tests/pipelines/stable_diffusion_gligen/test_stable_diffusion_gligen.py

# coding=utf-8
# Copyright 2024 HuggingFace Inc.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

import unittest

import numpy as np
import torch
from transformers import CLIPTextConfig, CLIPTextModel, CLIPTokenizer

from diffusers import (
    AutoencoderKL,
    DDIMScheduler,
    EulerAncestralDiscreteScheduler,
    StableDiffusionGLIGENPipeline,
    UNet2DConditionModel,
)
from diffusers.utils.testing_utils import enable_full_determinism

from ..pipeline_params import (
    TEXT_TO_IMAGE_BATCH_PARAMS,
    TEXT_TO_IMAGE_IMAGE_PARAMS,
    TEXT_TO_IMAGE_PARAMS,
)
from ..test_pipelines_common import (
    PipelineFromPipeTesterMixin,
    PipelineKarrasSchedulerTesterMixin,
    PipelineLatentTesterMixin,
    PipelineTesterMixin,
)


enable_full_determinism()


class GligenPipelineFastTests(
    PipelineLatentTesterMixin,
    PipelineKarrasSchedulerTesterMixin,
    PipelineTesterMixin,
    PipelineFromPipeTesterMixin,
    unittest.TestCase,
):
    pipeline_class = StableDiffusionGLIGENPipeline
    params = TEXT_TO_IMAGE_PARAMS | {"gligen_phrases", "gligen_boxes"}
    batch_params = TEXT_TO_IMAGE_BATCH_PARAMS
    image_params = TEXT_TO_IMAGE_IMAGE_PARAMS
    image_latents_params = TEXT_TO_IMAGE_IMAGE_PARAMS

    def get_dummy_components(self):
        torch.manual_seed(0)
        unet = UNet2DConditionModel(
            block_out_channels=(32, 64),
            layers_per_block=2,
            sample_size=32,
            in_channels=4,
            out_channels=4,
            down_block_types=("DownBlock2D", "CrossAttnDownBlock2D"),
            up_block_types=("CrossAttnUpBlock2D", "UpBlock2D"),
            cross_attention_dim=32,
            attention_type="gated",
        )
        # unet.position_net = PositionNet(32,32)
        scheduler = DDIMScheduler(
            beta_start=0.00085,
            beta_end=0.012,
            beta_schedule="scaled_linear",
            clip_sample=False,
            set_alpha_to_one=False,
        )
        torch.manual_seed(0)
        vae = AutoencoderKL(
            block_out_channels=[32, 64],
            in_channels=3,
            out_channels=3,
            down_block_types=["DownEncoderBlock2D", "DownEncoderBlock2D"],
            up_block_types=["UpDecoderBlock2D", "UpDecoderBlock2D"],
            latent_channels=4,
            sample_size=128,
        )
        torch.manual_seed(0)
        text_encoder_config = CLIPTextConfig(
            bos_token_id=0,
            eos_token_id=2,
            hidden_size=32,
            intermediate_size=37,
            layer_norm_eps=1e-05,
            num_attention_heads=4,
            num_hidden_layers=5,
            pad_token_id=1,
            vocab_size=1000,
        )
        text_encoder = CLIPTextModel(text_encoder_config)
        tokenizer = CLIPTokenizer.from_pretrained("hf-internal-testing/tiny-random-clip")

        components = {
            "unet": unet,
            "scheduler": scheduler,
            "vae": vae,
            "text_encoder": text_encoder,
            "tokenizer": tokenizer,
            "safety_checker": None,
            "feature_extractor": None,
        }
        return components

    def get_dummy_inputs(self, device, seed=0):
        if str(device).startswith("mps"):
            generator = torch.manual_seed(seed)
        else:
            generator = torch.Generator(device=device).manual_seed(seed)
        inputs = {
            "prompt": "A modern livingroom",
            "generator": generator,
            "num_inference_steps": 2,
            "guidance_scale": 6.0,
            "gligen_phrases": ["a birthday cake"],
            "gligen_boxes": [[0.2676, 0.6088, 0.4773, 0.7183]],
            "output_type": "np",
        }
        return inputs

    def test_stable_diffusion_gligen_default_case(self):
        device = "cpu"  # ensure determinism for the device-dependent torch.Generator
        components = self.get_dummy_components()
        sd_pipe = StableDiffusionGLIGENPipeline(**components)
        sd_pipe = sd_pipe.to(device)
        sd_pipe.set_progress_bar_config(disable=None)

        inputs = self.get_dummy_inputs(device)
        image = sd_pipe(**inputs).images
        image_slice = image[0, -3:, -3:, -1]

        assert image.shape == (1, 64, 64, 3)
        expected_slice = np.array([0.5069, 0.5561, 0.4577, 0.4792, 0.5203, 0.4089, 0.5039, 0.4919, 0.4499])

        assert np.abs(image_slice.flatten() - expected_slice).max() < 1e-2

    def test_stable_diffusion_gligen_k_euler_ancestral(self):
        device = "cpu"  # ensure determinism for the device-dependent torch.Generator
        components = self.get_dummy_components()
        sd_pipe = StableDiffusionGLIGENPipeline(**components)
        sd_pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(sd_pipe.scheduler.config)
        sd_pipe = sd_pipe.to(device)
        sd_pipe.set_progress_bar_config(disable=None)

        inputs = self.get_dummy_inputs(device)
        output = sd_pipe(**inputs)
        image = output.images
        image_slice = image[0, -3:, -3:, -1]

        assert image.shape == (1, 64, 64, 3)
        expected_slice = np.array([0.425, 0.494, 0.429, 0.469, 0.525, 0.417, 0.533, 0.5, 0.47])

        assert np.abs(image_slice.flatten() - expected_slice).max() < 1e-2

    def test_attention_slicing_forward_pass(self):
        super().test_attention_slicing_forward_pass(expected_max_diff=3e-3)

    def test_inference_batch_single_identical(self):
        super().test_inference_batch_single_identical(batch_size=3, expected_max_diff=3e-3)