Feat: z-image pixel space (model still training atm) (#12709)

* draft zeta (z-image pixel space)

* revert gitignore

* model loaded and able to run however vector direction still wrong tho

* flip the vector direction to original again this time

* Move wrongly positioned Z image pixel space class

* inherit Radiance LatentFormat class

* Fix parameters in classes for Zeta x0 dino

* remove arbitrary nn.init instances

* Remove unused import of lru_cache

---------

Co-authored-by: silveroxides <ishimarukaito@gmail.com>

comfy/model_base.py

@@ -1263,6 +1263,11 @@ class Lumina2(BaseModel):
             out['ref_latents'] = list([1, 16, sum(map(lambda a: math.prod(a.size()[2:]), ref_latents))])
         return out
 
+class ZImagePixelSpace(Lumina2):
+    def __init__(self, model_config, model_type=ModelType.FLOW, device=None):
+        BaseModel.__init__(self, model_config, model_type, device=device, unet_model=comfy.ldm.lumina.model.NextDiTPixelSpace)
+        self.memory_usage_factor_conds = ("ref_latents",)
+
 class WAN21(BaseModel):
     def __init__(self, model_config, model_type=ModelType.FLOW, image_to_video=False, device=None):
         super().__init__(model_config, model_type, device=device, unet_model=comfy.ldm.wan.model.WanModel)