add refiner vae

Author: yiyixuxu

src/diffusers/__init__.py

@@ -185,6 +185,8 @@
             "AutoencoderKLCogVideoX",
             "AutoencoderKLCosmos",
             "AutoencoderKLHunyuanVideo",
+            "AutoencoderKLHunyuanImageRefiner",
+            "AutoencoderKLHunyuanImage",
             "AutoencoderKLLTXVideo",
             "AutoencoderKLMagvit",
             "AutoencoderKLMochi",
@@ -215,6 +217,7 @@
             "HunyuanDiT2DControlNetModel",
             "HunyuanDiT2DModel",
             "HunyuanDiT2DMultiControlNetModel",
+            "HunyuanImageTransformer2DModel",
             "HunyuanVideoFramepackTransformer3DModel",
             "HunyuanVideoTransformer3DModel",
             "I2VGenXLUNet",
@@ -870,6 +873,8 @@
             AutoencoderKLCogVideoX,
             AutoencoderKLCosmos,
             AutoencoderKLHunyuanVideo,
+            AutoencoderKLHunyuanImage,
+            AutoencoderKLHunyuanImageRefiner,
             AutoencoderKLLTXVideo,
             AutoencoderKLMagvit,
             AutoencoderKLMochi,
@@ -902,6 +907,7 @@
             HunyuanDiT2DMultiControlNetModel,
             HunyuanVideoFramepackTransformer3DModel,
             HunyuanVideoTransformer3DModel,
+            HunyuanImageTransformer2DModel,
             I2VGenXLUNet,
             Kandinsky3UNet,
             LatteTransformer3DModel,

src/diffusers/models/__init__.py

@@ -35,6 +35,8 @@
     _import_structure["autoencoders.autoencoder_kl_cogvideox"] = ["AutoencoderKLCogVideoX"]
     _import_structure["autoencoders.autoencoder_kl_cosmos"] = ["AutoencoderKLCosmos"]
     _import_structure["autoencoders.autoencoder_kl_hunyuan_video"] = ["AutoencoderKLHunyuanVideo"]
+    _import_structure["autoencoders.autoencoder_kl_hunyuanimage"] = ["AutoencoderKLHunyuanImage"]
+    _import_structure["autoencoders.autoencoder_kl_hunyuanimage_refiner"] = ["AutoencoderKLHunyuanImageRefiner"]
     _import_structure["autoencoders.autoencoder_kl_ltx"] = ["AutoencoderKLLTXVideo"]
     _import_structure["autoencoders.autoencoder_kl_magvit"] = ["AutoencoderKLMagvit"]
     _import_structure["autoencoders.autoencoder_kl_mochi"] = ["AutoencoderKLMochi"]
@@ -71,6 +73,7 @@
     _import_structure["transformers.dit_transformer_2d"] = ["DiTTransformer2DModel"]
     _import_structure["transformers.dual_transformer_2d"] = ["DualTransformer2DModel"]
     _import_structure["transformers.hunyuan_transformer_2d"] = ["HunyuanDiT2DModel"]
+    _import_structure["transformers.transformer_hunyuanimage"] = ["HunyuanImageTransformer2DModel"]
     _import_structure["transformers.latte_transformer_3d"] = ["LatteTransformer3DModel"]
     _import_structure["transformers.lumina_nextdit2d"] = ["LuminaNextDiT2DModel"]
     _import_structure["transformers.pixart_transformer_2d"] = ["PixArtTransformer2DModel"]
@@ -130,6 +133,8 @@
             AutoencoderKLCogVideoX,
             AutoencoderKLCosmos,
             AutoencoderKLHunyuanVideo,
+            AutoencoderKLHunyuanImage,
+            AutoencoderKLHunyuanImageRefiner,
             AutoencoderKLLTXVideo,
             AutoencoderKLMagvit,
             AutoencoderKLMochi,
@@ -178,6 +183,7 @@
             FluxTransformer2DModel,
             HiDreamImageTransformer2DModel,
             HunyuanDiT2DModel,
+            HunyuanImageTransformer2DModel,
             HunyuanVideoFramepackTransformer3DModel,
             HunyuanVideoTransformer3DModel,
             LatteTransformer3DModel,

src/diffusers/models/autoencoders/__init__.py

@@ -9,6 +9,8 @@
 from .autoencoder_kl_magvit import AutoencoderKLMagvit
 from .autoencoder_kl_mochi import AutoencoderKLMochi
 from .autoencoder_kl_qwenimage import AutoencoderKLQwenImage
+from .autoencoder_kl_hunyuanimage import AutoencoderKLHunyuanImage
+from .autoencoder_kl_hunyuanimage_refiner import AutoencoderKLHunyuanImageRefiner
 from .autoencoder_kl_temporal_decoder import AutoencoderKLTemporalDecoder
 from .autoencoder_kl_wan import AutoencoderKLWan
 from .autoencoder_oobleck import AutoencoderOobleck