Add Latent Consistency Models Pipeline

docs/source/en/_toctree.yml

@@ -250,6 +250,8 @@
       title: Kandinsky
     - local: api/pipelines/kandinsky_v22
       title: Kandinsky 2.2
+    - local: api/pipelines/latent_consistency_models
+      title: Latent Consistency Models
     - local: api/pipelines/latent_diffusion
       title: Latent Diffusion
     - local: api/pipelines/panorama
@@ -366,6 +368,8 @@
       title: KDPM2AncestralDiscreteScheduler
     - local: api/schedulers/dpm_discrete
       title: KDPM2DiscreteScheduler
+    - local: api/schedulers/lcm
+      title: LCMScheduler
     - local: api/schedulers/lms_discrete
       title: LMSDiscreteScheduler
     - local: api/schedulers/pndm

docs/source/en/api/pipelines/latent_consistency_models.md

@@ -0,0 +1,44 @@
+# Latent Consistency Models
+
+Latent Consistency Models (LCMs) were proposed in [Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference](https://arxiv.org/abs/2310.04378) by Simian Luo, Yiqin Tan, Longbo Huang, Jian Li, and Hang Zhao.
+
+The abstract of the [paper](https://arxiv.org/pdf/2310.04378.pdf) is as follows:
+
+*Latent Diffusion models (LDMs) have achieved remarkable results in synthesizing high-resolution images. However, the iterative sampling process is computationally intensive and leads to slow generation. Inspired by Consistency Models (song et al.), we propose Latent Consistency Models (LCMs), enabling swift inference with minimal steps on any pre-trained LDMs, including Stable Diffusion (rombach et al). Viewing the guided reverse diffusion process as solving an augmented probability flow ODE (PF-ODE), LCMs are designed to directly predict the solution of such ODE in latent space, mitigating the need for numerous iterations and allowing rapid, high-fidelity sampling. Efficiently distilled from pre-trained classifier-free guided diffusion models, a high-quality 768 x 768 2~4-step LCM takes only 32 A100 GPU hours for training. Furthermore, we introduce Latent Consistency Fine-tuning (LCF), a novel method that is tailored for fine-tuning LCMs on customized image datasets. Evaluation on the LAION-5B-Aesthetics dataset demonstrates that LCMs achieve state-of-the-art text-to-image generation performance with few-step inference.*
+
+A demo for the [SimianLuo/LCM_Dreamshaper_v7](https://huggingface.co/SimianLuo/LCM_Dreamshaper_v7) checkpoint can be found [here](https://huggingface.co/spaces/SimianLuo/Latent_Consistency_Model).
+
+This pipeline was contributed by [luosiallen](https://luosiallen.github.io/) and [dg845](https://github.com/dg845).
+
+```python
+import torch
+from diffusers import DiffusionPipeline
+
+pipe = DiffusionPipeline.from_pretrained("SimianLuo/LCM_Dreamshaper_v7", torch_dtype=torch.float32)
+
+# To save GPU memory, torch.float16 can be used, but it may compromise image quality.
+pipe.to(torch_device="cuda", torch_dtype=torch.float32)
+
+prompt = "Self-portrait oil painting, a beautiful cyborg with golden hair, 8k"
+
+# Can be set to 1~50 steps. LCM support fast inference even <= 4 steps. Recommend: 1~8 steps.
+num_inference_steps = 4 
+
+images = pipe(prompt=prompt, num_inference_steps=num_inference_steps, guidance_scale=8.0).images
+```
+
+## LatentConsistencyModelPipeline
+
+[[autodoc]] LatentConsistencyModelPipeline
+    - all
+    - __call__
+    - enable_freeu
+    - disable_freeu
+    - enable_vae_slicing
+    - disable_vae_slicing
+    - enable_vae_tiling
+    - disable_vae_tiling
+
+## StableDiffusionPipelineOutput
+
+[[autodoc]] pipelines.stable_diffusion.StableDiffusionPipelineOutput

docs/source/en/api/schedulers/lcm.md

@@ -0,0 +1,9 @@
+# Latent Consistency Model Multistep Scheduler
+
+## Overview
+
+Multistep and onestep scheduler (Algorithm 3) introduced alongside latent consistency models in the paper [Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference](https://arxiv.org/abs/2310.04378) by Simian Luo, Yiqin Tan, Longbo Huang, Jian Li, and Hang Zhao.
+This scheduler should be able to generate good samples from [`LatentConsistencyModelPipeline`] in 1-8 steps.
+
+## LCMScheduler
+[[autodoc]] LCMScheduler

src/diffusers/__init__.py

@@ -142,6 +142,7 @@
             "KarrasVeScheduler",
             "KDPM2AncestralDiscreteScheduler",
             "KDPM2DiscreteScheduler",
+            "LCMScheduler",
             "PNDMScheduler",
             "RePaintScheduler",
             "SchedulerMixin",
@@ -226,6 +227,7 @@
             "KandinskyV22Pipeline",
             "KandinskyV22PriorEmb2EmbPipeline",
             "KandinskyV22PriorPipeline",
+            "LatentConsistencyModelPipeline",
             "LDMTextToImagePipeline",
             "MusicLDMPipeline",
             "PaintByExamplePipeline",
@@ -499,6 +501,7 @@
             KarrasVeScheduler,
             KDPM2AncestralDiscreteScheduler,
             KDPM2DiscreteScheduler,
+            LCMScheduler,
             PNDMScheduler,
             RePaintScheduler,
             SchedulerMixin,
@@ -564,6 +567,7 @@
             KandinskyV22Pipeline,
             KandinskyV22PriorEmb2EmbPipeline,
             KandinskyV22PriorPipeline,
+            LatentConsistencyModelPipeline,
             LDMTextToImagePipeline,
             MusicLDMPipeline,
             PaintByExamplePipeline,

src/diffusers/pipelines/__init__.py

@@ -109,6 +109,7 @@
         "KandinskyV22PriorEmb2EmbPipeline",
         "KandinskyV22PriorPipeline",
     ]
+    _import_structure["latent_consistency_models"] = ["LatentConsistencyModelPipeline"]
     _import_structure["latent_diffusion"].extend(["LDMTextToImagePipeline"])
     _import_structure["musicldm"] = ["MusicLDMPipeline"]
     _import_structure["paint_by_example"] = ["PaintByExamplePipeline"]
@@ -331,6 +332,7 @@
             KandinskyV22PriorEmb2EmbPipeline,
             KandinskyV22PriorPipeline,
         )
+        from .latent_consistency_models import LatentConsistencyModelPipeline
         from .latent_diffusion import LDMTextToImagePipeline
         from .musicldm import MusicLDMPipeline
         from .paint_by_example import PaintByExamplePipeline

src/diffusers/pipelines/latent_consistency_models/__init__.py

@@ -0,0 +1,22 @@
+from typing import TYPE_CHECKING
+
+from ...utils import (
+    _LazyModule,
+)
+
+
+_import_structure = {"pipeline_latent_consistency_models": ["LatentConsistencyModelPipeline"]}
+
+
+if TYPE_CHECKING:
+    from .pipeline_latent_consistency_models import LatentConsistencyModelPipeline
+
+else:
+    import sys
+
+    sys.modules[__name__] = _LazyModule(
+        __name__,
+        globals()["__file__"],
+        _import_structure,
+        module_spec=__spec__,
+    )