Merge branch 'main' into missing_kwargs_lora_pipeline_py

Author: CyberVy

docs/source/en/quantization/torchao.md

@@ -126,7 +126,7 @@ image = pipe(prompt, num_inference_steps=30, guidance_scale=7.0).images[0]
 image.save("output.png")
 ```
 
-Some quantization methods, such as `uint4wo`, cannot be loaded directly and may result in an `UnpicklingError` when trying to load the models, but work as expected when saving them. In order to work around this, one can load the state dict manually into the model. Note, however, that this requires using `weights_only=False` in `torch.load`, so it should be run only if the weights were obtained from a trustable source.
+If you are using `torch<=2.6.0`, some quantization methods, such as `uint4wo`, cannot be loaded directly and may result in an `UnpicklingError` when trying to load the models, but work as expected when saving them. In order to work around this, one can load the state dict manually into the model. Note, however, that this requires using `weights_only=False` in `torch.load`, so it should be run only if the weights were obtained from a trustable source.
 
 ```python
 import torch

examples/community/mixture_tiling_sdxl.py

@@ -1,4 +1,4 @@
-# Copyright 2025 The HuggingFace Team. All rights reserved.
+# Copyright 2025 The DEVAIEXP Team and The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -1070,32 +1070,32 @@ def __call__(
                     text_encoder_projection_dim = int(pooled_prompt_embeds.shape[-1])
                 else:
                     text_encoder_projection_dim = self.text_encoder_2.config.projection_dim
-                    add_time_ids = self._get_add_time_ids(
-                        original_size,
-                        crops_coords_top_left[row][col],
-                        target_size,
+                add_time_ids = self._get_add_time_ids(
+                    original_size,
+                    crops_coords_top_left[row][col],
+                    target_size,
+                    dtype=prompt_embeds.dtype,
+                    text_encoder_projection_dim=text_encoder_projection_dim,
+                )
+                if negative_original_size is not None and negative_target_size is not None:
+                    negative_add_time_ids = self._get_add_time_ids(
+                        negative_original_size,
+                        negative_crops_coords_top_left[row][col],
+                        negative_target_size,
                         dtype=prompt_embeds.dtype,
                         text_encoder_projection_dim=text_encoder_projection_dim,
                     )
-                    if negative_original_size is not None and negative_target_size is not None:
-                        negative_add_time_ids = self._get_add_time_ids(
-                            negative_original_size,
-                            negative_crops_coords_top_left[row][col],
-                            negative_target_size,
-                            dtype=prompt_embeds.dtype,
-                            text_encoder_projection_dim=text_encoder_projection_dim,
-                        )
-                    else:
-                        negative_add_time_ids = add_time_ids
+                else:
+                    negative_add_time_ids = add_time_ids
 
-                    if self.do_classifier_free_guidance:
-                        prompt_embeds = torch.cat([negative_prompt_embeds, prompt_embeds], dim=0)
-                        add_text_embeds = torch.cat([negative_pooled_prompt_embeds, add_text_embeds], dim=0)
-                        add_time_ids = torch.cat([negative_add_time_ids, add_time_ids], dim=0)
+                if self.do_classifier_free_guidance:
+                    prompt_embeds = torch.cat([negative_prompt_embeds, prompt_embeds], dim=0)
+                    add_text_embeds = torch.cat([negative_pooled_prompt_embeds, add_text_embeds], dim=0)
+                    add_time_ids = torch.cat([negative_add_time_ids, add_time_ids], dim=0)
 
-                    prompt_embeds = prompt_embeds.to(device)
-                    add_text_embeds = add_text_embeds.to(device)
-                    add_time_ids = add_time_ids.to(device).repeat(batch_size * num_images_per_prompt, 1)
+                prompt_embeds = prompt_embeds.to(device)
+                add_text_embeds = add_text_embeds.to(device)
+                add_time_ids = add_time_ids.to(device).repeat(batch_size * num_images_per_prompt, 1)
                 addition_embed_type_row.append((prompt_embeds, add_text_embeds, add_time_ids))
             embeddings_and_added_time.append(addition_embed_type_row)
 

examples/research_projects/anytext/README.md

@@ -0,0 +1,32 @@
+# AnyTextPipeline Pipeline
+
+Project page: https://aigcdesigngroup.github.io/homepage_anytext
+
+"AnyText comprises a diffusion pipeline with two primary elements: an auxiliary latent module and a text embedding module. The former uses inputs like text glyph, position, and masked image to generate latent features for text generation or editing. The latter employs an OCR model for encoding stroke data as embeddings, which blend with image caption embeddings from the tokenizer to generate texts that seamlessly integrate with the background. We employed text-control diffusion loss and text perceptual loss for training to further enhance writing accuracy."
+
+Each text line that needs to be generated should be enclosed in double quotes. For any usage questions, please refer to the [paper](https://arxiv.org/abs/2311.03054).
+
+
+```py
+import torch
+from diffusers import DiffusionPipeline
+from anytext_controlnet import AnyTextControlNetModel
+from diffusers.utils import load_image
+
+# I chose a font file shared by an HF staff:
+# !wget https://huggingface.co/spaces/ysharma/TranslateQuotesInImageForwards/resolve/main/arial-unicode-ms.ttf
+
+anytext_controlnet = AnyTextControlNetModel.from_pretrained("tolgacangoz/anytext-controlnet", torch_dtype=torch.float16,
+                                                            variant="fp16",)
+pipe = DiffusionPipeline.from_pretrained("tolgacangoz/anytext", font_path="arial-unicode-ms.ttf",
+                                          controlnet=anytext_controlnet, torch_dtype=torch.float16,
+                                          trust_remote_code=False,  # One needs to give permission to run this pipeline's code
+                                          ).to("cuda")
+
+# generate image
+prompt = 'photo of caramel macchiato coffee on the table, top-down perspective, with "Any" "Text" written on it using cream'
+draw_pos = load_image("https://raw.githubusercontent.com/tyxsspa/AnyText/refs/heads/main/example_images/gen9.png")
+image = pipe(prompt, num_inference_steps=20, mode="generate", draw_pos=draw_pos,
+             ).images[0]
+image
+```