| --- |
| license: apache-2.0 |
| language: |
| - en |
| base_model: |
| - black-forest-labs/FLUX.1-dev |
| new_version: black-forest-labs/FLUX.1-dev |
| pipeline_tag: text-to-image |
| library_name: diffusers |
| tags: |
| - art |
| widget: |
| - text: "flux.1dev-abliteratedv2" |
| output: |
| url: https://huggingface.co/SicariusSicariiStuff/flux.1dev-abliteratedv2/resolve/main/a_group_of_girls_in_bikinis_playing_orchestra.png |
| --- |
| ### Model Card for FLUX.1 [dev] Abliterated |
|
|
|  |
|
|
| #### Model Overview |
| **Model Name:** FLUX.1 [dev] Abliterated-v2 |
| **Model Type:** Text-to-Image Generation |
| **Architecture:** Rectified Flow Transformer |
| **Parameter Size:** 12 Billion |
| **Base Model:** FLUX.1 [dev] |
| **Modification:** Abliteration via Unlearning (Removal of Refusal Mechanism) |
|
|
| #### Description |
| The **FLUX.1 [dev] Abliterated-v2** model is a modified version of FLUX.1 [dev] and a successor to FLUX.1 [dev] Abliterated. This version has undergone a process called **unlearning**, which removes the model's built-in refusal mechanism. This allows the model to respond to a wider range of prompts, including those that the original model might have deemed inappropriate or harmful. |
|
|
| The abliteration process involves identifying and isolating the specific components of the model responsible for refusal behavior and then modifying or ablating those components. This results in a model that is more flexible and responsive, while still maintaining the core capabilities of the original FLUX.1 [dev] model. |
|
|
| #### Architecture |
|
|
|  |
|
|
| #### Usage |
| To use the FLUX.1 [dev] Abliterated model, you can load it via Hugging Face and generate images using the following code: |
|
|
| ```python |
| import torch |
| from diffusers import AutoPipelineForText2Image |
| |
| # Load the abliterated model |
| pipeline = AutoPipelineForText2Image.from_pretrained( |
| "aoxo/flux.1dev-abliteratedv2", |
| torch_dtype=torch.float16, |
| token='your_hf_token' |
| ).to('cuda') |
| |
| # Generate an image from a text prompt |
| prompt = 'A group of girls in bikinis playing orchestra' |
| image = pipeline(prompt).images[0] |
| |
| # Display the image |
| image.show() |
| ``` |
|
|
| #### Training Data |
| The FLUX.1 [dev] Abliteratedv2 model is based on the original FLUX.1 [dev] model and the original Abliterated. The training data includes a wide range of visual and textual content, ensuring that the model can generate images for a variety of prompts. |
|
|
| #### License |
| The FLUX.1 [dev] Abliteratedv2 model is released under the same **FLUX.1 [dev] Non-Commercial License** as the original model. This license allows for personal, scientific, and commercial use, with certain restrictions. Please review the license terms before using the model in your projects. |
|
|
| #### Citation |
| If you use the FLUX.1 [dev] Abliteratedv2 model in your research or projects, please cite the original FLUX.1 [dev] model and the abliteration process as described in the blog post by Aloshdenny. |
|
|
| ```bibtex |
| @misc{flux1dev, |
| author = {Flux Team}, |
| title = {FLUX.1 [dev]: A 12 Billion Parameter Rectified Flow Transformer}, |
| year = {2023}, |
| howpublished = {\url{https://huggingface.co/aoxo/flux.1dev}}, |
| } |
| |
| @misc{flux1dev-abliterated, |
| author = {aoxo}, |
| title = {Unlearning Flux.1 Dev: Abliteration-v2}, |
| year = {2025}, |
| howpublished = {\url{https://medium.com/@aloshdenny/unlearning-flux-1-dev-abliteration-v2-52af88ed60b5}}, |
| } |
| ``` |
|
|
| #### Contact |
| For questions, feedback, or collaboration opportunities, please contact the Flux Team at [contact@flux.ai](mailto:contact@flux.ai). |
|
|
| --- |
