Instructions to use InsecureErasure/FLUX.2-small-decoder-BF16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use InsecureErasure/FLUX.2-small-decoder-BF16 with Diffusion Single File:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
| license: apache-2.0 | |
| language: | |
| - en | |
| pipeline_tag: image-to-image | |
| tags: | |
| - text-to-image | |
| - image-editing | |
| - flux | |
| - diffusion-single-file | |
| base_model: | |
| - black-forest-labs/FLUX.2-small-decoder | |
| base_model_relation: quantized | |
| This is a BF16 conversion of [`black-forest-labs/FLUX.2-small-decoder`](https://huggingface.co/black-forest-labs/FLUX.2-small-decoder), converted using `diffusers` and `safetensors`. Weights cast from FP32 to BF16; `bn` statistics preserved as-is. | |
| `FLUX.2 Small Decoder` is a distilled VAE decoder that serves as a **drop-in replacement** for the standard FLUX.2 decoder. It delivers faster decoding and lower VRAM usage with minimal to zero quality loss. The encoder remains unchanged. | |
| Both images below have been generated using FLUX.2 Klein NVFP4 with BF16 VAEs. | |
| <table style="width:auto"> | |
| <tr> | |
| <td align="center"><a href="./images/flux2-vae-small.png"><img src="./images/flux2-vae-small.png" style="width:65%"/></a></td> | |
| <td align="center"><a href="./images/flux2-vae-small.png"><img src="./images/flux2-vae.png" style="width:65%"/></a></td> | |
| </tr> | |
| <tr> | |
| <td align="center"><b>FLUX.2 VAE small</b></td> | |
| <td align="center"><b>FLUX.2 VAE</b></td> | |
| </tr> | |
| </table> | |
| **Prompt** | |
| <pre>A black cat holding a sign that says 'hello world' in typewriter font</pre> | |
| # **Key Features** | |
| 1. **~1.4x faster decoding** compared to the full decoder. | |
| 2. **~1.4x less VRAM** at decode time, enabling higher resolutions without running out of memory. | |
| 3. **~28M decoder parameters** (vs ~50M in the full decoder) thanks to narrower channel widths (`[96, 192, 384, 384]` vs `[128, 256, 512, 512]`). | |
| 4. **Minimal quality loss** — images are almost identical. | |
| 5. Available under the Apache 2.0 license. | |
| Compatible with all open FLUX.2 models: | |
| - [FLUX.2-klein-4B](https://huggingface.co/black-forest-labs/FLUX.2-klein-4B) | |
| - [FLUX.2-klein-9B](https://huggingface.co/black-forest-labs/FLUX.2-klein-9B) | |
| - [FLUX.2-klein-9b-kv](https://huggingface.co/black-forest-labs/FLUX.2-klein-9b-kv) | |
| - [FLUX.2-dev](https://huggingface.co/black-forest-labs/FLUX.2-dev) | |
| --- | |
| # License | |
| This model is licensed under the https://www.apache.org/licenses/LICENSE-2.0. |