[Core] Add `shift_factor` to SD3 tiny autoencoder (#8618)

* shift factor argument to tiny

* remove shift factor rejigging from the sd3 docs

docs/source/en/api/pipelines/stable_diffusion/stable_diffusion_3.md

@@ -211,7 +211,6 @@ pipe = StableDiffusion3Pipeline.from_pretrained(
     "stabilityai/stable-diffusion-3-medium-diffusers", torch_dtype=torch.float16
 )
 pipe.vae = AutoencoderTiny.from_pretrained("madebyollin/taesd3", torch_dtype=torch.float16)
-pipe.vae.config.shift_factor = 0.0
 pipe = pipe.to("cuda")
 
 prompt = "slice of delicious New York-style berry cheesecake"

src/diffusers/models/autoencoders/autoencoder_tiny.py

@@ -111,6 +111,7 @@ class AutoencoderTiny(ModelMixin, ConfigMixin):
         latent_shift: float = 0.5,
         force_upcast: bool = False,
         scaling_factor: float = 1.0,
+        shift_factor: float = 0.0,
     ):
         super().__init__()