Update README.md

README.md

@@ -58,11 +58,14 @@ You can find ready-to-use scripts in the [diffusers-recipes](https://github.com/
 
 ```python
 import torch
-from diffusers import ModularPipeline
+from diffusers import AutoencoderKLMiniMaxH3, ModularPipeline
 from diffusers.hooks import apply_group_offloading
 from diffusers.utils.export_utils import encode_video
 from sdnq import SDNQConfig  # noqa: F401
 
+# patch until fixed upstream, the fp32 pin covers the whole VAE and ignores dtype
+AutoencoderKLMiniMaxH3._keep_in_fp32_modules = []
+
 pipe = ModularPipeline.from_pretrained("OzzyGT/MiniMax_H3_sdnq_4bit_pruned", workflow="t2va", trust_remote_code=True)
 pipe.load_components(dtype=torch.bfloat16, trust_remote_code=True)