Diffusers documentation

Inferencia remota

You are viewing main version, which requires installation from source. If you'd like regular pip install, checkout the latest stable version (v0.42.1).
Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

Inferencia remota

Esta es actualmente una función experimental, y si tienes algún comentario, no dudes en dejarlo aquí.

La inferencia remota delega el proceso de decodificación y codificación en un punto de acceso remoto para aliviar los requisitos de memoria de la inferencia local con modelos grandes. Esta función se basa en Inference Endpoints. Consulte la tabla siguiente para conocer los modelos y el punto de acceso compatibles.

ModeloEndpointCheckpointSoporte
Stable Diffusion v1https://q1bj3bpq6kzilnsu.us-east-1.aws.endpoints.huggingface.cloudstabilityai/sd-vae-ft-mseencode/decode
Stable Diffusion XLhttps://x2dmsqunjd6k9prw.us-east-1.aws.endpoints.huggingface.cloudmadebyollin/sdxl-vae-fp16-fixencode/decode
Fluxhttps://whhx50ex1aryqvw6.us-east-1.aws.endpoints.huggingface.cloudblack-forest-labs/FLUX.1-schnellencode/decode
HunyuanVideohttps://o7ywnmrahorts457.us-east-1.aws.endpoints.huggingface.cloudhunyuanvideo-community/HunyuanVideodecode

Esta guía te mostrará cómo codificar y decodificar latentes con inferencia remota.

Codificación

Encoding convierte imágenes y videos en representaciones latentes. Consulte la tabla siguiente para conocer los VAE admitidos.

Pase una imagen a ~utils.remote_encode para codificarla. Los valores específicos de scaling_factor y shift_factor para cada modelo se pueden encontrar en la referencia de la API de Remote inference.

import torch
from diffusers import FluxPipeline
from diffusers.utils import load_image
from diffusers.utils.remote_utils import remote_encode

pipeline = FluxPipeline.from_pretrained(
    "black-forest-labs/FLUX.1-schnell",
    dtype=torch.float16,
    vae=None,
    device_map="cuda"  # or "mps", "xpu", "cpu"
)

init_image = load_image(
    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/astronaut.jpg"
)
init_image = init_image.resize((768, 512))

init_latent = remote_encode(
    endpoint="https://whhx50ex1aryqvw6.us-east-1.aws.endpoints.huggingface.cloud",
    image=init_image,
    scaling_factor=0.3611,
    shift_factor=0.1159
)

Decodificación

El decodificado convierte las representaciones latentes de nuevo en imágenes o videos. Consulte la tabla siguiente para conocer los VAE disponibles y compatibles.

Establezca el tipo de salida como "latent" en el pipeline y establezca vae en None. Pase los latentes a la función remote_decode(). En el caso de Flux, los latentes están empaquetados, por lo que también es necesario pasar height y width. Los valores específicos de scaling_factor y shift_factor para cada modelo se pueden encontrar en la referencia de la API de Remote inference.

Flux
HunyuanVideo
from diffusers import FluxPipeline

pipeline = FluxPipeline.from_pretrained(
    "black-forest-labs/FLUX.1-schnell",
    dtype=torch.bfloat16,
    vae=None,
    device_map="cuda"  # or "mps", "xpu", "cpu"
)

prompt = """
A photorealistic Apollo-era photograph of a cat in a small astronaut suit with a bubble helmet, standing on the Moon and holding a flagpole planted in the dusty lunar soil. The flag shows a colorful paw-print emblem. Earth glows in the black sky above the stark gray surface, with sharp shadows and high-contrast lighting like vintage NASA photos.
"""

latent = pipeline(
    prompt=prompt,
    guidance_scale=0.0,
    num_inference_steps=4,
    output_type="latent",
).images
image = remote_decode(
    endpoint="https://whhx50ex1aryqvw6.us-east-1.aws.endpoints.huggingface.cloud/",
    tensor=latent,
    height=1024,
    width=1024,
    scaling_factor=0.3611,
    shift_factor=0.1159,
)
image.save("image.jpg")

Cola

La inferencia remota admite la colocación en cola para procesar múltiples solicitudes de generación. Mientras se decodifica el latente actual, puedes colocar el siguiente prompt en la cola.

import queue
import threading
from IPython.display import display
from diffusers import StableDiffusionXLPipeline

def decode_worker(q: queue.Queue):
    while True:
        item = q.get()
        if item is None:
            break
        image = remote_decode(
            endpoint="https://q1bj3bpq6kzilnsu.us-east-1.aws.endpoints.huggingface.cloud/",
            tensor=item,
            scaling_factor=0.13025,
        )
        display(image)
        q.task_done()

q = queue.Queue()
thread = threading.Thread(target=decode_worker, args=(q,), daemon=True)
thread.start()

def decode(latent: torch.Tensor):
    q.put(latent)

prompts = [
    "A grainy Apollo-era style photograph of a cat in a snug astronaut suit with a bubble helmet, standing on the lunar surface and gripping a flag with a paw-print emblem. The gray Moon landscape stretches behind it, Earth glowing vividly in the black sky, shadows crisp and high-contrast.",
    "A vintage 1960s sci-fi pulp magazine cover illustration of a heroic cat astronaut planting a flag on the Moon. Bold, saturated colors, exaggerated space gear, playful typography floating in the background, Earth painted in bright blues and greens.",
    "A hyper-detailed cinematic shot of a cat astronaut on the Moon holding a fluttering flag, fur visible through the helmet glass, lunar dust scattering under its feet. The vastness of space and Earth in the distance create an epic, awe-inspiring tone.",
    "A colorful cartoon drawing of a happy cat wearing a chunky, oversized spacesuit, proudly holding a flag with a big paw print on it. The Moon’s surface is simplified with craters drawn like doodles, and Earth in the sky has a smiling face.",
    "A monochrome 1969-style press photo of a “first cat on the Moon” moment. The cat, in a tiny astronaut suit, stands by a planted flag, with grainy textures, scratches, and a blurred Earth in the background, mimicking old archival space photos."
]


pipeline = StableDiffusionXLPipeline.from_pretrained(
    "https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0",
    dtype=torch.float16,
    vae=None,
    device_map="cuda"  # or "mps", "xpu", "cpu"
)

pipeline.unet = pipeline.unet.to(memory_format=torch.channels_last)
pipeline.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)

_ = pipeline(
    prompt=prompts[0],
    output_type="latent",
)

for prompt in prompts:
    latent = pipeline(
        prompt=prompt,
        output_type="latent",
    ).images
    decode(latent)

q.put(None)
thread.join()

Benchmarks

Las tablas muestran los requisitos de memoria para la codificación y la decodificación con Stable Diffusion v1.5 y SDXL en diferentes GPUs.

Para la mayoría de estas GPUs, el uso de memoria determina si otros modelos (codificadores de texto, UNet/transformer) deben descargarse o si se requiere codificación por mosaicos. Estas dos últimas técnicas aumentan el tiempo de inferencia y afectan la calidad.

Encoding - Stable Diffusion v1.5
GPUResoluciónTiempo (segundos)Memoria (%)Tiempo en mosaico (segundos)Memoria en mosaicos (%)
NVIDIA GeForce RTX 4090512x5120.0153.519010.0153.51901
NVIDIA GeForce RTX 4090256x2560.0041.31540.0051.3154
NVIDIA GeForce RTX 40902048x20480.40247.18520.4963.51901
NVIDIA GeForce RTX 40901024x10240.07812.26580.0943.51901
NVIDIA GeForce RTX 4080 SUPER512x5120.0235.301050.0235.30105
NVIDIA GeForce RTX 4080 SUPER256x2560.0061.981520.0061.98152
NVIDIA GeForce RTX 4080 SUPER2048x20480.57471.080.6565.30105
NVIDIA GeForce RTX 4080 SUPER1024x10240.11118.47720.145.30105
NVIDIA GeForce RTX 3090512x5120.0323.527820.0323.52782
NVIDIA GeForce RTX 3090256x2560.011.318690.0091.31869
NVIDIA GeForce RTX 30902048x20480.74247.30330.9543.52782
NVIDIA GeForce RTX 30901024x10240.13612.29650.2073.52782
NVIDIA GeForce RTX 3080512x5120.0368.517610.0368.51761
NVIDIA GeForce RTX 3080256x2560.013.183870.013.18387
NVIDIA GeForce RTX 30802048x20480.86386.74241.1918.51761
NVIDIA GeForce RTX 30801024x10240.15729.68880.2278.51761
NVIDIA GeForce RTX 3070512x5120.05110.69410.05110.6941
NVIDIA GeForce RTX 3070256x2560.0153.997430.0153.99743
NVIDIA GeForce RTX 30702048x20481.21796.0541.48210.6941
NVIDIA GeForce RTX 30701024x10240.22337.27510.32710.6941
Encoding SDXL
GPUResoluciónTiempo (segundos)Memoria consumida (%)Tiempo en mosaico (segundos)Memoria en mosaicos (%)
NVIDIA GeForce RTX 4090512x5120.0294.957070.0294.95707
NVIDIA GeForce RTX 4090256x2560.0072.296660.0072.29666
NVIDIA GeForce RTX 40902048x20480.87366.34520.86315.5649
NVIDIA GeForce RTX 40901024x10240.14215.54790.14315.5479
NVIDIA GeForce RTX 4080 SUPER512x5120.0447.467350.0447.46735
NVIDIA GeForce RTX 4080 SUPER256x2560.013.45970.013.4597
NVIDIA GeForce RTX 4080 SUPER2048x20481.31787.16151.29123.447
NVIDIA GeForce RTX 4080 SUPER1024x10240.21323.42150.21423.4215
NVIDIA GeForce RTX 3090512x5120.0585.656380.0585.65638
NVIDIA GeForce RTX 3090256x2560.0162.450810.0162.45081
NVIDIA GeForce RTX 30902048x20481.75577.82391.61418.4193
NVIDIA GeForce RTX 30901024x10240.26518.40230.26518.4023
NVIDIA GeForce RTX 3080512x5120.06413.65680.06413.6568
NVIDIA GeForce RTX 3080256x2560.0185.917280.0185.91728
NVIDIA GeForce RTX 30802048x2048OOMOOM1.86644.4717
NVIDIA GeForce RTX 30801024x10240.30244.43080.30244.4308
NVIDIA GeForce RTX 3070512x5120.09317.14650.09317.1465
NVIDIA GeForce RTX 3070256x2560.0257.429310.0267.42931
NVIDIA GeForce RTX 30702048x2048OOMOOM2.67455.8355
NVIDIA GeForce RTX 30701024x10240.44355.78410.44355.7841
Decoding - Stable Diffusion v1.5
GPUResoluciónTiempo (segundos)Memoria (%)Tiempo en mosaico (segundos)Memoria en mosaicos (%)
NVIDIA GeForce RTX 4090512x5120.0315.60%0.031 (0%)5.60%
NVIDIA GeForce RTX 40901024x10240.14820.00%0.301 (+103%)5.60%
NVIDIA GeForce RTX 4080512x5120.058.40%0.050 (0%)8.40%
NVIDIA GeForce RTX 40801024x10240.22430.00%0.356 (+59%)8.40%
NVIDIA GeForce RTX 4070 Ti512x5120.06611.30%0.066 (0%)11.30%
NVIDIA GeForce RTX 4070 Ti1024x10240.28440.50%0.454 (+60%)11.40%
NVIDIA GeForce RTX 3090512x5120.0625.20%0.062 (0%)5.20%
NVIDIA GeForce RTX 30901024x10240.25318.50%0.464 (+83%)5.20%
NVIDIA GeForce RTX 3080512x5120.0712.80%0.070 (0%)12.80%
NVIDIA GeForce RTX 30801024x10240.28645.30%0.466 (+63%)12.90%
NVIDIA GeForce RTX 3070512x5120.10215.90%0.102 (0%)15.90%
NVIDIA GeForce RTX 30701024x10240.42156.30%0.746 (+77%)16.00%
Decoding SDXL
GPUResoluciónTiempo (segundos)Memoria consumida (%)Tiempo en mosaico (segundos)Memoria en mosaicos (%)
NVIDIA GeForce RTX 4090512x5120.05710.00%0.057 (0%)10.00%
NVIDIA GeForce RTX 40901024x10240.25635.50%0.257 (+0.4%)35.50%
NVIDIA GeForce RTX 4080512x5120.09215.00%0.092 (0%)15.00%
NVIDIA GeForce RTX 40801024x10240.40653.30%0.406 (0%)53.30%
NVIDIA GeForce RTX 4070 Ti512x5120.12120.20%0.120 (-0.8%)20.20%
NVIDIA GeForce RTX 4070 Ti1024x10240.51972.00%0.519 (0%)72.00%
NVIDIA GeForce RTX 3090512x5120.10710.50%0.107 (0%)10.50%
NVIDIA GeForce RTX 30901024x10240.45938.00%0.460 (+0.2%)38.00%
NVIDIA GeForce RTX 3080512x5120.12125.60%0.121 (0%)25.60%
NVIDIA GeForce RTX 30801024x10240.52493.00%0.524 (0%)93.00%
NVIDIA GeForce RTX 3070512x5120.18331.80%0.183 (0%)31.80%
NVIDIA GeForce RTX 30701024x10240.79496.40%0.794 (0%)96.40%

Recursos

Update on GitHub