Diffusers documentation

Inferência remota

Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

Inferência remota

Esta é atualmente uma funcionalidade experimental e, se você tiver algum feedback, sinta-se à vontade para deixá-lo aqui.

A inferência remota transfere o processo de decodificação e codificação para um endpoint remoto, aliviando os requisitos de memória para a inferência local com modelos grandes. Este recurso é impulsionado por Inference Endpoints. Consulte a tabela abaixo para os modelos e endpoints suportados.

ModelEndpointCheckpointSuporte
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

Este guia mostrará como codificar e decodificar latentes com inferência remota.

Codificação

O Encoding converte imagens e vídeos em representações latentes. A tabela no topo desta página lista os modelos que suportam encoding.

Passe uma imagem para remote_encode() para codificá-la. Os valores específicos de scaling_factor e shift_factor para cada modelo podem ser encontrados na referência da 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
)

Decodificação

O decodificação converte representações latentes de volta em imagens ou vídeos. A tabela no topo desta página lista os modelos que suportam decodificação.

Defina o tipo de saída como "latent" no pipeline e defina o vae como None. Passe os latentes para a função remote_decode(). Para o Flux, os latentes são empacotados, portanto, a height e a width também precisam ser passadas. Os valores específicos de scaling_factor e shift_factor para cada modelo podem ser encontrados na referência da API de Remote inference.

Flux
HunyuanVideo
import torch
from diffusers import FluxPipeline
from diffusers.utils.remote_utils import remote_decode

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")

Fila

A inferência remota suporta enfileiramento para processar múltiplas solicitações de geração. Enquanto o latente atual está sendo decodificado, você pode enfileirar o próximo prompt.

import queue
import threading
import torch
from IPython.display import display
from diffusers import StableDiffusionXLPipeline
from diffusers.utils.remote_utils import remote_decode

def decode_worker(q: queue.Queue):
    while True:
        item = q.get()
        if item is None:
            break
        image = remote_decode(
            endpoint="https://x2dmsqunjd6k9prw.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(
    "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(pipeline.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

As tabelas demonstram os requisitos de memória para codificação e decodificação com Stable Diffusion v1.5 e SDXL em diferentes GPUs.

Para a maioria dessas GPUs, o uso de memória determina se outros modelos (codificadores de texto, UNet/transformer) precisam ser descarregados ou se é necessário o uso de codificação em blocos. As duas últimas técnicas aumentam o tempo de inferência e impactam a qualidade.

Encoding - Stable Diffusion v1.5
GPUResoluçãoTempo (segundos)Memória (%)Tempo em blocos (segundos)Memória em blocos (%)
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
GPUResoluçãoTempo (segundos)Memória Consumida (%)Tempo em blocos (segundos)Memória em blocos (%)
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
GPUResoluçãoTempo (segundos)Memória (%)Tempo em blocos (segundos)Memória em blocos (%)
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
GPUResoluçãoTempo (segundos)Memória Consumida (%)Tempo em blocos (segundos)Memória em blocos (%)
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