Add latent consistency (#5438)

* Add latent consistency

* Update examples/community/README.md

* Add latent consistency

* make fix copies

* Apply suggestions from code review

examples/community/README.md

@@ -44,6 +44,7 @@ Stable Diffusion XL Long Weighted Prompt Pipeline | A pipeline support unlimited
 FABRIC - Stable Diffusion with feedback Pipeline | pipeline supports feedback from liked and disliked images | [Stable Diffusion Fabric Pipeline](#stable-diffusion-fabric-pipeline) | - | [Shauray Singh](https://shauray8.github.io/about_shauray/) | 
 sketch inpaint - Inpainting with non-inpaint Stable Diffusion | sketch inpaint much like in automatic1111 | [Masked Im2Im Stable Diffusion Pipeline](#stable-diffusion-masked-im2im) | - | [Anatoly Belikov](https://github.com/noskill) | 
 prompt-to-prompt | change parts of a prompt and retain image structure (see [paper page](https://prompt-to-prompt.github.io/)) | [Prompt2Prompt Pipeline](#prompt2prompt-pipeline) | - | [Umer H. Adil](https://twitter.com/UmerHAdil) | 
+|   Latent Consistency Pipeline                                                                                                    | Implementation of [Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference](https://arxiv.org/abs/2310.04378)                                                                                                                                                                                                                                                                                                                                                                                                                                      | [Latent Consistency Pipeline](#latent-consistency-pipeline)      | - |              [Simian Luo](https://github.com/luosiallen) |
 
 
 To load a custom pipeline you just need to pass the `custom_pipeline` argument to `DiffusionPipeline`, as one of the files in `diffusers/examples/community`. Feel free to send a PR with your own pipelines, we will merge them quickly.
@@ -2147,3 +2148,40 @@ edit_kcross_attention_kwargswargs = {
 ```
 
 Side note: See [this GitHub gist](https://gist.github.com/UmerHA/b65bb5fb9626c9c73f3ade2869e36164) if you want to visualize the attention maps.
+
+### Latent Consistency Pipeline
+
+Latent Consistency Models was 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, Hang Zhao* from Tsinghua University.
+
+The abstract of the paper reads 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. Project Page: [this https URL](https://latent-consistency-models.github.io/)*
+
+The model can be used with `diffusers` as follows:
+
+ - *1. Load the model from the community pipeline.*
+
+```py
+from diffusers import DiffusionPipeline
+import torch
+
+pipe = DiffusionPipeline.from_pretrained("SimianLuo/LCM_Dreamshaper_v7", custom_pipeline="latent_consistency_txt2img")
+
+# To save GPU memory, torch.float16 can be used, but it may compromise image quality.
+pipe.to(torch_device="cuda", torch_dtype=torch.float32)
+```
+
+- 2. Run inference with as little as 4 steps:
+
+```py
+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, lcm_origin_steps=50, output_type="pil").images
+```
+
+For any questions or feedback, feel free to reach out to [Simian Luo](https://github.com/luosiallen).
+
+You can also try this pipeline directly in the [🚀 official spaces](https://huggingface.co/spaces/SimianLuo/Latent_Consistency_Model).