fix: correct possessive 'it's' to 'its' in model docstrings

src/diffusers/models/autoencoders/autoencoder_asym_kl.py

@@ -26,7 +26,7 @@ class AsymmetricAutoencoderKL(ModelMixin, AutoencoderMixin, ConfigMixin):
     Designing a Better Asymmetric VQGAN for StableDiffusion https://huggingface.co/papers/2306.04632 . A VAE model with
     KL loss for encoding images into latents and decoding latent representations into images.
 
-    This model inherits from [`ModelMixin`]. Check the superclass documentation for it's generic methods implemented
+    This model inherits from [`ModelMixin`]. Check the superclass documentation for its generic methods implemented
     for all models (such as downloading or saving).
 
     Parameters:

src/diffusers/models/autoencoders/autoencoder_dc.py

@@ -382,7 +382,7 @@ class AutoencoderDC(ModelMixin, AutoencoderMixin, ConfigMixin, FromOriginalModel
     An Autoencoder model introduced in [DCAE](https://huggingface.co/papers/2410.10733) and used in
     [SANA](https://huggingface.co/papers/2410.10629).
 
-    This model inherits from [`ModelMixin`]. Check the superclass documentation for it's generic methods implemented
+    This model inherits from [`ModelMixin`]. Check the superclass documentation for its generic methods implemented
     for all models (such as downloading or saving).
 
     Args:

src/diffusers/models/autoencoders/autoencoder_kl.py

@@ -39,7 +39,7 @@ class AutoencoderKL(
     r"""
     A VAE model with KL loss for encoding images into latents and decoding latent representations into images.
 
-    This model inherits from [`ModelMixin`]. Check the superclass documentation for it's generic methods implemented
+    This model inherits from [`ModelMixin`]. Check the superclass documentation for its generic methods implemented
     for all models (such as downloading or saving).
 
     Parameters:

src/diffusers/models/autoencoders/autoencoder_kl_allegro.py

@@ -678,7 +678,7 @@ class AutoencoderKLAllegro(ModelMixin, AutoencoderMixin, ConfigMixin):
     A VAE model with KL loss for encoding videos into latents and decoding latent representations into videos. Used in
     [Allegro](https://github.com/rhymes-ai/Allegro).
 
-    This model inherits from [`ModelMixin`]. Check the superclass documentation for it's generic methods implemented
+    This model inherits from [`ModelMixin`]. Check the superclass documentation for its generic methods implemented
     for all models (such as downloading or saving).
 
     Parameters:

src/diffusers/models/autoencoders/autoencoder_kl_cogvideox.py

@@ -958,7 +958,7 @@ class AutoencoderKLCogVideoX(ModelMixin, AutoencoderMixin, ConfigMixin, FromOrig
     A VAE model with KL loss for encoding images into latents and decoding latent representations into images. Used in
     [CogVideoX](https://github.com/THUDM/CogVideo).
 
-    This model inherits from [`ModelMixin`]. Check the superclass documentation for it's generic methods implemented
+    This model inherits from [`ModelMixin`]. Check the superclass documentation for its generic methods implemented
     for all models (such as downloading or saving).
 
     Parameters:

src/diffusers/models/autoencoders/autoencoder_kl_flux2.py

@@ -41,7 +41,7 @@ class AutoencoderKLFlux2(
     r"""
     A VAE model with KL loss for encoding images into latents and decoding latent representations into images.
 
-    This model inherits from [`ModelMixin`]. Check the superclass documentation for it's generic methods implemented
+    This model inherits from [`ModelMixin`]. Check the superclass documentation for its generic methods implemented
     for all models (such as downloading or saving).
 
     Parameters:

src/diffusers/models/autoencoders/autoencoder_kl_hunyuan_video.py

@@ -627,7 +627,7 @@ class AutoencoderKLHunyuanVideo(ModelMixin, AutoencoderMixin, ConfigMixin):
     A VAE model with KL loss for encoding videos into latents and decoding latent representations into videos.
     Introduced in [HunyuanVideo](https://huggingface.co/papers/2412.03603).
 
-    This model inherits from [`ModelMixin`]. Check the superclass documentation for it's generic methods implemented
+    This model inherits from [`ModelMixin`]. Check the superclass documentation for its generic methods implemented
     for all models (such as downloading or saving).
     """
 

src/diffusers/models/autoencoders/autoencoder_kl_hunyuanimage.py

@@ -413,7 +413,7 @@ class AutoencoderKLHunyuanImage(ModelMixin, AutoencoderMixin, ConfigMixin, FromO
     r"""
     A VAE model for 2D images with spatial tiling support.
 
-    This model inherits from [`ModelMixin`]. Check the superclass documentation for it's generic methods implemented
+    This model inherits from [`ModelMixin`]. Check the superclass documentation for its generic methods implemented
     for all models (such as downloading or saving).
     """
 

src/diffusers/models/autoencoders/autoencoder_kl_hunyuanimage_refiner.py

@@ -595,7 +595,7 @@ class AutoencoderKLHunyuanImageRefiner(ModelMixin, AutoencoderMixin, ConfigMixin
     A VAE model with KL loss for encoding videos into latents and decoding latent representations into videos. Used for
     HunyuanImage-2.1 Refiner.
 
-    This model inherits from [`ModelMixin`]. Check the superclass documentation for it's generic methods implemented
+    This model inherits from [`ModelMixin`]. Check the superclass documentation for its generic methods implemented
     for all models (such as downloading or saving).
     """
 

src/diffusers/models/autoencoders/autoencoder_kl_hunyuanvideo15.py

@@ -636,7 +636,7 @@ class AutoencoderKLHunyuanVideo15(ModelMixin, AutoencoderMixin, ConfigMixin):
     A VAE model with KL loss for encoding videos into latents and decoding latent representations into videos. Used for
     HunyuanVideo-1.5.
 
-    This model inherits from [`ModelMixin`]. Check the superclass documentation for it's generic methods implemented
+    This model inherits from [`ModelMixin`]. Check the superclass documentation for its generic methods implemented
     for all models (such as downloading or saving).
     """
 

src/diffusers/models/autoencoders/autoencoder_kl_ltx.py

@@ -1037,7 +1037,7 @@ class AutoencoderKLLTXVideo(ModelMixin, AutoencoderMixin, ConfigMixin, FromOrigi
     A VAE model with KL loss for encoding images into latents and decoding latent representations into images. Used in
     [LTX](https://huggingface.co/Lightricks/LTX-Video).
 
-    This model inherits from [`ModelMixin`]. Check the superclass documentation for it's generic methods implemented
+    This model inherits from [`ModelMixin`]. Check the superclass documentation for its generic methods implemented
     for all models (such as downloading or saving).
 
     Args:

src/diffusers/models/autoencoders/autoencoder_kl_ltx2.py

@@ -1027,7 +1027,7 @@ class AutoencoderKLLTX2Video(ModelMixin, AutoencoderMixin, ConfigMixin, FromOrig
     A VAE model with KL loss for encoding images into latents and decoding latent representations into images. Used in
     [LTX-2](https://huggingface.co/Lightricks/LTX-2).
 
-    This model inherits from [`ModelMixin`]. Check the superclass documentation for it's generic methods implemented
+    This model inherits from [`ModelMixin`]. Check the superclass documentation for its generic methods implemented
     for all models (such as downloading or saving).
 
     Args:

src/diffusers/models/autoencoders/autoencoder_kl_magvit.py

@@ -667,7 +667,7 @@ class AutoencoderKLMagvit(ModelMixin, AutoencoderMixin, ConfigMixin):
     A VAE model with KL loss for encoding images into latents and decoding latent representations into images. This
     model is used in [EasyAnimate](https://huggingface.co/papers/2405.18991).
 
-    This model inherits from [`ModelMixin`]. Check the superclass documentation for it's generic methods implemented
+    This model inherits from [`ModelMixin`]. Check the superclass documentation for its generic methods implemented
     for all models (such as downloading or saving).
     """
 

src/diffusers/models/autoencoders/autoencoder_kl_mochi.py

@@ -657,7 +657,7 @@ class AutoencoderKLMochi(ModelMixin, AutoencoderMixin, ConfigMixin):
     A VAE model with KL loss for encoding images into latents and decoding latent representations into images. Used in
     [Mochi 1 preview](https://github.com/genmoai/models).
 
-    This model inherits from [`ModelMixin`]. Check the superclass documentation for it's generic methods implemented
+    This model inherits from [`ModelMixin`]. Check the superclass documentation for its generic methods implemented
     for all models (such as downloading or saving).
 
     Parameters:

src/diffusers/models/autoencoders/autoencoder_kl_qwenimage.py

@@ -674,7 +674,7 @@ class AutoencoderKLQwenImage(ModelMixin, AutoencoderMixin, ConfigMixin, FromOrig
     r"""
     A VAE model with KL loss for encoding videos into latents and decoding latent representations into videos.
 
-    This model inherits from [`ModelMixin`]. Check the superclass documentation for it's generic methods implemented
+    This model inherits from [`ModelMixin`]. Check the superclass documentation for its generic methods implemented
     for all models (such as downloading or saving).
     """
 

src/diffusers/models/autoencoders/autoencoder_kl_temporal_decoder.py

@@ -139,7 +139,7 @@ class AutoencoderKLTemporalDecoder(ModelMixin, AttentionMixin, AutoencoderMixin,
     r"""
     A VAE model with KL loss for encoding images into latents and decoding latent representations into images.
 
-    This model inherits from [`ModelMixin`]. Check the superclass documentation for it's generic methods implemented
+    This model inherits from [`ModelMixin`]. Check the superclass documentation for its generic methods implemented
     for all models (such as downloading or saving).
 
     Parameters:

src/diffusers/models/autoencoders/autoencoder_kl_wan.py

@@ -962,7 +962,7 @@ class AutoencoderKLWan(ModelMixin, AutoencoderMixin, ConfigMixin, FromOriginalMo
     A VAE model with KL loss for encoding videos into latents and decoding latent representations into videos.
     Introduced in [Wan 2.1].
 
-    This model inherits from [`ModelMixin`]. Check the superclass documentation for it's generic methods implemented
+    This model inherits from [`ModelMixin`]. Check the superclass documentation for its generic methods implemented
     for all models (such as downloading or saving).
     """
 

src/diffusers/models/autoencoders/autoencoder_oobleck.py

@@ -296,7 +296,7 @@ class AutoencoderOobleck(ModelMixin, AutoencoderMixin, ConfigMixin):
     An autoencoder for encoding waveforms into latents and decoding latent representations into waveforms. First
     introduced in Stable Audio.
 
-    This model inherits from [`ModelMixin`]. Check the superclass documentation for it's generic methods implemented
+    This model inherits from [`ModelMixin`]. Check the superclass documentation for its generic methods implemented
     for all models (such as downloading or saving).
 
     Parameters:

src/diffusers/models/autoencoders/autoencoder_vidtok.py

@@ -940,7 +940,7 @@ class AutoencoderVidTok(ModelMixin, ConfigMixin):
     A VAE model for encoding videos into latents and decoding latent representations into videos, supporting both
     continuous and discrete latent representations. Used in [VidTok](https://github.com/microsoft/VidTok).
 
-    This model inherits from [`ModelMixin`]. Check the superclass documentation for it's generic methods implemented
+    This model inherits from [`ModelMixin`]. Check the superclass documentation for its generic methods implemented
     for all models (such as downloading or saving).
 
     Args:

src/diffusers/models/autoencoders/vq_model.py

@@ -41,7 +41,7 @@ class VQModel(ModelMixin, AutoencoderMixin, ConfigMixin):
     r"""
     A VQ-VAE model for decoding latent representations.
 
-    This model inherits from [`ModelMixin`]. Check the superclass documentation for it's generic methods implemented
+    This model inherits from [`ModelMixin`]. Check the superclass documentation for its generic methods implemented
     for all models (such as downloading or saving).
 
     Parameters:

src/diffusers/models/controlnets/controlnet_xs.py

@@ -246,7 +246,7 @@ class ControlNetXSAdapter(ModelMixin, AttentionMixin, ConfigMixin):
     A `ControlNetXSAdapter` model. To use it, pass it into a `UNetControlNetXSModel` (together with a
     `UNet2DConditionModel` base model).
 
-    This model inherits from [`ModelMixin`] and [`ConfigMixin`]. Check the superclass documentation for it's generic
+    This model inherits from [`ModelMixin`] and [`ConfigMixin`]. Check the superclass documentation for its generic
     methods implemented for all models (such as downloading or saving).
 
     Like `UNetControlNetXSModel`, `ControlNetXSAdapter` is compatible with StableDiffusion and StableDiffusion-XL. It's
@@ -512,13 +512,13 @@ class UNetControlNetXSModel(ModelMixin, AttentionMixin, ConfigMixin):
     r"""
     A UNet fused with a ControlNet-XS adapter model
 
-    This model inherits from [`ModelMixin`] and [`ConfigMixin`]. Check the superclass documentation for it's generic
+    This model inherits from [`ModelMixin`] and [`ConfigMixin`]. Check the superclass documentation for its generic
     methods implemented for all models (such as downloading or saving).
 
-    `UNetControlNetXSModel` is compatible with StableDiffusion and StableDiffusion-XL. It's default parameters are
+    `UNetControlNetXSModel` is compatible with StableDiffusion and StableDiffusion-XL. Its default parameters are
     compatible with StableDiffusion.
 
-    It's parameters are either passed to the underlying `UNet2DConditionModel` or used exactly like in
+    Its parameters are either passed to the underlying `UNet2DConditionModel` or used exactly like in
     `ControlNetXSAdapter` . See their documentation for details.
     """
 

src/diffusers/models/unets/unet_1d.py

@@ -41,7 +41,7 @@ class UNet1DModel(ModelMixin, ConfigMixin):
     r"""
     A 1D UNet model that takes a noisy sample and a timestep and returns a sample shaped output.
 
-    This model inherits from [`ModelMixin`]. Check the superclass documentation for it's generic methods implemented
+    This model inherits from [`ModelMixin`]. Check the superclass documentation for its generic methods implemented
     for all models (such as downloading or saving).
 
     Parameters:

src/diffusers/models/unets/unet_2d.py

@@ -40,7 +40,7 @@ class UNet2DModel(ModelMixin, ConfigMixin):
     r"""
     A 2D UNet model that takes a noisy sample and a timestep and returns a sample shaped output.
 
-    This model inherits from [`ModelMixin`]. Check the superclass documentation for it's generic methods implemented
+    This model inherits from [`ModelMixin`]. Check the superclass documentation for its generic methods implemented
     for all models (such as downloading or saving).
 
     Parameters:

src/diffusers/models/unets/unet_2d_condition.py

@@ -79,7 +79,7 @@ class UNet2DConditionModel(
     A conditional 2D UNet model that takes a noisy sample, conditional state, and a timestep and returns a sample
     shaped output.
 
-    This model inherits from [`ModelMixin`]. Check the superclass documentation for it's generic methods implemented
+    This model inherits from [`ModelMixin`]. Check the superclass documentation for its generic methods implemented
     for all models (such as downloading or saving).
 
     Parameters:

src/diffusers/models/unets/unet_2d_condition_flax.py

@@ -53,7 +53,7 @@ class FlaxUNet2DConditionModel(nn.Module, FlaxModelMixin, ConfigMixin):
     A conditional 2D UNet model that takes a noisy sample, conditional state, and a timestep and returns a sample
     shaped output.
 
-    This model inherits from [`FlaxModelMixin`]. Check the superclass documentation for it's generic methods
+    This model inherits from [`FlaxModelMixin`]. Check the superclass documentation for its generic methods
     implemented for all models (such as downloading or saving).
 
     This model is also a Flax Linen [flax.linen.Module](https://flax.readthedocs.io/en/latest/flax.linen.html#module)

src/diffusers/models/unets/unet_3d_condition.py

@@ -63,7 +63,7 @@ class UNet3DConditionModel(ModelMixin, AttentionMixin, ConfigMixin, UNet2DCondit
     A conditional 3D UNet model that takes a noisy sample, conditional state, and a timestep and returns a sample
     shaped output.
 
-    This model inherits from [`ModelMixin`]. Check the superclass documentation for it's generic methods implemented
+    This model inherits from [`ModelMixin`]. Check the superclass documentation for its generic methods implemented
     for all models (such as downloading or saving).
 
     Parameters:

src/diffusers/models/unets/unet_i2vgen_xl.py

@@ -97,7 +97,7 @@ class I2VGenXLUNet(ModelMixin, AttentionMixin, ConfigMixin, UNet2DConditionLoade
     I2VGenXL UNet. It is a conditional 3D UNet model that takes a noisy sample, conditional state, and a timestep and
     returns a sample-shaped output.
 
-    This model inherits from [`ModelMixin`]. Check the superclass documentation for it's generic methods implemented
+    This model inherits from [`ModelMixin`]. Check the superclass documentation for its generic methods implemented
     for all models (such as downloading or saving).
 
     Parameters:

src/diffusers/models/unets/unet_motion_model.py

@@ -1199,7 +1199,7 @@ class UNetMotionModel(ModelMixin, AttentionMixin, ConfigMixin, UNet2DConditionLo
     A modified conditional 2D UNet model that takes a noisy sample, conditional state, and a timestep and returns a
     sample shaped output.
 
-    This model inherits from [`ModelMixin`]. Check the superclass documentation for it's generic methods implemented
+    This model inherits from [`ModelMixin`]. Check the superclass documentation for its generic methods implemented
     for all models (such as downloading or saving).
     """
 

src/diffusers/models/unets/unet_spatio_temporal_condition.py

@@ -34,7 +34,7 @@ class UNetSpatioTemporalConditionModel(ModelMixin, AttentionMixin, ConfigMixin,
     A conditional Spatio-Temporal UNet model that takes a noisy video frames, conditional state, and a timestep and
     returns a sample shaped output.
 
-    This model inherits from [`ModelMixin`]. Check the superclass documentation for it's generic methods implemented
+    This model inherits from [`ModelMixin`]. Check the superclass documentation for its generic methods implemented
     for all models (such as downloading or saving).
 
     Parameters:

src/diffusers/models/vae_flax.py

@@ -774,7 +774,7 @@ class FlaxAutoencoderKL(nn.Module, FlaxModelMixin, ConfigMixin):
     r"""
     Flax implementation of a VAE model with KL loss for decoding latent representations.
 
-    This model inherits from [`FlaxModelMixin`]. Check the superclass documentation for it's generic methods
+    This model inherits from [`FlaxModelMixin`]. Check the superclass documentation for its generic methods
     implemented for all models (such as downloading or saving).
 
     This model is a Flax Linen [flax.linen.Module](https://flax.readthedocs.io/en/latest/flax.linen.html#module)

src/diffusers/pipelines/audioldm2/modeling_audioldm2.py

@@ -167,7 +167,7 @@ class AudioLDM2UNet2DConditionModel(ModelMixin, AttentionMixin, ConfigMixin, UNe
     self-attention layer in each Transformer block, as well as multiple cross-attention layers. It also allows for up
     to two cross-attention embeddings, `encoder_hidden_states` and `encoder_hidden_states_1`.
 
-    This model inherits from [`ModelMixin`]. Check the superclass documentation for it's generic methods implemented
+    This model inherits from [`ModelMixin`]. Check the superclass documentation for its generic methods implemented
     for all models (such as downloading or saving).
 
     Parameters:

src/diffusers/pipelines/deprecated/versatile_diffusion/modeling_text_unet.py

@@ -273,7 +273,7 @@ class UNetFlatConditionModel(ModelMixin, ConfigMixin):
     A conditional 2D UNet model that takes a noisy sample, conditional state, and a timestep and returns a sample
     shaped output.
 
-    This model inherits from [`ModelMixin`]. Check the superclass documentation for it's generic methods implemented
+    This model inherits from [`ModelMixin`]. Check the superclass documentation for its generic methods implemented
     for all models (such as downloading or saving).
 
     Parameters: