Buckets:

hf-doc-build
/

doc

Files

xet

hf-doc-build/doc / diffusers /main /es /using-diffusers /text-img2vid.md

mishig

8 days ago

preview code

download

raw

19.3 kB

# Generación de video

Los modelos de generación de video extienden la generación de imágenes (que puede considerarse un video de un solo fotograma) para procesar también datos relacionados con el espacio y el tiempo. Asegurar que todos estos datos, texto, espacio y tiempo, permanezcan consistentes y alineados de un fotograma a otro es un gran desafío a la hora de generar videos largos y de alta resolución.

Los modelos de video modernos abordan este desafío con la arquitectura de transformador de difusión (DiT). Esto reduce los costos computacionales y permite una escalabilidad más eficiente hacia datos de imágenes y videos más grandes y de mayor calidad.

A continuación, echa un vistazo a lo que son capaces de hacer algunos de estos modelos de video.

```py
# pip install ftfy
import torch
import numpy as np
from diffusers import AutoModel, WanPipeline
from diffusers.hooks.group_offloading import apply_group_offloading
from diffusers.utils import export_to_video, load_image
from transformers import UMT5EncoderModel
text_encoder = UMT5EncoderModel.from_pretrained("Wan-AI/Wan2.1-T2V-14B-Diffusers", subfolder="text_encoder", dtype=torch.bfloat16)
vae = AutoModel.from_pretrained("Wan-AI/Wan2.1-T2V-14B-Diffusers", subfolder="vae", dtype=torch.float32)
transformer = AutoModel.from_pretrained("Wan-AI/Wan2.1-T2V-14B-Diffusers", subfolder="transformer", dtype=torch.bfloat16)
# group-offloading
onload_device = torch.device("cuda")
offload_device = torch.device("cpu")
apply_group_offloading(text_encoder,
    onload_device=onload_device,
    offload_device=offload_device,
    offload_type="block_level",
    num_blocks_per_group=4
)
transformer.enable_group_offload(
    onload_device=onload_device,
    offload_device=offload_device,
    offload_type="leaf_level",
    use_stream=True
)
pipeline = WanPipeline.from_pretrained(
    "Wan-AI/Wan2.1-T2V-14B-Diffusers",
    vae=vae,
    transformer=transformer,
    text_encoder=text_encoder,
    dtype=torch.bfloat16
)
pipeline.to("cuda")  # or "mps", "xpu", "cpu"
prompt = """
The camera rushes from far to near in a low-angle shot, 
revealing a white ferret on a log. It plays, leaps into the water, and emerges, as the camera zooms in 
for a close-up. Water splashes berry bushes nearby, while moss, snow, and leaves blanket the ground. 
Birch trees and a light blue sky frame the scene, with ferns in the foreground. Side lighting casts dynamic 
shadows and warm highlights. Medium composition, front view, low angle, with depth of field.
"""
negative_prompt = """
Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, 
low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, 
misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards
"""
output = pipeline(
    prompt=prompt,
    negative_prompt=negative_prompt,
    num_frames=81,
    guidance_scale=5.0,
).frames[0]
export_to_video(output, "output.mp4", fps=16)
```

```py
import torch
from diffusers importAutoModel, HunyuanVideoPipeline
from diffusers.quantizers import PipelineQuantizationConfig
from diffusers.utils import export_to_video
# quantize weights to int4 with bitsandbytes
pipeline_quant_config = PipelineQuantizationConfig(
  quant_backend="bitsandbytes_4bit",
  quant_kwargs={
    "load_in_4bit": True,
    "bnb_4bit_quant_type": "nf4",
    "bnb_4bit_compute_dtype": torch.bfloat16
    },
  components_to_quantize="transformer"
)
pipeline = HunyuanVideoPipeline.from_pretrained(
    "hunyuanvideo-community/HunyuanVideo",
    quantization_config=pipeline_quant_config,
    dtype=torch.bfloat16,
)
# model-offloading and tiling
pipeline.enable_model_cpu_offload()
pipeline.vae.enable_tiling()
prompt = "A fluffy teddy bear sits on a bed of soft pillows surrounded by children's toys."
video = pipeline(prompt=prompt, num_frames=61, num_inference_steps=30).frames[0]
export_to_video(video, "output.mp4", fps=15)
```

```py
import torch
from diffusers import LTXPipeline, AutoModel
from diffusers.hooks import apply_group_offloading
from diffusers.utils import export_to_video
# fp8 layerwise weight-casting
transformer = AutoModel.from_pretrained(
    "Lightricks/LTX-Video",
    subfolder="transformer",
    dtype=torch.bfloat16
)
transformer.enable_layerwise_casting(
    storage_dtype=torch.float8_e4m3fn, compute_dtype=torch.bfloat16
)
pipeline = LTXPipeline.from_pretrained("Lightricks/LTX-Video", transformer=transformer, dtype=torch.bfloat16)
# group-offloading
onload_device = torch.device("cuda")
offload_device = torch.device("cpu")
pipeline.transformer.enable_group_offload(onload_device=onload_device, offload_device=offload_device, offload_type="leaf_level", use_stream=True)
apply_group_offloading(pipeline.text_encoder, onload_device=onload_device, offload_type="block_level", num_blocks_per_group=2)
apply_group_offloading(pipeline.vae, onload_device=onload_device, offload_type="leaf_level")
prompt = """
A woman with long brown hair and light skin smiles at another woman with long blonde hair. The woman with brown hair wears a black jacket and has a small, barely noticeable mole on her right cheek. The camera angle is a close-up, focused on the woman with brown hair's face. The lighting is warm and natural, likely from the setting sun, casting a soft glow on the scene. The scene appears to be real-life footage
"""
negative_prompt = "worst quality, inconsistent motion, blurry, jittery, distorted"
video = pipeline(
    prompt=prompt,
    negative_prompt=negative_prompt,
    width=768,
    height=512,
    num_frames=161,
    decode_timestep=0.03,
    decode_noise_scale=0.025,
    num_inference_steps=50,
).frames[0]
export_to_video(video, "output.mp4", fps=24)
```

Esta guía cubrirá los fundamentos de la generación de video, como qué parámetros configurar y cómo reducir su uso de memoria.

> [!TIP]
> Si te interesa aprender más sobre cómo usar un modelo específico, consulta la tarjeta de modelo de su API de pipeline.

## Parámetros de la pipeline

Hay varios parámetros que configurar en el pipeline que afectarán a la calidad o la velocidad de la generación de video. Experimentar con diferentes valores de parámetros es importante para descubrir el equilibrio adecuado entre calidad y velocidad.

### num_frames
Un fotograma es una imagen fija que se reproduce en una secuencia de otros fotogramas para crear movimiento o un video. Controle el número de fotogramas generados por segundo con `num_frames`. Aumentar `num_frames` mejora la suavidad percibida del movimiento y la coherencia visual, lo que es especialmente importante para videos con contenido dinámico. Un valor más alto de `num_frames` también aumenta la duración del video.

Algunos modelos de vídeo requieren valores más específicos de `num_frames` para la inferencia. Por ejemplo, [HunyuanVideoPipeline](/docs/diffusers/main/es/api/pipelines/hunyuan_video#diffusers.HunyuanVideoPipeline) recomienda calcular `num_frames` con `(4 * num_frames) +1`. Consulta siempre la tarjeta de modelo de la API de un pipeline para ver si hay un valor recomendado.

```py
import torch
from diffusers import LTXPipeline
from diffusers.utils import export_to_video
pipeline = LTXPipeline.from_pretrained(
    "Lightricks/LTX-Video", dtype=torch.bfloat16
).to("cuda")  # or "mps", "xpu", "cpu"
prompt = """
A woman with long brown hair and light skin smiles at another woman with long blonde hair. The woman 
with brown hair wears a black jacket and has a small, barely noticeable mole on her right cheek. The 
camera angle is a close-up, focused on the woman with brown hair's face. The lighting is warm and 
natural, likely from the setting sun, casting a soft glow on the scene. The scene appears to be 
real-life footage
"""
video = pipeline(
    prompt=prompt,
    negative_prompt=negative_prompt,
    width=768,
    height=512,
    num_frames=161,
    decode_timestep=0.03,
    decode_noise_scale=0.025,
    num_inference_steps=50,
).frames[0]
export_to_video(video, "output.mp4", fps=24)
```

### guidance_scale
La escala de guía o "cfg" controla hasta qué punto los fotogramas generados se ajustan a la condición de entrada (texto, imagen o ambos). Aumentar `guidance_scale` genera fotogramas que se asemejan más a las condiciones de entrada e incluyen detalles más finos, pero con el riesgo de introducir artefactos y reducir la diversidad de la salida. Valores más bajos de `guidance_scale` fomentan un ajuste más laxo al prompt y una mayor variedad en la salida, aunque los detalles pueden no ser tan buenos. Si es demasiado bajo, es posible que ignore por completo el prompt y genere ruido aleatorio.
```py
import torch
from diffusers import CogVideoXPipeline, CogVideoXTransformer3DModel
from diffusers.utils import export_to_video
pipeline = CogVideoXPipeline.from_pretrained(
  "THUDM/CogVideoX-2b",
  dtype=torch.float16
).to("cuda")  # or "mps", "xpu", "cpu"

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, "output.mp4", fps=8)
```
### negative_prompt

Un prompt negativo es útil para excluir elementos que no deseas ver en el video generado. Se utiliza comúnmente para refinar la calidad y la alineación del video generado, alejando al modelo de elementos no deseados como "blurry, distorted, ugly". Esto puede crear videos más limpios y enfocados.

```py
# pip install ftfy
import torch
from diffusers import WanPipeline
from diffusers.schedulers.scheduling_unipc_multistep import UniPCMultistepScheduler
from diffusers.utils import export_to_video
vae = AutoencoderKLWan.from_pretrained(
  "Wan-AI/Wan2.1-T2V-14B-Diffusers", subfolder="vae", dtype=torch.float32
)
pipeline = WanPipeline.from_pretrained(
  "Wan-AI/Wan2.1-T2V-14B-Diffusers", vae=vae, dtype=torch.bfloat16
)
pipeline.scheduler = UniPCMultistepScheduler.from_config(
  pipeline.scheduler.config, flow_shift=5.0
)
pipeline.to("cuda")  # or "mps", "xpu", "cpu"
pipeline.load_lora_weights("benjamin-paine/steamboat-willie-14b", adapter_name="steamboat-willie")
pipeline.set_adapters("steamboat-willie")
pipeline.enable_model_cpu_offload()
# use "steamboat willie style" to trigger the LoRA
prompt = """
steamboat willie style, golden era animation, The camera rushes from far to near in a low-angle shot, 
revealing a white ferret on a log. It plays, leaps into the water, and emerges, as the camera zooms in 
for a close-up. Water splashes berry bushes nearby, while moss, snow, and leaves blanket the ground. 
Birch trees and a light blue sky frame the scene, with ferns in the foreground. Side lighting casts 
dynamic shadows and warm highlights. Medium composition, front view, low angle, with depth of field.
"""
output = pipeline(
  prompt=prompt,
  num_frames=81,
  guidance_scale=5.0,
).frames[0]
export_to_video(output, "output.mp4", fps=16)
```

## Reducir el uso de memoria

Los modelos de video recientes, como [HunyuanVideoPipeline](/docs/diffusers/main/es/api/pipelines/hunyuan_video#diffusers.HunyuanVideoPipeline) y [WanPipeline](/docs/diffusers/main/es/api/pipelines/wan#diffusers.WanPipeline), que tienen más de 10 mil millones de parámetros, requieren mucha memoria y a menudo superan la memoria disponible en el hardware de consumo. Diffusers ofrece varias técnicas para reducir los requisitos de memoria de estos modelos grandes.

> [!TIP]
> Consulte la guía [Reduce memory usage](../optimization/memory) para obtener más detalles sobre otras técnicas de ahorro de memoria.

Una de estas técnicas es [group-offloading](../optimization/memory#group-offloading), que descarga grupos de capas internas del modelo (como `torch.nn.Sequential`) a la CPU cuando no se están utilizando. Estas capas solo se cargan cuando son necesarias para el cálculo, evitando así almacenar **todos** los componentes del modelo en la GPU. Para un modelo de 14B parámetros como [WanPipeline](/docs/diffusers/main/es/api/pipelines/wan#diffusers.WanPipeline), el group-offloading puede reducir la memoria requerida a ~13GB de VRAM.

```py
# pip install ftfy
import torch
import numpy as np
from diffusers import AutoModel, WanPipeline
from diffusers.hooks.group_offloading import apply_group_offloading
from diffusers.utils import export_to_video, load_image
from transformers import UMT5EncoderModel
text_encoder = UMT5EncoderModel.from_pretrained("Wan-AI/Wan2.1-T2V-14B-Diffusers", subfolder="text_encoder", dtype=torch.bfloat16)
vae = AutoModel.from_pretrained("Wan-AI/Wan2.1-T2V-14B-Diffusers", subfolder="vae", dtype=torch.float32)
transformer = AutoModel.from_pretrained("Wan-AI/Wan2.1-T2V-14B-Diffusers", subfolder="transformer", dtype=torch.bfloat16)
# group-offloading
onload_device = torch.device("cuda")
offload_device = torch.device("cpu")
apply_group_offloading(text_encoder,
    onload_device=onload_device,
    offload_device=offload_device,
    offload_type="block_level",
    num_blocks_per_group=4
)
transformer.enable_group_offload(
    onload_device=onload_device,
    offload_device=offload_device,
    offload_type="leaf_level",
    use_stream=True
)
pipeline = WanPipeline.from_pretrained(
    "Wan-AI/Wan2.1-T2V-14B-Diffusers",
    vae=vae,
    transformer=transformer,
    text_encoder=text_encoder,
    dtype=torch.bfloat16
)
pipeline.to("cuda")  # or "mps", "xpu", "cpu"
prompt = """
The camera rushes from far to near in a low-angle shot, 
revealing a white ferret on a log. It plays, leaps into the water, and emerges, as the camera zooms in 
for a close-up. Water splashes berry bushes nearby, while moss, snow, and leaves blanket the ground. 
Birch trees and a light blue sky frame the scene, with ferns in the foreground. Side lighting casts dynamic 
shadows and warm highlights. Medium composition, front view, low angle, with depth of field.
"""
negative_prompt = """
Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, 
low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, 
misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards
"""
output = pipeline(
    prompt=prompt,
    negative_prompt=negative_prompt,
    num_frames=81,
    guidance_scale=5.0,
).frames[0]
export_to_video(output, "output.mp4", fps=16)
```

Otra opción para reducir la memoria es considerar la cuantización de un modelo, que almacena los pesos del modelo en un tipo de datos de menor precisión. Sin embargo, la cuantización puede afectar la calidad del vídeo dependiendo del modelo de vídeo específico. Consulte el [Resumen](../quantization/overview) de la cuantización para obtener más información sobre los diferentes backends de cuantización admitidos.

El ejemplo siguiente utiliza [bitsandbytes](../quantization/bitsandbytes) para cuantizar un modelo.

```py
# pip install ftfy
import torch
from diffusers import WanPipeline
from diffusers import AutoModel, WanPipeline
from diffusers.quantizers import PipelineQuantizationConfig
from diffusers.schedulers.scheduling_unipc_multistep import UniPCMultistepScheduler
from transformers import UMT5EncoderModel
from diffusers.utils import export_to_video
# quantize transformer and text encoder weights with bitsandbytes
pipeline_quant_config = PipelineQuantizationConfig(
  quant_backend="bitsandbytes_4bit",
  quant_kwargs={"load_in_4bit": True},
  components_to_quantize=["transformer", "text_encoder"]
)
vae = AutoModel.from_pretrained(
  "Wan-AI/Wan2.1-T2V-14B-Diffusers", subfolder="vae", dtype=torch.float32
)
pipeline = WanPipeline.from_pretrained(
  "Wan-AI/Wan2.1-T2V-14B-Diffusers", vae=vae, quantization_config=pipeline_quant_config, dtype=torch.bfloat16
)
pipeline.scheduler = UniPCMultistepScheduler.from_config(
  pipeline.scheduler.config, flow_shift=5.0
)
pipeline.to("cuda")  # or "mps", "xpu", "cpu"
pipeline.load_lora_weights("benjamin-paine/steamboat-willie-14b", adapter_name="steamboat-willie")
pipeline.set_adapters("steamboat-willie")
pipeline.enable_model_cpu_offload()
# use "steamboat willie style" to trigger the LoRA
prompt = """
steamboat willie style, golden era animation, The camera rushes from far to near in a low-angle shot, 
revealing a white ferret on a log. It plays, leaps into the water, and emerges, as the camera zooms in 
for a close-up. Water splashes berry bushes nearby, while moss, snow, and leaves blanket the ground. 
Birch trees and a light blue sky frame the scene, with ferns in the foreground. Side lighting casts 
dynamic shadows and warm highlights. Medium composition, front view, low angle, with depth of field.
"""
output = pipeline(
  prompt=prompt,
  num_frames=81,
  guidance_scale=5.0,
).frames[0]
export_to_video(output, "output.mp4", fps=16)
```

## Velocidad de inferencia

[torch.compile](https://docs.pytorch.org/tutorials/intermediate/torch_compile_tutorial.html) puede acelerar la inferencia mediante el uso de kernels optimizados. La compilación tarda más la primera vez, pero una vez compilado, es mucho más rápido. Lo ideal es compilar el pipeline una sola vez y luego usarlo múltiples veces sin cambiar nada. Un cambio, como en el tamaño de la imagen, provoca una recompilación.

El siguiente ejemplo compila el transformer en el pipeline y usa el modo `"max-autotune"` para maximizar el rendimiento.

```py
import torch
from diffusers import CogVideoXPipeline, CogVideoXTransformer3DModel
from diffusers.utils import export_to_video
pipeline = CogVideoXPipeline.from_pretrained(
  "THUDM/CogVideoX-2b",
  dtype=torch.float16
).to("cuda")  # or "mps", "xpu", "cpu"
# torch.compile
pipeline.transformer.to(memory_format=torch.channels_last)
pipeline.transformer = torch.compile(
    pipeline.transformer, mode="max-autotune", fullgraph=True
)
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, "output.mp4", fps=8)
```

Xet Storage Details

Size:: 19.3 kB
Xet hash:: 1e8879e6e433cd3cdd54923205e2c6b9b0859e66e8efb8b0e36389827254e0ca

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.

	# Generación de video

	Los modelos de generación de video extienden la generación de imágenes (que puede considerarse un video de un solo fotograma) para procesar también datos relacionados con el espacio y el tiempo. Asegurar que todos estos datos, texto, espacio y tiempo, permanezcan consistentes y alineados de un fotograma a otro es un gran desafío a la hora de generar videos largos y de alta resolución.

	Los modelos de video modernos abordan este desafío con la arquitectura de transformador de difusión (DiT). Esto reduce los costos computacionales y permite una escalabilidad más eficiente hacia datos de imágenes y videos más grandes y de mayor calidad.

	A continuación, echa un vistazo a lo que son capaces de hacer algunos de estos modelos de video.

	```py
	# pip install ftfy
	import torch
	import numpy as np
	from diffusers import AutoModel, WanPipeline
	from diffusers.hooks.group_offloading import apply_group_offloading
	from diffusers.utils import export_to_video, load_image
	from transformers import UMT5EncoderModel

	text_encoder = UMT5EncoderModel.from_pretrained("Wan-AI/Wan2.1-T2V-14B-Diffusers", subfolder="text_encoder", dtype=torch.bfloat16)
	vae = AutoModel.from_pretrained("Wan-AI/Wan2.1-T2V-14B-Diffusers", subfolder="vae", dtype=torch.float32)
	transformer = AutoModel.from_pretrained("Wan-AI/Wan2.1-T2V-14B-Diffusers", subfolder="transformer", dtype=torch.bfloat16)

	# group-offloading
	onload_device = torch.device("cuda")
	offload_device = torch.device("cpu")
	apply_group_offloading(text_encoder,
	onload_device=onload_device,
	offload_device=offload_device,
	offload_type="block_level",
	num_blocks_per_group=4
	)
	transformer.enable_group_offload(
	onload_device=onload_device,
	offload_device=offload_device,
	offload_type="leaf_level",
	use_stream=True
	)

	pipeline = WanPipeline.from_pretrained(
	"Wan-AI/Wan2.1-T2V-14B-Diffusers",
	vae=vae,
	transformer=transformer,
	text_encoder=text_encoder,
	dtype=torch.bfloat16
	)
	pipeline.to("cuda") # or "mps", "xpu", "cpu"

	prompt = """
	The camera rushes from far to near in a low-angle shot,
	revealing a white ferret on a log. It plays, leaps into the water, and emerges, as the camera zooms in
	for a close-up. Water splashes berry bushes nearby, while moss, snow, and leaves blanket the ground.
	Birch trees and a light blue sky frame the scene, with ferns in the foreground. Side lighting casts dynamic
	shadows and warm highlights. Medium composition, front view, low angle, with depth of field.
	"""
	negative_prompt = """
	Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality,
	low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured,
	misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards
	"""

	output = pipeline(
	prompt=prompt,
	negative_prompt=negative_prompt,
	num_frames=81,
	guidance_scale=5.0,
	).frames[0]
	export_to_video(output, "output.mp4", fps=16)
	```

	```py
	import torch
	from diffusers importAutoModel, HunyuanVideoPipeline
	from diffusers.quantizers import PipelineQuantizationConfig
	from diffusers.utils import export_to_video

	# quantize weights to int4 with bitsandbytes
	pipeline_quant_config = PipelineQuantizationConfig(
	quant_backend="bitsandbytes_4bit",
	quant_kwargs={
	"load_in_4bit": True,
	"bnb_4bit_quant_type": "nf4",
	"bnb_4bit_compute_dtype": torch.bfloat16
	},
	components_to_quantize="transformer"
	)

	pipeline = HunyuanVideoPipeline.from_pretrained(
	"hunyuanvideo-community/HunyuanVideo",
	quantization_config=pipeline_quant_config,
	dtype=torch.bfloat16,
	)

	# model-offloading and tiling
	pipeline.enable_model_cpu_offload()
	pipeline.vae.enable_tiling()

	prompt = "A fluffy teddy bear sits on a bed of soft pillows surrounded by children's toys."
	video = pipeline(prompt=prompt, num_frames=61, num_inference_steps=30).frames[0]
	export_to_video(video, "output.mp4", fps=15)
	```

	```py
	import torch
	from diffusers import LTXPipeline, AutoModel
	from diffusers.hooks import apply_group_offloading
	from diffusers.utils import export_to_video

	# fp8 layerwise weight-casting
	transformer = AutoModel.from_pretrained(
	"Lightricks/LTX-Video",
	subfolder="transformer",
	dtype=torch.bfloat16
	)
	transformer.enable_layerwise_casting(
	storage_dtype=torch.float8_e4m3fn, compute_dtype=torch.bfloat16
	)

	pipeline = LTXPipeline.from_pretrained("Lightricks/LTX-Video", transformer=transformer, dtype=torch.bfloat16)

	# group-offloading
	onload_device = torch.device("cuda")
	offload_device = torch.device("cpu")
	pipeline.transformer.enable_group_offload(onload_device=onload_device, offload_device=offload_device, offload_type="leaf_level", use_stream=True)
	apply_group_offloading(pipeline.text_encoder, onload_device=onload_device, offload_type="block_level", num_blocks_per_group=2)
	apply_group_offloading(pipeline.vae, onload_device=onload_device, offload_type="leaf_level")

	prompt = """
	A woman with long brown hair and light skin smiles at another woman with long blonde hair. The woman with brown hair wears a black jacket and has a small, barely noticeable mole on her right cheek. The camera angle is a close-up, focused on the woman with brown hair's face. The lighting is warm and natural, likely from the setting sun, casting a soft glow on the scene. The scene appears to be real-life footage
	"""
	negative_prompt = "worst quality, inconsistent motion, blurry, jittery, distorted"

	video = pipeline(
	prompt=prompt,
	negative_prompt=negative_prompt,
	width=768,
	height=512,
	num_frames=161,
	decode_timestep=0.03,
	decode_noise_scale=0.025,
	num_inference_steps=50,
	).frames[0]
	export_to_video(video, "output.mp4", fps=24)
	```

	Esta guía cubrirá los fundamentos de la generación de video, como qué parámetros configurar y cómo reducir su uso de memoria.

	> [!TIP]
	> Si te interesa aprender más sobre cómo usar un modelo específico, consulta la tarjeta de modelo de su API de pipeline.

	## Parámetros de la pipeline

	Hay varios parámetros que configurar en el pipeline que afectarán a la calidad o la velocidad de la generación de video. Experimentar con diferentes valores de parámetros es importante para descubrir el equilibrio adecuado entre calidad y velocidad.

	### num_frames

	Un fotograma es una imagen fija que se reproduce en una secuencia de otros fotogramas para crear movimiento o un video. Controle el número de fotogramas generados por segundo con `num_frames`. Aumentar `num_frames` mejora la suavidad percibida del movimiento y la coherencia visual, lo que es especialmente importante para videos con contenido dinámico. Un valor más alto de `num_frames` también aumenta la duración del video.

	Algunos modelos de vídeo requieren valores más específicos de `num_frames` para la inferencia. Por ejemplo, [HunyuanVideoPipeline](/docs/diffusers/main/es/api/pipelines/hunyuan_video#diffusers.HunyuanVideoPipeline) recomienda calcular `num_frames` con `(4 * num_frames) +1`. Consulta siempre la tarjeta de modelo de la API de un pipeline para ver si hay un valor recomendado.

	```py
	import torch
	from diffusers import LTXPipeline
	from diffusers.utils import export_to_video

	pipeline = LTXPipeline.from_pretrained(
	"Lightricks/LTX-Video", dtype=torch.bfloat16
	).to("cuda") # or "mps", "xpu", "cpu"

	prompt = """
	A woman with long brown hair and light skin smiles at another woman with long blonde hair. The woman
	with brown hair wears a black jacket and has a small, barely noticeable mole on her right cheek. The
	camera angle is a close-up, focused on the woman with brown hair's face. The lighting is warm and
	natural, likely from the setting sun, casting a soft glow on the scene. The scene appears to be
	real-life footage
	"""

	video = pipeline(
	prompt=prompt,
	negative_prompt=negative_prompt,
	width=768,
	height=512,
	num_frames=161,
	decode_timestep=0.03,
	decode_noise_scale=0.025,
	num_inference_steps=50,
	).frames[0]
	export_to_video(video, "output.mp4", fps=24)
	```

	### guidance_scale

	La escala de guía o "cfg" controla hasta qué punto los fotogramas generados se ajustan a la condición de entrada (texto, imagen o ambos). Aumentar `guidance_scale` genera fotogramas que se asemejan más a las condiciones de entrada e incluyen detalles más finos, pero con el riesgo de introducir artefactos y reducir la diversidad de la salida. Valores más bajos de `guidance_scale` fomentan un ajuste más laxo al prompt y una mayor variedad en la salida, aunque los detalles pueden no ser tan buenos. Si es demasiado bajo, es posible que ignore por completo el prompt y genere ruido aleatorio.

	```py
	import torch
	from diffusers import CogVideoXPipeline, CogVideoXTransformer3DModel
	from diffusers.utils import export_to_video

	pipeline = CogVideoXPipeline.from_pretrained(
	"THUDM/CogVideoX-2b",
	dtype=torch.float16
	).to("cuda") # or "mps", "xpu", "cpu"

	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, "output.mp4", fps=8)
	```

	### negative_prompt

	Un prompt negativo es útil para excluir elementos que no deseas ver en el video generado. Se utiliza comúnmente para refinar la calidad y la alineación del video generado, alejando al modelo de elementos no deseados como "blurry, distorted, ugly". Esto puede crear videos más limpios y enfocados.

	```py
	# pip install ftfy
	import torch
	from diffusers import WanPipeline
	from diffusers.schedulers.scheduling_unipc_multistep import UniPCMultistepScheduler
	from diffusers.utils import export_to_video

	vae = AutoencoderKLWan.from_pretrained(
	"Wan-AI/Wan2.1-T2V-14B-Diffusers", subfolder="vae", dtype=torch.float32
	)
	pipeline = WanPipeline.from_pretrained(
	"Wan-AI/Wan2.1-T2V-14B-Diffusers", vae=vae, dtype=torch.bfloat16
	)
	pipeline.scheduler = UniPCMultistepScheduler.from_config(
	pipeline.scheduler.config, flow_shift=5.0
	)
	pipeline.to("cuda") # or "mps", "xpu", "cpu"

	pipeline.load_lora_weights("benjamin-paine/steamboat-willie-14b", adapter_name="steamboat-willie")
	pipeline.set_adapters("steamboat-willie")

	pipeline.enable_model_cpu_offload()

	# use "steamboat willie style" to trigger the LoRA
	prompt = """
	steamboat willie style, golden era animation, The camera rushes from far to near in a low-angle shot,
	revealing a white ferret on a log. It plays, leaps into the water, and emerges, as the camera zooms in
	for a close-up. Water splashes berry bushes nearby, while moss, snow, and leaves blanket the ground.
	Birch trees and a light blue sky frame the scene, with ferns in the foreground. Side lighting casts
	dynamic shadows and warm highlights. Medium composition, front view, low angle, with depth of field.
	"""

	output = pipeline(
	prompt=prompt,
	num_frames=81,
	guidance_scale=5.0,
	).frames[0]
	export_to_video(output, "output.mp4", fps=16)
	```

	## Reducir el uso de memoria

	Los modelos de video recientes, como [HunyuanVideoPipeline](/docs/diffusers/main/es/api/pipelines/hunyuan_video#diffusers.HunyuanVideoPipeline) y [WanPipeline](/docs/diffusers/main/es/api/pipelines/wan#diffusers.WanPipeline), que tienen más de 10 mil millones de parámetros, requieren mucha memoria y a menudo superan la memoria disponible en el hardware de consumo. Diffusers ofrece varias técnicas para reducir los requisitos de memoria de estos modelos grandes.

	> [!TIP]
	> Consulte la guía [Reduce memory usage](../optimization/memory) para obtener más detalles sobre otras técnicas de ahorro de memoria.

	Una de estas técnicas es [group-offloading](../optimization/memory#group-offloading), que descarga grupos de capas internas del modelo (como `torch.nn.Sequential`) a la CPU cuando no se están utilizando. Estas capas solo se cargan cuando son necesarias para el cálculo, evitando así almacenar todos los componentes del modelo en la GPU. Para un modelo de 14B parámetros como [WanPipeline](/docs/diffusers/main/es/api/pipelines/wan#diffusers.WanPipeline), el group-offloading puede reducir la memoria requerida a ~13GB de VRAM.

	```py
	# pip install ftfy
	import torch
	import numpy as np
	from diffusers import AutoModel, WanPipeline
	from diffusers.hooks.group_offloading import apply_group_offloading
	from diffusers.utils import export_to_video, load_image
	from transformers import UMT5EncoderModel

	text_encoder = UMT5EncoderModel.from_pretrained("Wan-AI/Wan2.1-T2V-14B-Diffusers", subfolder="text_encoder", dtype=torch.bfloat16)
	vae = AutoModel.from_pretrained("Wan-AI/Wan2.1-T2V-14B-Diffusers", subfolder="vae", dtype=torch.float32)
	transformer = AutoModel.from_pretrained("Wan-AI/Wan2.1-T2V-14B-Diffusers", subfolder="transformer", dtype=torch.bfloat16)

	# group-offloading
	onload_device = torch.device("cuda")
	offload_device = torch.device("cpu")
	apply_group_offloading(text_encoder,
	onload_device=onload_device,
	offload_device=offload_device,
	offload_type="block_level",
	num_blocks_per_group=4
	)
	transformer.enable_group_offload(
	onload_device=onload_device,
	offload_device=offload_device,
	offload_type="leaf_level",
	use_stream=True
	)

	pipeline = WanPipeline.from_pretrained(
	"Wan-AI/Wan2.1-T2V-14B-Diffusers",
	vae=vae,
	transformer=transformer,
	text_encoder=text_encoder,
	dtype=torch.bfloat16
	)
	pipeline.to("cuda") # or "mps", "xpu", "cpu"

	prompt = """
	The camera rushes from far to near in a low-angle shot,
	revealing a white ferret on a log. It plays, leaps into the water, and emerges, as the camera zooms in
	for a close-up. Water splashes berry bushes nearby, while moss, snow, and leaves blanket the ground.
	Birch trees and a light blue sky frame the scene, with ferns in the foreground. Side lighting casts dynamic
	shadows and warm highlights. Medium composition, front view, low angle, with depth of field.
	"""
	negative_prompt = """
	Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality,
	low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured,
	misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards
	"""

	output = pipeline(
	prompt=prompt,
	negative_prompt=negative_prompt,
	num_frames=81,
	guidance_scale=5.0,
	).frames[0]
	export_to_video(output, "output.mp4", fps=16)
	```

	Otra opción para reducir la memoria es considerar la cuantización de un modelo, que almacena los pesos del modelo en un tipo de datos de menor precisión. Sin embargo, la cuantización puede afectar la calidad del vídeo dependiendo del modelo de vídeo específico. Consulte el [Resumen](../quantization/overview) de la cuantización para obtener más información sobre los diferentes backends de cuantización admitidos.

	El ejemplo siguiente utiliza [bitsandbytes](../quantization/bitsandbytes) para cuantizar un modelo.

	```py
	# pip install ftfy

	import torch
	from diffusers import WanPipeline
	from diffusers import AutoModel, WanPipeline
	from diffusers.quantizers import PipelineQuantizationConfig
	from diffusers.schedulers.scheduling_unipc_multistep import UniPCMultistepScheduler
	from transformers import UMT5EncoderModel
	from diffusers.utils import export_to_video

	# quantize transformer and text encoder weights with bitsandbytes
	pipeline_quant_config = PipelineQuantizationConfig(
	quant_backend="bitsandbytes_4bit",
	quant_kwargs={"load_in_4bit": True},
	components_to_quantize=["transformer", "text_encoder"]
	)

	vae = AutoModel.from_pretrained(
	"Wan-AI/Wan2.1-T2V-14B-Diffusers", subfolder="vae", dtype=torch.float32
	)
	pipeline = WanPipeline.from_pretrained(
	"Wan-AI/Wan2.1-T2V-14B-Diffusers", vae=vae, quantization_config=pipeline_quant_config, dtype=torch.bfloat16
	)
	pipeline.scheduler = UniPCMultistepScheduler.from_config(
	pipeline.scheduler.config, flow_shift=5.0
	)
	pipeline.to("cuda") # or "mps", "xpu", "cpu"

	pipeline.load_lora_weights("benjamin-paine/steamboat-willie-14b", adapter_name="steamboat-willie")
	pipeline.set_adapters("steamboat-willie")

	pipeline.enable_model_cpu_offload()

	# use "steamboat willie style" to trigger the LoRA
	prompt = """
	steamboat willie style, golden era animation, The camera rushes from far to near in a low-angle shot,
	revealing a white ferret on a log. It plays, leaps into the water, and emerges, as the camera zooms in
	for a close-up. Water splashes berry bushes nearby, while moss, snow, and leaves blanket the ground.
	Birch trees and a light blue sky frame the scene, with ferns in the foreground. Side lighting casts
	dynamic shadows and warm highlights. Medium composition, front view, low angle, with depth of field.
	"""

	output = pipeline(
	prompt=prompt,
	num_frames=81,
	guidance_scale=5.0,
	).frames[0]
	export_to_video(output, "output.mp4", fps=16)
	```

	## Velocidad de inferencia

	[torch.compile](https://docs.pytorch.org/tutorials/intermediate/torch_compile_tutorial.html) puede acelerar la inferencia mediante el uso de kernels optimizados. La compilación tarda más la primera vez, pero una vez compilado, es mucho más rápido. Lo ideal es compilar el pipeline una sola vez y luego usarlo múltiples veces sin cambiar nada. Un cambio, como en el tamaño de la imagen, provoca una recompilación.

	El siguiente ejemplo compila el transformer en el pipeline y usa el modo `"max-autotune"` para maximizar el rendimiento.

	```py
	import torch
	from diffusers import CogVideoXPipeline, CogVideoXTransformer3DModel
	from diffusers.utils import export_to_video

	pipeline = CogVideoXPipeline.from_pretrained(
	"THUDM/CogVideoX-2b",
	dtype=torch.float16
	).to("cuda") # or "mps", "xpu", "cpu"

	# torch.compile
	pipeline.transformer.to(memory_format=torch.channels_last)
	pipeline.transformer = torch.compile(
	pipeline.transformer, mode="max-autotune", fullgraph=True
	)

	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, "output.mp4", fps=8)
	```