation or distribution of unlawful or policy-violating content appropriate to their use case. Deployers who fail to implement required safeguards are in breach of the license. See the license for details.

We conducted multiple rounds of internal and external safety evaluations before release, including adversarial testing designed to assess the model's resilience to attempts to elicit harmful or policy-violating outputs. Testing covered sexually explicit content, non-consensual intimate imagery, child-safety risks, and other high-risk content categories. Based on these evaluations, the release checkpoints demonstrated high resilience against violative inputs across the tested risk categories.

Krea maintains reporting channels for harmful, illegal, or policy-violating outputs at safety@krea.ai. Reports involving potential CSAM are escalated to NCMEC as required by law. Krea reserves the right to update model weights or revoke access in response to identified misuse patterns.

## Risks and Limitations

Krea 2 is a new technology and there are risks associated with its use. Testing conducted to date has not covered, nor could it cover, all possible scenarios. The model's potential outputs cannot be predicted in advance and may, in some instances, produce inaccurate, objectionable, or otherwise undesirable outputs.

This model is not intended to provide factual information. The model may fail to generate output that matches the prompt, and prompt following may be influenced by prompt style, specificity, language, and phrasing.

Before deploying any application using this model, developers should perform safety testing and tuning tailored to their specific application and must implement safeguards required by the Krea 2 Community License.

## License and Outputs

Krea does not claim copyright or other intellectual property rights over content generated by users of this model. Users are solely responsible for their outputs and any subsequent use of those outputs. As with other generative tools, the nature of a user's inputs influences the outputs produced, and prompts may produce images that implicate third-party rights. Users are solely responsible for assessing and addressing those risks. See the Krea 2 Community License for more information.

## Reporting

To report harmful, illegal, or policy-violating outputs generated by this model:

- **Email:** safety@krea.ai

Reports involving potential CSAM will be escalated to the National Center for Missing & Exploited Children (NCMEC) as required by law.

## Contact

- **General inquiries:** support@krea.ai
- **Safety and abuse:** safety@krea.ai
- **Model card version:** 1.0
- **Last updated:** June 22, 2026