Merge branch 'main' into allegro-impl

Author: a-r-r-o-w

docs/source/en/api/pipelines/stable_diffusion/stable_diffusion_3.md

@@ -313,6 +313,26 @@ image = pipe("a picture of a cat holding a sign that says hello world").images[0
 image.save('sd3-single-file-t5-fp8.png')
 ```
 
+### Loading the single file checkpoint for the Stable Diffusion 3.5 Transformer Model
+
+```python
+import torch
+from diffusers import SD3Transformer2DModel, StableDiffusion3Pipeline
+
+transformer = SD3Transformer2DModel.from_single_file(
+    "https://huggingface.co/stabilityai/stable-diffusion-3.5-large-turbo/blob/main/sd3.5_large.safetensors",
+    torch_dtype=torch.bfloat16,
+)
+pipe = StableDiffusion3Pipeline.from_pretrained(
+    "stabilityai/stable-diffusion-3.5-large",
+    transformer=transformer,
+    torch_dtype=torch.bfloat16,
+)
+pipe.enable_model_cpu_offload()
+image = pipe("a cat holding a sign that says hello world").images[0]
+image.save("sd35.png")
+```
+
 ## StableDiffusion3Pipeline
 
 [[autodoc]] StableDiffusion3Pipeline

docs/source/en/quantization/bitsandbytes.md

@@ -59,19 +59,7 @@ model_8bit = FluxTransformer2DModel.from_pretrained(
 model_8bit.transformer_blocks.layers[-1].norm2.weight.dtype
 ```
 
-Once a model is quantized, you can push the model to the Hub with the [`~ModelMixin.push_to_hub`] method. The quantization `config.json` file is pushed first, followed by the quantized model weights.
-
-```py
-from diffusers import FluxTransformer2DModel, BitsAndBytesConfig
-
-quantization_config = BitsAndBytesConfig(load_in_8bit=True)
-
-model_8bit = FluxTransformer2DModel.from_pretrained(
-    "black-forest-labs/FLUX.1-dev", 
-    subfolder="transformer",
-    quantization_config=quantization_config
-)
-```
+Once a model is quantized, you can push the model to the Hub with the [`~ModelMixin.push_to_hub`] method. The quantization `config.json` file is pushed first, followed by the quantized model weights. You can also save the serialized 4-bit models locally with [`~ModelMixin.save_pretrained`].
 
 </hfoption>
 <hfoption id="4-bit">
@@ -131,7 +119,7 @@ from diffusers import FluxTransformer2DModel, BitsAndBytesConfig
 quantization_config = BitsAndBytesConfig(load_in_4bit=True)
 
 model_4bit = FluxTransformer2DModel.from_pretrained(
-    "sayakpaul/flux.1-dev-nf4-pkg", subfolder="transformer"
+    "hf-internal-testing/flux.1-dev-nf4-pkg", subfolder="transformer"
 )
 ```
 
@@ -264,4 +252,9 @@ double_quant_model = SD3Transformer2DModel.from_pretrained(
     quantization_config=double_quant_config,
 )
 model.dequantize()
-```
+```
+
+## Resources
+
+* [End-to-end notebook showing Flux.1 Dev inference in a free-tier Colab](https://gist.github.com/sayakpaul/c76bd845b48759e11687ac550b99d8b4)
+* [Training](https://gist.github.com/sayakpaul/05afd428bc089b47af7c016e42004527)

examples/advanced_diffusion_training/train_dreambooth_lora_flux_advanced.py

@@ -74,7 +74,7 @@
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
+check_min_version("0.32.0.dev0")
 
 logger = get_logger(__name__)
 

examples/advanced_diffusion_training/train_dreambooth_lora_sd15_advanced.py

@@ -71,7 +71,7 @@
 
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
+check_min_version("0.32.0.dev0")
 
 logger = get_logger(__name__)
 

examples/advanced_diffusion_training/train_dreambooth_lora_sdxl_advanced.py

@@ -79,7 +79,7 @@
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
+check_min_version("0.32.0.dev0")
 
 logger = get_logger(__name__)
 

examples/cogvideo/train_cogvideox_image_to_video_lora.py

@@ -61,7 +61,7 @@
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
+check_min_version("0.32.0.dev0")
 
 logger = get_logger(__name__)
 

examples/cogvideo/train_cogvideox_lora.py

@@ -52,7 +52,7 @@
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
+check_min_version("0.32.0.dev0")
 
 logger = get_logger(__name__)
 

examples/community/marigold_depth_estimation.py

@@ -43,7 +43,7 @@
 
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
+check_min_version("0.32.0.dev0")
 
 
 class MarigoldDepthOutput(BaseOutput):

examples/consistency_distillation/train_lcm_distill_lora_sd_wds.py

@@ -73,7 +73,7 @@
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
+check_min_version("0.32.0.dev0")
 
 logger = get_logger(__name__)
 

examples/consistency_distillation/train_lcm_distill_lora_sdxl.py

@@ -66,7 +66,7 @@
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.31.0.dev0")
+check_min_version("0.32.0.dev0")
 
 logger = get_logger(__name__)