Fix typos in docs and comments (#11416)

* Fix typos in docs and comments

* Apply style fixes

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

scripts/convert_flux_to_diffusers.py

@@ -220,7 +220,7 @@ def convert_flux_transformer_checkpoint_to_diffusers(
             f"double_blocks.{i}.txt_attn.proj.bias"
         )
 
-    # single transfomer blocks
+    # single transformer blocks
     for i in range(num_single_layers):
         block_prefix = f"single_transformer_blocks.{i}."
         # norm.linear  <- single_blocks.0.modulation.lin

scripts/convert_sana_to_diffusers.py

@@ -394,7 +394,7 @@ if __name__ == "__main__":
         help="Scheduler type to use. Use 'scm' for Sana Sprint models.",
     )
     parser.add_argument("--dump_path", default=None, type=str, required=True, help="Path to the output pipeline.")
-    parser.add_argument("--save_full_pipeline", action="store_true", help="save all the pipelien elemets in one.")
+    parser.add_argument("--save_full_pipeline", action="store_true", help="save all the pipeline elements in one.")
     parser.add_argument("--dtype", default="fp32", type=str, choices=["fp32", "fp16", "bf16"], help="Weight dtype.")
 
     args = parser.parse_args()

scripts/convert_shap_e_to_diffusers.py

@@ -984,7 +984,7 @@ def renderer(*, args, checkpoint_map_location):
     return renderer_model
 
 
-# prior model will expect clip_mean and clip_std, whic are missing from the state_dict
+# prior model will expect clip_mean and clip_std, which are missing from the state_dict
 PRIOR_EXPECTED_MISSING_KEYS = ["clip_mean", "clip_std"]
 
 

scripts/convert_wuerstchen.py

@@ -55,8 +55,8 @@ for key in orig_state_dict.keys():
         state_dict[key.replace("attn.out_proj.bias", "to_out.0.bias")] = weights
     else:
         state_dict[key] = orig_state_dict[key]
-deocder = WuerstchenDiffNeXt()
-deocder.load_state_dict(state_dict)
+decoder = WuerstchenDiffNeXt()
+decoder.load_state_dict(state_dict)
 
 # Prior
 orig_state_dict = torch.load(os.path.join(model_path, "model_v3_stage_c.pt"), map_location=device)["ema_state_dict"]
@@ -94,7 +94,7 @@ prior_pipeline = WuerstchenPriorPipeline(
 prior_pipeline.save_pretrained("warp-ai/wuerstchen-prior")
 
 decoder_pipeline = WuerstchenDecoderPipeline(
-    text_encoder=gen_text_encoder, tokenizer=gen_tokenizer, vqgan=vqmodel, decoder=deocder, scheduler=scheduler
+    text_encoder=gen_text_encoder, tokenizer=gen_tokenizer, vqgan=vqmodel, decoder=decoder, scheduler=scheduler
 )
 decoder_pipeline.save_pretrained("warp-ai/wuerstchen")
 
@@ -103,7 +103,7 @@ wuerstchen_pipeline = WuerstchenCombinedPipeline(
     # Decoder
     text_encoder=gen_text_encoder,
     tokenizer=gen_tokenizer,
-    decoder=deocder,
+    decoder=decoder,
     scheduler=scheduler,
     vqgan=vqmodel,
     # Prior