Update README.md

README.md

@@ -8,7 +8,7 @@ language:
 pipeline_tag: text-to-image
 library_name: diffusers
 ---
-Being a distilled model, this model requires different parameters to run optimally compared to the undistilled Chroma1-HD version. However, after quite a while of testing, I am unable to determine what settings to use. The [model card](https://huggingface.co/lodestones/Chroma1-Flash) is blank, but the commit message by the author says "use heun 8 steps CFG=1". Sadly, trying to use the `HeunDiscreteScheduler` with this model causes the pipeline to fail, presumably due to [this issue](https://github.com/huggingface/diffusers/issues/9971) with the `diffusers` library. Thus, I decided to omit the line of code that calls the pipeline in the sample code below. If you have any ideas or suggestions on how this model can currently be used in the `diffusers` library, do post a comment and maybe we can discuss this further.
+Being a distilled model, this model requires different parameters to run optimally compared to the undistilled Chroma1-HD version. However, after quite a while of testing, I am unable to determine what settings to use. The [model card](https://huggingface.co/lodestones/Chroma1-Flash) is blank, but the commit message by the author says "use heun 8 steps CFG=1". Sadly, trying to use `HeunDiscreteScheduler` or `FlowMatchHeunDiscreteScheduler` with this model causes the pipeline to fail, presumably due to [this issue](https://github.com/huggingface/diffusers/issues/9971) with the `diffusers` library. Thus, I decided to omit the line of code that calls the pipeline in the sample code below. If you have any ideas or suggestions on how this model can currently be used in the `diffusers` library, do post a comment and maybe we can discuss this further.
 
 
 For more information (including how to compress models yourself), check out https://huggingface.co/DFloat11 and https://github.com/LeanModels/DFloat11