add other vid models

Author: stevhliu

docs/source/en/api/pipelines/aura_flow.md

@@ -12,7 +12,7 @@ specific language governing permissions and limitations under the License.
 
 # AuraFlow
 
-AuraFlow is inspired by [Stable Diffusion 3](../pipelines/stable_diffusion/stable_diffusion_3.md) and is by far the largest text-to-image generation model that comes with an Apache 2.0 license. This model achieves state-of-the-art results on the [GenEval](https://github.com/djghosh13/geneval) benchmark.
+AuraFlow is inspired by [Stable Diffusion 3](../pipelines/stable_diffusion/stable_diffusion_3) and is by far the largest text-to-image generation model that comes with an Apache 2.0 license. This model achieves state-of-the-art results on the [GenEval](https://github.com/djghosh13/geneval) benchmark.
 
 It was developed by the Fal team and more details about it can be found in [this blog post](https://blog.fal.ai/auraflow/).
 
@@ -22,6 +22,47 @@ AuraFlow can be quite expensive to run on consumer hardware devices. However, yo
 
 </Tip>
 
+## Quantization
+
+Quantization helps reduce the memory requirements of very large models by storing model weights in a lower precision data type. However, quantization may have varying impact on video quality depending on the video model.
+
+Refer to the [Quantization](../../quantization/overview) to learn more about supported quantization backends (bitsandbytes, torchao, gguf) and selecting a quantization backend that supports your use case. The example below demonstrates how to load a quantized [`AuraFlowPipeline`] for inference with bitsandbytes.
+
+```py
+import torch
+from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig, AuraFlowTransformer2DModel, AuraFlowPipeline
+from diffusers.utils import export_to_video
+from transformers import BitsAndBytesConfig as BitsAndBytesConfig, T5EncoderModel
+
+quant_config = BitsAndBytesConfig(load_in_8bit=True)
+text_encoder_8bit = T5EncoderModel.from_pretrained(
+    "fal/AuraFlow",
+    subfolder="text_encoder",
+    quantization_config=quant_config,
+    torch_dtype=torch.float16,
+)
+
+quant_config = DiffusersBitsAndBytesConfig(load_in_8bit=True)
+transformer_8bit = AuraFlowTransformer2DModel.from_pretrained(
+    "fal/AuraFlow",
+    subfolder="transformer",
+    quantization_config=quant_config,
+    torch_dtype=torch.float16,
+)
+
+pipeline = AuraFlowPipeline.from_pretrained(
+    "fal/AuraFlow",
+    text_encoder=text_encoder_8bit,
+    transformer=transformer_8bit,
+    torch_dtype=torch.float16,
+    device_map="balanced",
+)
+
+prompt = "A refreshing scene where a glass of freshly squeezed orange juice stands prominently at the center, bathed in warm, golden sunlight that highlights the vibrant, citrus hues of the juice. The glass is intricately detailed, showing condensation droplets that glisten like tiny jewels. Surrounding the base of the glass, scattered orange slices and lush green leaves add a touch of natural beauty and freshness. Above the glass, a dynamic splash of orange juice is captured mid-air, forming the word 'Orange' in a fluid, playful script. The splash is so vivid and realistic that each droplet seems to dance in the air, creating a sense of movement and energy. In the background, a serene orchard with rows of orange trees stretches out under a clear blue sky, their branches heavy with ripe oranges ready for harvest. Rays of sunlight filter through the leaves, casting dappled shadows on the ground. A gentle breeze rustles the leaves, adding a sense of calm and tranquility to the scene. The entire scene evokes a sense of purity, freshness, and vitality, inviting viewers to experience the simple joy of a glass of fresh orange juice."
+image = pipeline(prompt).images[0]
+image.save("auraflow.png")
+```
+
 ## AuraFlowPipeline
 
 [[autodoc]] AuraFlowPipeline

docs/source/en/api/pipelines/cogvideox.md

@@ -112,13 +112,46 @@ CogVideoX-2b requires about 19 GB of GPU memory to decode 49 frames (6 seconds o
   - With enabling cpu offloading and tiling, memory usage is `11 GB`
 - `pipe.vae.enable_slicing()`
 
-### Quantized inference
+## Quantization
 
-[torchao](https://github.com/pytorch/ao) and [optimum-quanto](https://github.com/huggingface/optimum-quanto/) can be used to quantize the text encoder, transformer and VAE modules to lower the memory requirements. This makes it possible to run the model on a free-tier T4 Colab or lower VRAM GPUs!
+Quantization helps reduce the memory requirements of very large models by storing model weights in a lower precision data type. However, quantization may have varying impact on video quality depending on the video model.
 
-It is also worth noting that torchao quantization is fully compatible with [torch.compile](/optimization/torch2.0#torchcompile), which allows for much faster inference speed. Additionally, models can be serialized and stored in a quantized datatype to save disk space with torchao. Find examples and benchmarks in the gists below.
-- [torchao](https://gist.github.com/a-r-r-o-w/4d9732d17412888c885480c6521a9897)
-- [quanto](https://gist.github.com/a-r-r-o-w/31be62828b00a9292821b85c1017effa)
+Refer to the [Quantization](../../quantization/overview) to learn more about supported quantization backends (bitsandbytes, torchao, gguf) and selecting a quantization backend that supports your use case. The example below demonstrates how to load a quantized [`CogVideoXPipeline`] for inference with bitsandbytes.
+
+```py
+import torch
+from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig, CogVideoXTransformer3DModel, CogVideoXPipeline
+from diffusers.utils import export_to_video
+from transformers import BitsAndBytesConfig as BitsAndBytesConfig, T5EncoderModel
+
+quant_config = BitsAndBytesConfig(load_in_8bit=True)
+text_encoder_8bit = T5EncoderModel.from_pretrained(
+    "THUDM/CogVideoX-2b",
+    subfolder="text_encoder",
+    quantization_config=quant_config,
+    torch_dtype=torch.float16,
+)
+
+quant_config = DiffusersBitsAndBytesConfig(load_in_8bit=True)
+transformer_8bit = CogVideoXTransformer3DModel.from_pretrained(
+    "THUDM/CogVideoX-2b",
+    subfolder="transformer",
+    quantization_config=quant_config,
+    torch_dtype=torch.float16,
+)
+
+pipeline = CogVideoXPipeline.from_pretrained(
+    "THUDM/CogVideoX-2b",
+    text_encoder=text_encoder_8bit,
+    transformer=transformer_8bit,
+    torch_dtype=torch.float16,
+    device_map="balanced",
+)
+
+prompt = "A detailed wooden toy ship with intricately carved masts and sails is seen gliding smoothly over a plush, blue carpet that mimics the waves of the sea. The ship's hull is painted a rich brown, with tiny windows. The carpet, soft and textured, provides a perfect backdrop, resembling an oceanic expanse. Surrounding the ship are various other toys and children's items, hinting at a playful environment. The scene captures the innocence and imagination of childhood, with the toy ship's journey symbolizing endless adventures in a whimsical, indoor setting."
+video = pipeline(prompt=prompt, guidance_scale=6, num_inference_steps=50).frames[0]
+export_to_video(video, "ship.mp4", fps=8)
+```
 
 ## CogVideoXPipeline
 

docs/source/en/api/pipelines/flux.md

@@ -334,6 +334,48 @@ out = pipe(
 out.save("image.png")
 ```
 
+## Quantization
+
+Quantization helps reduce the memory requirements of very large models by storing model weights in a lower precision data type. However, quantization may have varying impact on video quality depending on the video model.
+
+Refer to the [Quantization](../../quantization/overview) to learn more about supported quantization backends (bitsandbytes, torchao, gguf) and selecting a quantization backend that supports your use case. The example below demonstrates how to load a quantized [`FluxPipeline`] for inference with bitsandbytes.
+
+```py
+import torch
+from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig, FluxTransformer2DModel, FluxPipeline
+from diffusers.utils import export_to_video
+from transformers import BitsAndBytesConfig as BitsAndBytesConfig, T5EncoderModel
+
+quant_config = BitsAndBytesConfig(load_in_8bit=True)
+text_encoder_8bit = T5EncoderModel.from_pretrained(
+    "black-forest-labs/FLUX.1-dev",
+    subfolder="text_encoder_2",
+    quantization_config=quant_config,
+    torch_dtype=torch.float16,
+)
+
+quant_config = DiffusersBitsAndBytesConfig(load_in_8bit=True)
+transformer_8bit = FluxTransformer2DModel.from_pretrained(
+    "black-forest-labs/FLUX.1-dev",
+    subfolder="transformer",
+    quantization_config=quant_config,
+    torch_dtype=torch.float16,
+)
+
+pipeline = FluxPipeline.from_pretrained(
+    "black-forest-labs/FLUX.1-dev",
+    text_encoder=text_encoder_8bit,
+    transformer=transformer_8bit,
+    torch_dtype=torch.float16,
+    device_map="balanced",
+)
+
+prompt = "A refreshing scene where a glass of freshly squeezed orange juice stands prominently at the center, bathed in warm, golden sunlight that highlights the vibrant, citrus hues of the juice. The glass is intricately detailed, showing condensation droplets that glisten like tiny jewels. Surrounding the base of the glass, scattered orange slices and lush green leaves add a touch of natural beauty and freshness. Above the glass, a dynamic splash of orange juice is captured mid-air, forming the word 'Orange' in a fluid, playful script. The splash is so vivid and realistic that each droplet seems to dance in the air, creating a sense of movement and energy. In the background, a serene orchard with rows of orange trees stretches out under a clear blue sky, their branches heavy with ripe oranges ready for harvest. Rays of sunlight filter through the leaves, casting dappled shadows on the ground. A gentle breeze rustles the leaves, adding a sense of calm and tranquility to the scene. The entire scene evokes a sense of purity, freshness, and vitality, inviting viewers to experience the simple joy of a glass of fresh orange juice."
+
+image = pipeline(prompt, guidance_scale=3.5, height=768, width=1360, num_inference_steps=50).images[0]
+image.save("flux.png")
+```
+
 ## Single File Loading for the `FluxTransformer2DModel`
 
 The `FluxTransformer2DModel` supports loading checkpoints in the original format shipped by Black Forest Labs. This is also useful when trying to load finetunes or quantized versions of the models that have been published by the community.

docs/source/en/api/pipelines/hunyuan_video.md

@@ -32,6 +32,37 @@ Recommendations for inference:
 - For smaller resolution images, try lower values of `shift` (between `2.0` to `5.0`) in the [Scheduler](https://huggingface.co/docs/diffusers/main/en/api/schedulers/flow_match_euler_discrete#diffusers.FlowMatchEulerDiscreteScheduler.shift). For larger resolution images, try higher values (between `7.0` and `12.0`). The default value is `7.0` for HunyuanVideo.
 - For more information about supported resolutions and other details, please refer to the original repository [here](https://github.com/Tencent/HunyuanVideo/).
 
+## Quantization
+
+Quantization helps reduce the memory requirements of very large models by storing model weights in a lower precision data type. However, quantization may have varying impact on video quality depending on the video model.
+
+Refer to the [Quantization](../../quantization/overview) to learn more about supported quantization backends (bitsandbytes, torchao, gguf) and selecting a quantization backend that supports your use case. The example below demonstrates how to load a quantized [`HunyuanVideoPipeline`] for inference with bitsandbytes.
+
+```py
+import torch
+from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig, HunyuanVideoTransformer3DModel, HunyuanVideoPipeline
+from diffusers.utils import export_to_video
+
+quant_config = DiffusersBitsAndBytesConfig(load_in_8bit=True)
+transformer_8bit = HunyuanVideoTransformer3DModel.from_pretrained(
+    "tencent/HunyuanVideo",
+    subfolder="transformer",
+    quantization_config=quant_config,
+    torch_dtype=torch.float16,
+)
+
+pipeline = HunyuanVideoPipeline.from_pretrained(
+    "tencent/HunyuanVideo",
+    transformer=transformer_8bit,
+    torch_dtype=torch.float16,
+    device_map="balanced",
+)
+
+prompt = "A cat walks on the grass, realistic style."
+video = pipeline(prompt=prompt, num_frames=61, num_inference_steps=30).frames[0]
+export_to_video(video, "cat.mp4", fps=15)
+```
+
 ## HunyuanVideoPipeline
 
 [[autodoc]] HunyuanVideoPipeline

docs/source/en/api/pipelines/mochi.md

@@ -27,9 +27,9 @@
 
 ## Quantization
 
-Quantization helps reduce the memory requirements of very large models by storing model weights in a lower precision data type. Refer to the [Quantization](../../quantization/overview) to learn more about supported quantization backends and selecting a quantization backend that supports your use case.
+Quantization helps reduce the memory requirements of very large models by storing model weights in a lower precision data type. However, quantization may have varying impact on video quality depending on the video model.
 
-The example below demonstrates how to load a quantized [`MochiPipeline`] for inference with bitsandbytes.
+Refer to the [Quantization](../../quantization/overview) to learn more about supported quantization backends (bitsandbytes, torchao, gguf) and selecting a quantization backend that supports your use case. The example below demonstrates how to load a quantized [`MochiPipeline`] for inference with bitsandbytes.
 
 ```py
 import torch
@@ -61,12 +61,12 @@ pipeline = MochiPipeline.from_pretrained(
     device_map="balanced",
 )
 
-frames = pipeline(
+video = pipeline(
   "Close-up of a cats eye, with the galaxy reflected in the cats eye. Ultra high resolution 4k.",
   num_inference_steps=28,
   guidance_scale=3.5
 ).frames[0]
-export_to_video(frames, "cat.mp4")
+export_to_video(video, "cat.mp4")
 ```
 
 ## Generating videos with Mochi-1 Preview

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

@@ -268,6 +268,47 @@ image.save("sd3_hello_world.png")
 
 Check out the full script [here](https://gist.github.com/sayakpaul/508d89d7aad4f454900813da5d42ca97).
 
+## Quantization
+
+Quantization helps reduce the memory requirements of very large models by storing model weights in a lower precision data type. However, quantization may have varying impact on video quality depending on the video model.
+
+Refer to the [Quantization](../../quantization/overview) to learn more about supported quantization backends (bitsandbytes, torchao, gguf) and selecting a quantization backend that supports your use case. The example below demonstrates how to load a quantized [`StableDiffusion3Pipeline`] for inference with bitsandbytes.
+
+```py
+import torch
+from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig, SD3Transformer2DModel, StableDiffusion3Pipeline
+from diffusers.utils import export_to_video
+from transformers import BitsAndBytesConfig as BitsAndBytesConfig, T5EncoderModel
+
+quant_config = BitsAndBytesConfig(load_in_8bit=True)
+text_encoder_8bit = T5EncoderModel.from_pretrained(
+    "stabilityai/stable-diffusion-3.5-large",
+    subfolder="text_encoder_3",
+    quantization_config=quant_config,
+    torch_dtype=torch.float16,
+)
+
+quant_config = DiffusersBitsAndBytesConfig(load_in_8bit=True)
+transformer_8bit = SD3Transformer2DModel.from_pretrained(
+    "stabilityai/stable-diffusion-3.5-large",
+    subfolder="transformer",
+    quantization_config=quant_config,
+    torch_dtype=torch.float16,
+)
+
+pipeline = StableDiffusion3Pipeline.from_pretrained(
+    "stabilityai/stable-diffusion-3.5-large",
+    text_encoder=text_encoder_8bit,
+    transformer=transformer_8bit,
+    torch_dtype=torch.float16,
+    device_map="balanced",
+)
+
+prompt = "A refreshing scene where a glass of freshly squeezed orange juice stands prominently at the center, bathed in warm, golden sunlight that highlights the vibrant, citrus hues of the juice. The glass is intricately detailed, showing condensation droplets that glisten like tiny jewels. Surrounding the base of the glass, scattered orange slices and lush green leaves add a touch of natural beauty and freshness. Above the glass, a dynamic splash of orange juice is captured mid-air, forming the word 'Orange' in a fluid, playful script. The splash is so vivid and realistic that each droplet seems to dance in the air, creating a sense of movement and energy. In the background, a serene orchard with rows of orange trees stretches out under a clear blue sky, their branches heavy with ripe oranges ready for harvest. Rays of sunlight filter through the leaves, casting dappled shadows on the ground. A gentle breeze rustles the leaves, adding a sense of calm and tranquility to the scene. The entire scene evokes a sense of purity, freshness, and vitality, inviting viewers to experience the simple joy of a glass of fresh orange juice."
+image = pipeline(prompt, num_inference_steps=28, guidance_scale=7.0).images[0]
+image.save("sd3.png")
+```
+
 ## Using Long Prompts with the T5 Text Encoder
 
 By default, the T5 Text Encoder prompt uses a maximum sequence length of `256`. This can be adjusted by setting the `max_sequence_length` to accept fewer or more tokens. Keep in mind that longer sequences require additional resources and result in longer generation times, such as during batch inference.