Home - News ( United States | United Kingdom | Italy | Germany ) - Football scores

Showing content from https://diffengine.readthedocs.io/en/latest/run_guides/run_instruct_pix2pix.html below:

Website Navigation

• diffengine

InstructPix2Pix Training — diffengine 1.0.0 documentation

You can also check configs/instruct_pix2pix/README.md file.

All configuration files are placed under the configs/instruct_pix2pix folder.

Following is the example config fixed from the stable_diffusion_xl_instruct_pix2pix config file in configs/instruct_pix2pix/stable_diffusion_xl_instruct_pix2pix.py:

from mmengine.config import read_base

with read_base():
    from .._base_.datasets.instructpix2pix_xl import *
    from .._base_.default_runtime import *
    from .._base_.models.stable_diffusion_xl_instruct_pix2pix import *
    from .._base_.schedules.stable_diffusion_3e import *


optim_wrapper.update(
    optimizer=dict(
        type="Adafactor",
        lr=3e-5,
        weight_decay=1e-2,
        scale_parameter=False,
        relative_step=False),
    accumulative_counts=4)

Run train

# single gpu
$ diffengine train ${CONFIG_FILE}
# multi gpus
$ NPROC_PER_NODE=${GPU_NUM} diffengine train ${CONFIG_FILE}

# Example
$ diffengine train stable_diffusion_xl_instruct_pix2pix

Once you have trained a model, specify the path to the saved model and utilize it for inference using the diffusers.pipeline module.

Before inferencing, we should convert weights for diffusers format,

$ diffengine convert ${CONFIG_FILE} ${INPUT_FILENAME} ${OUTPUT_DIR} --save-keys ${SAVE_KEYS}
# Example
$ diffengine convert stable_diffusion_xl_instruct_pix2pix work_dirs/stable_diffusion_xl_instruct_pix2pix/epoch_3.pth work_dirs/stable_diffusion_xl_instruct_pix2pix --save-keys unet

Then we can run inference.

import torch
from diffusers import StableDiffusionXLInstructPix2PixPipeline, UNet2DConditionModel, AutoencoderKL
from diffusers.utils import load_image

checkpoint = 'work_dirs/stable_diffusion_xl_instruct_pix2pix'
prompt = 'make the mountains snowy'
condition_image = load_image(
    'https://huggingface.co/datasets/diffusers/diffusers-images-docs/resolve/main/mountain.png'
).resize((1024, 1024))

unet = UNet2DConditionModel.from_pretrained(
    checkpoint, subfolder='unet', torch_dtype=torch.float16)

vae = AutoencoderKL.from_pretrained(
    'madebyollin/sdxl-vae-fp16-fix',
    torch_dtype=torch.float16,
)
pipe = StableDiffusionXLInstructPix2PixPipeline.from_pretrained(
    'stabilityai/stable-diffusion-xl-base-1.0', unet=unet, vae=vae, torch_dtype=torch.float16)
pipe.to('cuda')

image = pipe(
    prompt,
    image=condition_image,
    num_inference_steps=50,
).images[0]
image.save('demo.png')

You can check configs/instruct_pix2pix/README.md for more details.

RetroSearch is an open source project built by @garambo | Open a GitHub Issue

Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo

HTML: 3.2 | Encoding: UTF-8 | Version: 0.7.4