FLUX 3 Image Klein is a 5.6B open weights image model from Black Forest Labs. One model handles text-to-image, editing with up to 10 reference images, and layout control with bounding boxes, at resolutions up to 4K.Originally released by <a target="_blank" rel="ugc" href="https://bfl.ai/models/flux-3-image-klein">Black Forest Labs</a> on Hugging Face. All credit for the model goes to the Black Forest Labs team. Civitai hosts a mirror so creators can generate with it on-site and train against it. Head to the <a target="_blank" rel="ugc" href="https://huggingface.co/black-forest-labs/flux-3-image-klein">original repo</a> for the reference code and updates.<h3>Two versions</h3><ul><li>Klein is the distilled model: 16 steps with no guidance, about 6x faster than Base. BFL recommends it for generation and editing.</li><li>Klein Base is the undistilled model: 50 steps at CFG 3.5. BFL recommends it for fine-tuning, LoRA training and research. LoRAs trained on Base can also be used on Klein, with partial compatibility.</li></ul><h3>Files</h3>Each version carries the diffusion model in bf16, int8 and nvfp4, from BFL's <a target="_blank" rel="ugc" href="https://huggingface.co/black-forest-labs/flux-3-image-klein-comfy">ComfyUI release</a>. The int8 files run on an 8 GB GPU (RTX 3070 class), and nvfp4 needs a Blackwell GPU. The text encoder and VAE ship in the ComfyUI repo.<h3>Generating on Civitai</h3>Both versions are in the Civitai generator for text-to-image and editing, with up to 10 reference images. Klein runs at fixed settings. Klein Base exposes steps, CFG and a negative prompt. Bounding-box layout is not in the generator yet.<h3>License</h3>FLUX 3 Image Klein is released under the <a target="_blank" rel="ugc" href="https://huggingface.co/black-forest-labs/flux-3-image-klein/blob/55d9cc2b0d33255ccd4fe1c9724bc3754de0ae96/LICENSE.md">FLUX Kommunity License</a>. The model and anything derived from it, including LoRAs and fine-tunes, are for non-commercial use, and derivatives must be shared under the same license. Users and companies with under US$5M in annual revenue may use the images they generate commercially. Larger commercial use needs a license from <a target="_blank" rel="ugc" href="https://bfl.ai/licensing">Black Forest Labs</a>.This FLUX Model is licensed by Black Forest Labs Inc. under the FLUX Kommunity License. Copyright Black Forest Labs Inc.<h3>Links</h3><ul><li><a target="_blank" rel="ugc" href="https://huggingface.co/black-forest-labs/flux-3-image-klein">FLUX 3 Image Klein</a></li><li><a target="_blank" rel="ugc" href="https://huggingface.co/black-forest-labs/flux-3-image-klein-base">FLUX 3 Image Klein Base</a></li><li><a target="_blank" rel="ugc" href="https://huggingface.co/black-forest-labs/flux-3-image-klein-comfy">ComfyUI files</a></li><li><a target="_blank" rel="ugc" href="https://bfl.ai/models/flux-3-image-klein">Black Forest Labs</a></li></ul>

Flux.3 Klein

qwen3vl_4b_bf16.safetensors

qwen3.5_9b_flux3_prompt_upsampler_int8_convrot.safetensors

flux3_image_klein_sd_nvfp4.safetensors

flux2-vae.safetensors

flux3_image_klein_sd_bf16.safetensors

qwen3vl_4b_int8_convrot.safetensors

flux3_image_klein_sd_int8_convrot.safetensors

Klein

Klein-Base

flux3_image_klein_int8_convrot.safetensors

flux3_image_klein_bf16.safetensors

flux3_image_klein_nvfp4.safetensors

Fibo-2.0-dev

text_encoder/model.safetensors

master

<img src="https://bria-public.s3.us-east-1.amazonaws.com/Bria-logo.svg" width="200"/>



 <a href="https://platform.bria.ai/"><img src="https://img.shields.io/badge/Bria-Platform-0EA5E9?style=for-the-badge"/></a>
 <a href="https://discord.com/invite/Nxe9YW9zHS"><img src="https://img.shields.io/badge/Discord-Join-5865F2?logo=discord&logoColor=white&style=for-the-badge"/></a>
 <a href="https://arxiv.org/abs/2511.06876"><img src="https://img.shields.io/badge/Tech%20Paper-lightgrey?logo=arxiv&logoColor=red&style=for-the-badge"/></a>


# Fibo 2.0 Edit Turbo

🏆 **#1 in image editing** among open-weights models on [Artificial Analysis](https://artificialanalysis.ai) (October 20, 2026).

**Fibo 2.0 image editing, in just a few steps.**

Fibo 2.0 is the next generation of Bria's FIBO family. For the first time, **image editing and image generation live in a single unified model**. It keeps the foundation that made FIBO the most controllable open image model: training on long, structured captions through the [Visual GenAI Language (VGL)](https://docs.bria.ai/vgl). On top of that foundation it adds high-quality, general-purpose editing and a leap in text rendering, texture and anatomy. Like every FIBO model, it is trained exclusively on licensed data.

**Fibo 2.0 Edit Turbo** is the distilled, production-ready **editing** model. It edits in 4 steps with no classifier-free guidance, so it delivers Fibo 2.0 editing quality at a fraction of the latency and cost. Turbo is for editing only: for text-to-image, use [Fibo 2.0 Dev](https://huggingface.co/briaai/Fibo-2.0-dev), which is also the model to fine-tune.

🚀 **Coming soon: multi-turn editing.** Chain edit after edit, each one building on the last, while the rest of the image stays pixel-stable.

---

## ✏️ Image Editing


 <img src="https://d1uqrfwi55x6ib.cloudfront.net/fibo-2.0-dev/assets/fibo2_edit_strip.jpg" width="100%"/>




---

## ✨ What's New in Fibo 2.0

| | |
|---|---|
| 🎯 **High-quality general editing** | Instruction-based edits that generalize across a wide range of tasks while preserving everything you didn't ask to change: identity, layout, lighting and fine detail. Masked and multi-reference edits are supported. |
| 🔤 **Better text, texture and anatomy** | Clear gains in legible in-image typography, realistic material and surface texture, and correct human anatomy (hands, faces, poses). |
| ⚡ **Dev and Edit Turbo variants** | **Edit Turbo** (this model) is distilled for few-step, low-latency image editing. **[Dev](https://huggingface.co/briaai/Fibo-2.0-dev)** is the full-quality base for generation and editing, built for professional fine-tuning and research. |
| 📐 **Still structured, still state of the art** | Still trained on structured captions, which gives Fibo 2.0 state-of-the-art prompt adherence and controllability among open models. |
| 🛡️ **Still 100% licensed** | Trained exclusively on licensed data, like every FIBO release. |

---

## 🛣️ Coming Soon

Fibo 2.0 is a platform, and we're already building on it:

| Release | What it does |
|---|---|
| 🔁 **Multi-Turn Local Editing LoRA** | Chain many localized edits in a row while the rest of the image stays pixel-stable, for true conversational editing. |
| ✂️ **Background Removal** | Clean, production-grade subject cutouts, built natively on Fibo 2.0. |
| 📦 **Product Shot LoRA** | Studio-quality product photography and placement for e-commerce and catalogs. |
| 🧽 **Eraser by Mask** | Paint a mask and remove any object, with seamless, context-aware fill. |
| 🖼️ **Image Expansion** | Extend images beyond their borders (outpainting) to any aspect ratio, with a coherent continuation of the scene. |

Follow [Bria on Hugging Face](https://huggingface.co/briaai) and join our [Discord](https://discord.com/invite/Nxe9YW9zHS) to be the first to know.

---

## 🌍 What's Fibo?

Most image models excel at imagination but not at control. FIBO was built for professional workflows. It was trained on structured JSON captions of up to 1,000+ words that describe lighting, composition, color, camera and depth of field explicitly. This gives the model **native disentanglement**: you can change one attribute, such as the camera angle, the time of day or a subject's outfit, without the rest of the scene drifting.

Fibo 2.0 applies the same principle to editing. An edit is a precise, structured change to a visual blueprint, not a loose text prompt, so the results are **explicit, interpretable and repeatable**.

### 📐 The VGL Paradigm

Fibo 2.0 is natively built on **[Visual GenAI Language (VGL)](https://docs.bria.ai/vgl)**. VGL replaces vague natural-language descriptions with explicit JSON that both humans and machines can read. Lighting, composition, style, camera parameters and every object in the scene are separate, addressable fields. Generation becomes "render this blueprint," and editing becomes "apply this diff to the blueprint."

You never have to write JSON by hand. [`bria-vgl`](https://github.com/Bria-AI/vgl), the same open-source package behind Bria's API, turns plain-language edit instructions into full structured prompts for you. To write or check captions yourself, see the [VGL caption guide](https://huggingface.co/briaai/Fibo-2.0-dev/blob/main/vgl/README.md).

---

## 🎨 Editing Workflows

| Mode | Input | What happens |
|---|---|---|
| **Edit** ✨ | Source image + instruction | Add, remove or replace objects, or change style, lighting, background, materials or text. Everything you didn't ask to change is preserved. |
| **Masked edit** ✨ | Source image + mask + instruction | The edit is confined to the masked region, and the rest of the image is left untouched. |
| **Multi-reference** ✨ | Up to 4 reference images + instruction | Information from every reference is combined into one result, for reference-guided composition, virtual try-on, product integration, and style or appearance transfer. |

---

## 🔑 Key Features

- **Few-step editing.** Edits in 4 steps with no classifier-free guidance, cutting latency and cost for interactive and high-volume editing pipelines.
- **High-fidelity editing.** Strong preservation of identity, structure and untouched regions across a wide range of edit types, with native mask and multi-reference support.
- **Structured JSON control.** Define images and edits with explicit parameters (lighting, composition, camera, style) for deterministic, reproducible results.
- **Enterprise-grade.** 100% licensed training data, with governance, attribution traceability and legal clarity for commercial use.
- **Built for production.** At 8B parameters, it balances high-fidelity output with efficiency. Available as open weights, API endpoints and ComfyUI nodes.

---

## 📊 Evaluation



🏆 **#1 in image editing** among open-weights models on the [Artificial Analysis](https://artificialanalysis.ai) Image Arena.


 <img src="https://d1uqrfwi55x6ib.cloudfront.net/fibo-2.0-dev/assets/benchmarks/aa_image_editing_v2.1.png" width="60%"/>


Rankings as of October 20, 2026.

---

## ⚡ Quick Start

| | Image editing |
|---|---|
| 🚀 **Try it now** | [Edit sandbox](https://platform.bria.ai/image-editing/fibo-image-edit/sandbox) |
| ⚡ **Fal.ai** | [bria/fibo-2/edit](https://fal.ai/models/bria/fibo-2/edit) |
| 🤗 **Hugging Face Space** | [Fibo-2.0-editing](https://huggingface.co/spaces/briaai/Fibo-2.0-editing) |

**Bria API:** [docs.bria.ai](https://docs.bria.ai/) · **Bria Create:** [create.bria.ai](https://create.bria.ai/)

**ComfyUI:** [Bria ComfyUI nodes](https://github.com/Bria-AI/ComfyUI-BRIA-API) · **Agents:** [Bria agent skill](https://github.com/Bria-AI/bria-skill)

**License:** Creative Commons Attribution–Non-Commercial (CC BY-NC 4.0) 
The model is released under a CC BY-NC 4.0 license for non-commercial use. 
Commercial use is subject to a commercial agreement with BRIA. Available [here](https://platform.bria.ai/licensing/pricing?model=fibo-2).

### Installation

[`bria-vgl`](https://github.com/Bria-AI/vgl) writes the structured prompts, with the same prompts and model as the Bria API and fal endpoints.

```bash
pip install -U "diffusers>=0.42.0" torch torchvision transformers accelerate
```

Install `bria-vgl` with pip or uv:

```bash
pip install bria-vgl
# or
uv add bria-vgl
```

`bria-vgl` runs on Gemini; set your key ([get one here](https://aistudio.google.com/apikey)):

```bash
export GEMINI_API_KEY="your-api-key"
```

> ⚡ **Few-step distilled model.** Use `num_inference_steps=4` and `guidance_scale=1.0`. `negative_prompt` has no effect. This checkpoint is **not intended for fine-tuning**; start from [Fibo 2.0 Dev](https://huggingface.co/briaai/Fibo-2.0-dev) instead.

### Setup

Fibo 2.0 reads structured VGL captions. `bria-vgl`'s `modify()` turns images plus a plain-language instruction into one: the caption of the result, with its `edit_instruction`.

```python
import json
import torch
from PIL import Image
from diffusers import BriaFibo2Pipeline
from huggingface_hub import hf_hub_download
from bria_vgl import modify
from bria_vgl.dialects.thales import EditImages, EditImageWithMask

pipe = BriaFibo2Pipeline.from_pretrained("briaai/Fibo-2.0-edit-turbo", dtype=torch.bfloat16).to("cuda")
# On Hopper GPUs (H100), FlashAttention-3 is faster:
# pipe.transformer.set_attention_backend("_flash_3_varlen_hub")

# Fibo 2.0 sees each text in the caption drawn as a small image.
fonts = [hf_hub_download("briaai/Fibo-2.0-edit-turbo", name, subfolder="fonts") for name in ("Aileron-Regular.otf", "DejaVuSans.ttf")]


# bria-vgl's scene as the JSON prompt the pipeline reads
def vgl(scene) -> str:
 return json.dumps(scene.model_dump(exclude_none=True), ensure_ascii=False)
```

### Edit

```python
source = Image.open("photo.jpg").convert("RGB")
scene = modify(EditImages(prompt="replace the jacket with a red leather one", images=[source]), seed=0)
print(scene.edit_instruction) # the instruction, rewritten in the form Fibo 2.0 was trained on

edited = pipe(prompt=vgl(scene), image=source, num_inference_steps=4, guidance_scale=1.0, fonts=fonts).images[0]
edited.save("edited.png")
```


 <img src="https://d1uqrfwi55x6ib.cloudfront.net/fibo-2.0-dev/assets/edit/red_jacket.png" width="100%"/>


### Masked edit

White marks the region to regenerate; everything else is kept. The mask goes to both `bria-vgl` and the pipeline.

```python
source = Image.open("suitcase.png").convert("RGB")
mask = Image.open("suitcase_mask.png").convert("L") # same size as the source
scene = modify(EditImageWithMask(prompt="replace the suitcase with a vintage brown leather one", image=source, mask=mask), seed=0)
edited = pipe(prompt=vgl(scene), image=source, mask=mask, num_inference_steps=4, guidance_scale=1.0, fonts=fonts).images[0]
```


 <img src="https://d1uqrfwi55x6ib.cloudfront.net/fibo-2.0-dev/assets/edit/masked_suitcase.png" width="100%"/>


### Multiple references

Up to 4 images, referred to in order as `<image_1>`, `<image_2>`, and so on.

```python
references = [Image.open("person.png").convert("RGB"), Image.open("dress.png").convert("RGB")]
scene = modify(EditImages(prompt="dress the person in <image_1> in the dress from <image_2>", images=references), seed=0)
result = pipe(prompt=vgl(scene), image=references, num_inference_steps=4, guidance_scale=1.0, fonts=fonts).images[0]
```


 <img src="https://d1uqrfwi55x6ib.cloudfront.net/fibo-2.0-dev/assets/edit/multiref_dress.png" width="100%"/>


---

## 🧠 Training and Architecture

Fibo 2.0 is an **8B-parameter flow-matching model** operating in the latent space of the **FLUX.2 VAE**. Prompts are encoded by **Qwen3-VL-4B-Instruct**, and context images for editing are encoded by both the VLM and the VAE. A two-layer Perceiver resampler compresses the VLM output into **256–512 "gist" tokens**, with more tokens for longer prompts. These are prepended to the image tokens (the noisy latent and, when editing, the clean context latents) and processed by a **single-stream DiT with 44 blocks**. Internal VLM layers also feed five of those blocks directly through cross-attention.

Fibo 2.0 Edit Turbo is distilled from [Fibo 2.0 Dev](https://huggingface.co/briaai/Fibo-2.0-dev) for few-step, guidance-free editing, with the same architecture. 

**Data:** trained exclusively on licensed data, curated from Bria's ~1B-image dataset and paired with long, structured captions.

---

FIBO is inspired by the Fibonacci sequence, where math meets beauty through the golden ratio, nature's and design's timeless key to harmony.

If you have questions, feedback or want to contribute, we welcome your discussions and pull requests in this model's [Community tab](https://huggingface.co/briaai/Fibo-2.0-edit-turbo/discussions). If you're passionate about fundamental research, we're hiring full-time employees and research interns. Reach out to us at hr@bria.ai.

## Citation

```bibtex
@article{gutflaish2025generating,
 title={Generating an Image From 1,000 Words: Enhancing Text-to-Image With Structured Captions},
 author={Gutflaish, Eyal and Kachlon, Eliran and Zisman, Hezi and Hacham, Tal and Sarid, Nimrod and Visheratin, Alexander and Huberman, Saar and Davidi, Gal and Bukchin, Guy and Goldberg, Kfir and others},
 journal={arXiv preprint arXiv:2511.06876},
 year={2025}
}
```

Fibo-2.0-edit-turbo

Files with SHA256: f0b24fc5c8d7c0ea6ca909da14c20af5cac53f22506be942c6c956f838b9630f