feat: Support MageFlow (CORE-372) (#15026)

comfy/supported_models.py

@@ -27,6 +27,7 @@ import comfy.text_encoders.z_image
 import comfy.text_encoders.ideogram4
 import comfy.text_encoders.boogu
 import comfy.text_encoders.krea2
+import comfy.text_encoders.mage_flow
 import comfy.text_encoders.joyimage
 import comfy.text_encoders.anima
 import comfy.text_encoders.ace15
@@ -1883,6 +1884,35 @@ class Krea2(supported_models_base.BASE):
         hunyuan_detect = comfy.text_encoders.hunyuan_video.llama_detect(state_dict, "{}qwen3vl_4b.transformer.".format(pref))
         return supported_models_base.ClipTarget(comfy.text_encoders.krea2.Krea2Tokenizer, comfy.text_encoders.krea2.te(**hunyuan_detect))
 
+class MageFlow(supported_models_base.BASE):
+    unet_config = {
+        "image_model": "mage_flow",
+    }
+
+    sampling_settings = {
+        "multiplier": 1.0,
+        "shift": 6.0,
+    }
+
+    memory_usage_factor = 6.5
+
+    unet_extra_config = {}
+    latent_format = latent_formats.Flux2
+
+    supported_inference_dtypes = [torch.bfloat16, torch.float32]
+
+    vae_key_prefix = ["vae."]
+    text_encoder_key_prefix = ["text_encoders."]
+
+    def get_model(self, state_dict, prefix="", device=None):
+        out = model_base.MageFlow(self, device=device)
+        return out
+
+    def clip_target(self, state_dict={}):
+        pref = self.text_encoder_key_prefix[0]
+        hunyuan_detect = comfy.text_encoders.hunyuan_video.llama_detect(state_dict, "{}qwen3vl_4b.transformer.".format(pref))
+        return supported_models_base.ClipTarget(comfy.text_encoders.mage_flow.MageFlowTokenizer, comfy.text_encoders.mage_flow.te(**hunyuan_detect))
+
 class QwenImage(supported_models_base.BASE):
     unet_config = {
         "image_model": "qwen_image",
@@ -2421,6 +2451,7 @@ models = [
     ACEStep15,
     Omnigen2,
     Boogu,
+    MageFlow,
     QwenImage,
     JoyImage,
     Ideogram4,