default to 1024 1024.

src/diffusers/models/transformers/auraflow_transformer_2d.py

@@ -75,7 +75,7 @@ def forward(self, latent):
         )
         latent = latent.permute(0, 2, 4, 1, 3, 5).flatten(-3).flatten(1, 2)
         latent = self.proj(latent)
-        return latent + self.pos_embed[:, : latent.size(1)]
+        return latent + self.pos_embed
 
 
 # Taken from the original Aura flow inference code.

src/diffusers/pipelines/aura_flow/pipeline_aura_flow.py

@@ -391,8 +391,8 @@ def __call__(
         sigmas: List[float] = None,
         guidance_scale: float = 3.5,
         num_images_per_prompt: Optional[int] = 1,
-        height: Optional[int] = 512,
-        width: Optional[int] = 512,
+        height: Optional[int] = 1024,
+        width: Optional[int] = 1024,
         generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
         latents: Optional[torch.Tensor] = None,
         prompt_embeds: Optional[torch.Tensor] = None,
@@ -415,9 +415,9 @@ def __call__(
                 `negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is
                 less than `1`).
             height (`int`, *optional*, defaults to self.transformer.config.sample_size * self.vae_scale_factor):
-                The height in pixels of the generated image. This is set to 512 by default.
+                The height in pixels of the generated image. This is set to 1024 by default for best results.
             width (`int`, *optional*, defaults to self.transformer.config.sample_size * self.vae_scale_factor):
-                The width in pixels of the generated image. This is set to 512 by default.
+                The width in pixels of the generated image. This is set to 1024 by default for best results.
             num_inference_steps (`int`, *optional*, defaults to 50):
                 The number of denoising steps. More denoising steps usually lead to a higher quality image at the
                 expense of slower inference.