update

Author: ishan-modi

docs/source/en/_toctree.yml

@@ -175,7 +175,7 @@
     title: gguf
   - local: quantization/torchao
     title: torchao
-  - local: quantization/quanto 
+  - local: quantization/quanto
     title: quanto
   title: Quantization Methods
 - sections:
@@ -270,6 +270,8 @@
     - sections:
       - local: api/models/controlnet
         title: ControlNetModel
+      - local: api/models/controlnet_union
+        title: ControlNetUnionModel
       - local: api/models/controlnet_flux
         title: FluxControlNetModel
       - local: api/models/controlnet_hunyuandit
@@ -278,8 +280,6 @@
         title: SD3ControlNetModel
       - local: api/models/controlnet_sparsectrl
         title: SparseControlNetModel
-      - local: api/models/controlnet_union
-        title: ControlNetUnionModel
       title: ControlNets
     - sections:
       - local: api/models/allegro_transformer3d
@@ -288,12 +288,12 @@
         title: AuraFlowTransformer2DModel
       - local: api/models/cogvideox_transformer3d
         title: CogVideoXTransformer3DModel
-      - local: api/models/consisid_transformer3d
-        title: ConsisIDTransformer3DModel
       - local: api/models/cogview3plus_transformer2d
         title: CogView3PlusTransformer2DModel
       - local: api/models/cogview4_transformer2d
         title: CogView4Transformer2DModel
+      - local: api/models/consisid_transformer3d
+        title: ConsisIDTransformer3DModel
       - local: api/models/dit_transformer2d
         title: DiTTransformer2DModel
       - local: api/models/easyanimate_transformer3d
@@ -306,12 +306,12 @@
         title: HunyuanVideoTransformer3DModel
       - local: api/models/latte_transformer3d
         title: LatteTransformer3DModel
-      - local: api/models/lumina_nextdit2d
-        title: LuminaNextDiT2DModel
-      - local: api/models/lumina2_transformer2d
-        title: Lumina2Transformer2DModel
       - local: api/models/ltx_video_transformer3d
         title: LTXVideoTransformer3DModel
+      - local: api/models/lumina2_transformer2d
+        title: Lumina2Transformer2DModel
+      - local: api/models/lumina_nextdit2d
+        title: LuminaNextDiT2DModel
       - local: api/models/mochi_transformer3d
         title: MochiTransformer3DModel
       - local: api/models/omnigen_transformer
@@ -320,10 +320,10 @@
         title: PixArtTransformer2DModel
       - local: api/models/prior_transformer
         title: PriorTransformer
-      - local: api/models/sd3_transformer2d
-        title: SD3Transformer2DModel
       - local: api/models/sana_transformer2d
         title: SanaTransformer2DModel
+      - local: api/models/sd3_transformer2d
+        title: SD3Transformer2DModel
       - local: api/models/stable_audio_transformer
         title: StableAudioDiTModel
       - local: api/models/transformer2d
@@ -338,10 +338,10 @@
         title: StableCascadeUNet
       - local: api/models/unet
         title: UNet1DModel
-      - local: api/models/unet2d
-        title: UNet2DModel
       - local: api/models/unet2d-cond
         title: UNet2DConditionModel
+      - local: api/models/unet2d
+        title: UNet2DModel
       - local: api/models/unet3d-cond
         title: UNet3DConditionModel
       - local: api/models/unet-motion
@@ -350,6 +350,10 @@
         title: UViT2DModel
       title: UNets
     - sections:
+      - local: api/models/asymmetricautoencoderkl
+        title: AsymmetricAutoencoderKL
+      - local: api/models/autoencoder_dc
+        title: AutoencoderDC
       - local: api/models/autoencoderkl
         title: AutoencoderKL
       - local: api/models/autoencoderkl_allegro
@@ -366,10 +370,6 @@
         title: AutoencoderKLMochi
       - local: api/models/autoencoder_kl_wan
         title: AutoencoderKLWan
-      - local: api/models/asymmetricautoencoderkl
-        title: AsymmetricAutoencoderKL
-      - local: api/models/autoencoder_dc
-        title: AutoencoderDC
       - local: api/models/consistency_decoder_vae
         title: ConsistencyDecoderVAE
       - local: api/models/autoencoder_oobleck
@@ -513,40 +513,40 @@
     - sections:
       - local: api/pipelines/stable_diffusion/overview
         title: Overview
-      - local: api/pipelines/stable_diffusion/text2img
-        title: Text-to-image
+      - local: api/pipelines/stable_diffusion/depth2img
+        title: Depth-to-image
+      - local: api/pipelines/stable_diffusion/gligen
+        title: GLIGEN (Grounded Language-to-Image Generation)
+      - local: api/pipelines/stable_diffusion/image_variation
+        title: Image variation
       - local: api/pipelines/stable_diffusion/img2img
         title: Image-to-image
       - local: api/pipelines/stable_diffusion/svd
         title: Image-to-video
       - local: api/pipelines/stable_diffusion/inpaint
         title: Inpainting
-      - local: api/pipelines/stable_diffusion/depth2img
-        title: Depth-to-image
-      - local: api/pipelines/stable_diffusion/image_variation
-        title: Image variation
+      - local: api/pipelines/stable_diffusion/k_diffusion
+        title: K-Diffusion
+      - local: api/pipelines/stable_diffusion/latent_upscale
+        title: Latent upscaler
+      - local: api/pipelines/stable_diffusion/ldm3d_diffusion
+        title: LDM3D Text-to-(RGB, Depth), Text-to-(RGB-pano, Depth-pano), LDM3D Upscaler
       - local: api/pipelines/stable_diffusion/stable_diffusion_safe
         title: Safe Stable Diffusion
+      - local: api/pipelines/stable_diffusion/sdxl_turbo
+        title: SDXL Turbo
       - local: api/pipelines/stable_diffusion/stable_diffusion_2
         title: Stable Diffusion 2
       - local: api/pipelines/stable_diffusion/stable_diffusion_3
         title: Stable Diffusion 3
       - local: api/pipelines/stable_diffusion/stable_diffusion_xl
         title: Stable Diffusion XL
-      - local: api/pipelines/stable_diffusion/sdxl_turbo
-        title: SDXL Turbo
-      - local: api/pipelines/stable_diffusion/latent_upscale
-        title: Latent upscaler
       - local: api/pipelines/stable_diffusion/upscale
         title: Super-resolution
-      - local: api/pipelines/stable_diffusion/k_diffusion
-        title: K-Diffusion
-      - local: api/pipelines/stable_diffusion/ldm3d_diffusion
-        title: LDM3D Text-to-(RGB, Depth), Text-to-(RGB-pano, Depth-pano), LDM3D Upscaler
       - local: api/pipelines/stable_diffusion/adapter
         title: T2I-Adapter
-      - local: api/pipelines/stable_diffusion/gligen
-        title: GLIGEN (Grounded Language-to-Image Generation)
+      - local: api/pipelines/stable_diffusion/text2img
+        title: Text-to-image
       title: Stable Diffusion
     - local: api/pipelines/stable_unclip
       title: Stable unCLIP

utils/check_doc_toc.py

@@ -123,11 +123,13 @@ def check_pipeline_doc(overwrite=False):
 
     # sort sub pipeline docs
     for pipeline_doc in pipeline_docs:
-        if "section" in pipeline_doc:
-            sub_pipeline_doc = pipeline_doc["section"]
+        if "sections" in pipeline_doc:
+            sub_pipeline_doc = pipeline_doc["sections"]
             new_sub_pipeline_doc = clean_doc_toc(sub_pipeline_doc)
-            if overwrite:
-                pipeline_doc["section"] = new_sub_pipeline_doc
+            if new_sub_pipeline_doc != sub_pipeline_doc:
+                diff = True
+                if overwrite:
+                    pipeline_doc["sections"] = new_sub_pipeline_doc
         new_pipeline_docs.append(pipeline_doc)
 
     # sort overall pipeline doc
@@ -149,10 +151,60 @@ def check_pipeline_doc(overwrite=False):
             )
 
 
+def check_model_doc(overwrite=False):
+    with open(PATH_TO_TOC, encoding="utf-8") as f:
+        content = yaml.safe_load(f.read())
+
+    # Get to the API doc
+    api_idx = 0
+    while content[api_idx]["title"] != "API":
+        api_idx += 1
+    api_doc = content[api_idx]["sections"]
+
+    # Then to the model doc
+    model_idx = 0
+    while api_doc[model_idx]["title"] != "Models":
+        model_idx += 1
+
+    diff = False
+    model_docs = api_doc[model_idx]["sections"]
+    new_model_docs = []
+
+    # sort sub model docs
+    for model_doc in model_docs:
+        if "sections" in model_doc:
+            sub_model_doc = model_doc["sections"]
+            new_sub_model_doc = clean_doc_toc(sub_model_doc)
+            if new_sub_model_doc != sub_model_doc:
+                diff = True
+                if overwrite:
+                    model_doc["sections"] = new_sub_model_doc
+        new_model_docs.append(model_doc)
+
+    # sort overall model doc
+    new_model_docs = clean_doc_toc(new_model_docs)
+
+    if new_model_docs != model_docs:
+        diff = True
+        if overwrite:
+            api_doc[model_idx]["sections"] = new_model_docs
+
+    if diff:
+        if overwrite:
+            content[api_idx]["sections"] = api_doc
+            with open(PATH_TO_TOC, "w", encoding="utf-8") as f:
+                f.write(yaml.dump(content, allow_unicode=True))
+        else:
+            raise ValueError(
+                "The model doc part of the table of content is not properly sorted, run `make style` to fix this."
+            )
+
+
 if __name__ == "__main__":
     parser = argparse.ArgumentParser()
     parser.add_argument("--fix_and_overwrite", action="store_true", help="Whether to fix inconsistencies.")
     args = parser.parse_args()
 
     check_scheduler_doc(args.fix_and_overwrite)
     check_pipeline_doc(args.fix_and_overwrite)
+    check_model_doc(args.fix_and_overwrite)