Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,59 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+LICENSE.pdf filter=lfs diff=lfs merge=lfs -text
+tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+images/00.png filter=lfs diff=lfs merge=lfs -text
+images/01.png filter=lfs diff=lfs merge=lfs -text
+images/02.png filter=lfs diff=lfs merge=lfs -text
+images/03.png filter=lfs diff=lfs merge=lfs -text
+images/04.png filter=lfs diff=lfs merge=lfs -text
+images/05.png filter=lfs diff=lfs merge=lfs -text
+images/06.png filter=lfs diff=lfs merge=lfs -text
+images/07.png filter=lfs diff=lfs merge=lfs -text
+images/08.png filter=lfs diff=lfs merge=lfs -text
+images/09.png filter=lfs diff=lfs merge=lfs -text
+images/10.png filter=lfs diff=lfs merge=lfs -text
+images/11.png filter=lfs diff=lfs merge=lfs -text
+images/12.png filter=lfs diff=lfs merge=lfs -text
+images/13.png filter=lfs diff=lfs merge=lfs -text
+images/14.png filter=lfs diff=lfs merge=lfs -text
+images/15.png filter=lfs diff=lfs merge=lfs -text
+images/header.png filter=lfs diff=lfs merge=lfs -text
+images/00.jpg filter=lfs diff=lfs merge=lfs -text
+images/01.jpg filter=lfs diff=lfs merge=lfs -text
+images/02.jpg filter=lfs diff=lfs merge=lfs -text
+images/03.jpg filter=lfs diff=lfs merge=lfs -text
+images/04.jpg filter=lfs diff=lfs merge=lfs -text
+images/05.jpg filter=lfs diff=lfs merge=lfs -text
+images/06.jpg filter=lfs diff=lfs merge=lfs -text
+images/07.jpg filter=lfs diff=lfs merge=lfs -text
+images/08.jpg filter=lfs diff=lfs merge=lfs -text
+images/09.jpg filter=lfs diff=lfs merge=lfs -text
+images/10.jpg filter=lfs diff=lfs merge=lfs -text
+images/11.jpg filter=lfs diff=lfs merge=lfs -text
+images/12.jpg filter=lfs diff=lfs merge=lfs -text
+images/13.jpg filter=lfs diff=lfs merge=lfs -text
+images/14.jpg filter=lfs diff=lfs merge=lfs -text
+images/15.jpg filter=lfs diff=lfs merge=lfs -text
+images/header.jpg filter=lfs diff=lfs merge=lfs -text
+images/16.jpg filter=lfs diff=lfs merge=lfs -text
+images/17.jpg filter=lfs diff=lfs merge=lfs -text
+images/18.jpg filter=lfs diff=lfs merge=lfs -text
+images/19.jpg filter=lfs diff=lfs merge=lfs -text
+images/20.jpg filter=lfs diff=lfs merge=lfs -text
+images/21.jpg filter=lfs diff=lfs merge=lfs -text
+images/22.jpg filter=lfs diff=lfs merge=lfs -text
+images/23.jpg filter=lfs diff=lfs merge=lfs -text
+images/24.jpg filter=lfs diff=lfs merge=lfs -text
+images/25.jpg filter=lfs diff=lfs merge=lfs -text
+images/26.jpg filter=lfs diff=lfs merge=lfs -text
+images/27.jpg filter=lfs diff=lfs merge=lfs -text
+images/28.jpg filter=lfs diff=lfs merge=lfs -text
+images/29.jpg filter=lfs diff=lfs merge=lfs -text
+images/30.jpg filter=lfs diff=lfs merge=lfs -text
+images/31.jpg filter=lfs diff=lfs merge=lfs -text
+images/32.jpg filter=lfs diff=lfs merge=lfs -text
+images/33.jpg filter=lfs diff=lfs merge=lfs -text
+images/34.jpg filter=lfs diff=lfs merge=lfs -text
+images/35.jpg filter=lfs diff=lfs merge=lfs -text

LICENSE.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b82a2805162bde714a4eb27b9063c4fc3345d08a30be055134a6160e5430ba74
+size 137711

README.md

@@ -0,0 +1,350 @@
+---
+language:
+- en
+base_model:
+- krea/Krea-2-Raw
+pipeline_tag: text-to-image
+library_name: diffusers
+license: other
+license_name: krea-2-community-license
+license_link: https://huggingface.co/krea/Krea-2-Turbo/blob/main/LICENSE.pdf
+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.jpg
+- 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.jpg
+- 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.jpg
+- 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.jpg
+- 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.jpg
+- 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.jpg
+- 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.jpg
+- 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.jpg
+- 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.jpg
+- 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.jpg
+- 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.jpg
+- 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.jpg
+- 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.jpg
+- 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.jpg
+- 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.jpg
+- 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.jpg
+- 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.jpg
+- 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.jpg
+- 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.jpg
+- 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.jpg
+---
+
+# Krea 2 Text-to-Image Model
+
+![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 `turbo.safetensors` in this repo
+3. `export OSS_TURBO=<path-to-turbo.safetensors>`
+Run inference:
+   ```bash
+   uv run inference.py "a fox walking in the snow" \
+    --checkpoint oss_turbo --steps 8 --cfg 0.0 --mu 1.15 --width 2048 --height 2048
+   ```
+
+## 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-Turbo", torch_dtype=torch.bfloat16).to("cuda")
+image = pipe("a fox in the snow", num_inference_steps=8, guidance_scale=0.0).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-Turbo \
+    --prompt "a red fox sitting in fresh snow, golden hour, photorealistic" \
+    --num-inference-steps 8 --height 1024 --width 1024 --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

model_index.json

@@ -0,0 +1,41 @@
+{
+  "_class_name": "Krea2Pipeline",
+  "_diffusers_version": "0.39.0.dev0",
+  "_name_or_path": "./tmp_model",
+  "is_distilled": true,
+  "patch_size": 2,
+  "scheduler": [
+    "diffusers",
+    "FlowMatchEulerDiscreteScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "Qwen3VLModel"
+  ],
+  "text_encoder_select_layers": [
+    2,
+    5,
+    8,
+    11,
+    14,
+    17,
+    20,
+    23,
+    26,
+    29,
+    32,
+    35
+  ],
+  "tokenizer": [
+    "transformers",
+    "Qwen2Tokenizer"
+  ],
+  "transformer": [
+    "diffusers",
+    "Krea2Transformer2DModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKLQwenImage"
+  ]
+}

quantization_info.json

@@ -0,0 +1,9 @@
+{
+  "quantization_method": "mixed_precision_nf4",
+  "model_type": "krea",
+  "description": "First and last blocks plus boundary modules kept at bfloat16, middle layers quantized to NF4 (krea architecture)",
+  "high_precision_layers_count": 56,
+  "removed_stale_checkpoint_indexes": [
+    "transformer/diffusion_pytorch_model.safetensors.index.json"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "FlowMatchEulerDiscreteScheduler",
+  "_diffusers_version": "0.39.0.dev0",
+  "base_image_seq_len": 256,
+  "base_shift": 0.5,
+  "invert_sigmas": false,
+  "max_image_seq_len": 6400,
+  "max_shift": 1.15,
+  "num_train_timesteps": 1000,
+  "shift": 1.0,
+  "shift_terminal": null,
+  "stochastic_sampling": false,
+  "time_shift_type": "exponential",
+  "use_beta_sigmas": false,
+  "use_dynamic_shifting": true,
+  "use_exponential_sigmas": false,
+  "use_karras_sigmas": false
+}

text_encoder/config.json

@@ -0,0 +1,81 @@
+{
+  "architectures": [
+    "Qwen3VLModel"
+  ],
+  "dtype": "bfloat16",
+  "image_token_id": 151655,
+  "model_type": "qwen3_vl",
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "dtype": "bfloat16",
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 2560,
+    "initializer_range": 0.02,
+    "intermediate_size": 9728,
+    "max_position_embeddings": 262144,
+    "model_type": "qwen3_vl_text",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 36,
+    "num_key_value_heads": 8,
+    "pad_token_id": null,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        24,
+        20,
+        20
+      ],
+      "rope_theta": 5000000,
+      "rope_type": "default"
+    },
+    "tie_word_embeddings": true,
+    "use_cache": true,
+    "vocab_size": 151936
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.12.1",
+  "video_token_id": 151656,
+  "vision_config": {
+    "deepstack_visual_indexes": [
+      5,
+      11,
+      17
+    ],
+    "depth": 24,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1024,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "model_type": "qwen3_vl_vision",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 2560,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be7235ff7d69b135e483a94133a090ae2005b6ffad818b72ea3ec5dcc1af4dff
+size 2874030922

tokenizer/chat_template.jinja

@@ -0,0 +1,120 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' }}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+    {%- if message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content_item in message.content %}
+                {%- if 'text' in content_item %}
+                    {{- content_item.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and message.content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

tokenizer/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

tokenizer/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

transformer/config.json

@@ -0,0 +1,103 @@
+{
+  "_class_name": "Krea2Transformer2DModel",
+  "_diffusers_version": "0.39.0.dev0",
+  "_name_or_path": "./tmp_model/transformer",
+  "attention_head_dim": 128,
+  "axes_dims_rope": [
+    32,
+    48,
+    48
+  ],
+  "in_channels": 64,
+  "intermediate_size": 16384,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 48,
+  "num_key_value_heads": 12,
+  "num_layers": 28,
+  "num_layerwise_text_blocks": 2,
+  "num_refiner_text_blocks": 2,
+  "num_text_layers": 12,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": [
+      "img_in",
+      "time_embed.linear_1",
+      "time_embed.linear_2",
+      "time_mod_proj",
+      "text_fusion.projector",
+      "txt_in.linear_1",
+      "txt_in.linear_2",
+      "final_layer.linear",
+      "text_fusion.layerwise_blocks.0.attn.to_q",
+      "text_fusion.layerwise_blocks.0.attn.to_k",
+      "text_fusion.layerwise_blocks.0.attn.to_v",
+      "text_fusion.layerwise_blocks.0.attn.to_gate",
+      "text_fusion.layerwise_blocks.0.attn.to_out.0",
+      "text_fusion.layerwise_blocks.0.ff.gate",
+      "text_fusion.layerwise_blocks.0.ff.up",
+      "text_fusion.layerwise_blocks.0.ff.down",
+      "text_fusion.layerwise_blocks.1.attn.to_q",
+      "text_fusion.layerwise_blocks.1.attn.to_k",
+      "text_fusion.layerwise_blocks.1.attn.to_v",
+      "text_fusion.layerwise_blocks.1.attn.to_gate",
+      "text_fusion.layerwise_blocks.1.attn.to_out.0",
+      "text_fusion.layerwise_blocks.1.ff.gate",
+      "text_fusion.layerwise_blocks.1.ff.up",
+      "text_fusion.layerwise_blocks.1.ff.down",
+      "text_fusion.refiner_blocks.0.attn.to_q",
+      "text_fusion.refiner_blocks.0.attn.to_k",
+      "text_fusion.refiner_blocks.0.attn.to_v",
+      "text_fusion.refiner_blocks.0.attn.to_gate",
+      "text_fusion.refiner_blocks.0.attn.to_out.0",
+      "text_fusion.refiner_blocks.0.ff.gate",
+      "text_fusion.refiner_blocks.0.ff.up",
+      "text_fusion.refiner_blocks.0.ff.down",
+      "text_fusion.refiner_blocks.1.attn.to_q",
+      "text_fusion.refiner_blocks.1.attn.to_k",
+      "text_fusion.refiner_blocks.1.attn.to_v",
+      "text_fusion.refiner_blocks.1.attn.to_gate",
+      "text_fusion.refiner_blocks.1.attn.to_out.0",
+      "text_fusion.refiner_blocks.1.ff.gate",
+      "text_fusion.refiner_blocks.1.ff.up",
+      "text_fusion.refiner_blocks.1.ff.down",
+      "transformer_blocks.0.attn.to_q",
+      "transformer_blocks.0.attn.to_k",
+      "transformer_blocks.0.attn.to_v",
+      "transformer_blocks.0.attn.to_gate",
+      "transformer_blocks.0.attn.to_out.0",
+      "transformer_blocks.0.ff.gate",
+      "transformer_blocks.0.ff.up",
+      "transformer_blocks.0.ff.down",
+      "transformer_blocks.27.attn.to_q",
+      "transformer_blocks.27.attn.to_k",
+      "transformer_blocks.27.attn.to_v",
+      "transformer_blocks.27.attn.to_gate",
+      "transformer_blocks.27.attn.to_out.0",
+      "transformer_blocks.27.ff.gate",
+      "transformer_blocks.27.ff.up",
+      "transformer_blocks.27.ff.down",
+      "norm",
+      "norm1",
+      "norm2",
+      "norm_q",
+      "norm_k"
+    ],
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rope_theta": 1000.0,
+  "text_hidden_dim": 2560,
+  "text_intermediate_size": 6912,
+  "text_num_attention_heads": 20,
+  "text_num_key_value_heads": 20,
+  "timestep_embed_dim": 256
+}

transformer/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d216777aa4dd1187f35a21dcf5b88da2692969ed5de1e544b3ced5dfdfed1381
+size 8890150227