add kontext

Author: lmxyy

docs/source/advanced_features/kontext.rst

@@ -0,0 +1,14 @@
+FLUX.1-Kontext
+==============
+
+.. image:: https://huggingface.co/mit-han-lab/nunchaku-artifacts/resolve/main/nunchaku/assets/kontext.png
+   :alt: FLUX.1-Kontext-dev integration with Nunchaku
+
+Nunchaku supports `FLUX-Kontext-dev <_flux1_kontext_dev>`_,
+an advanced model that enables precise image editing through natural language prompts.
+The implementation follows the same pattern as described in :doc:`Basic Usage <../basic_usage/basic_usage>`.
+
+.. literalinclude:: ../../../examples/flux.1-kontext-dev.py
+   :language: python
+   :caption: Running FLUX.1-Kontext-dev (`examples/flux.1-kontext-dev.py <https://github.com/mit-han-lab/nunchaku/blob/main/examples/flux.1-kontext-dev.py>`__)
+   :linenos:

docs/source/index.rst

@@ -22,6 +22,7 @@ Check out `DeepCompressor <deepcompressor_repo>`_ for the quantization library.
     :caption: Advanced Features
 
     advanced_features/lora.rst
+    advanced_features/kontext.rst
     advanced_features/controlnet.rst
     advanced_features/qencoder.rst
     advanced_features/offload.rst

docs/source/links.rst

@@ -27,3 +27,4 @@
 .. _controlnet_union_pro2: https://huggingface.co/Shakker-Labs/FLUX.1-dev-ControlNet-Union-Pro-2.0
 .. _fbcache: https://github.com/chengzeyi/ParaAttention?tab=readme-ov-file#first-block-cache-our-dynamic-caching
 .. _pulid: https://arxiv.org/abs/2404.16022
+.. _flux1_kontext_dev: https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev