Updated new readme

README.md

@@ -1,75 +1,56 @@
 ---
-license: mit
+
 language:
 - en
-pipeline_tag: text-to-image
+license: mit
 tags:
+- stable-diffusion
+- stable-diffusion-diffusers
 - text-to-image
+- diffusers
+inference: true
 ---
 
-# Latent Consistency Models
-
-Official Repository of the paper: *[Latent Consistency Models](https://arxiv.org/abs/2310.04378)*.
-
-Project Page: https://latent-consistency-models.github.io
+<p align="center" width="100%">
+    <img width="80%" src="Assets/OnnxStack - 640x320.png">
+</p>
 
-## Try our Hugging Face demos: 
-[![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/SimianLuo/Latent_Consistency_Model)
+### OnnxStack
+This model has been converted to ONNX and tested with OnnxStack
 
-## Model Descriptions:
-Distilled from [Dreamshaper v7](https://huggingface.co/Lykon/dreamshaper-7) fine-tune of [Stable-Diffusion v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5) with only 4,000 training iterations (~32 A100 GPU Hours). 
+- [OnnxStack](https://github.com/saddam213/OnnxStack)
 
-## Generation Results:
+### LCM Dreamshaper V7 Diffusion
+This model was converted to ONNX from LCM Dreamshaper V7
 
-<p align="center">
-    <img src="teaser.png">
-</p>
+- [LCM-Dreamshaper-V7](https://huggingface.co/SimianLuo/LCM_Dreamshaper_v7)
 
-By distilling classifier-free guidance into the model's input, LCM can generate high-quality images in very short inference time. We compare the inference time at the setting of 768 x 768 resolution, CFG scale w=8, batchsize=4, using a A800 GPU. 
+### Sample Images
+*A demon*
 
-<p align="center">
-    <img src="speed_fid.png">
-</p>
+<img src="Assets/lcm_demon_30_7.5_2092464983.png" width="256" alt="Image of browser inferencing on sample images."/>
 
-## Usage
+     Seed: 207582124     GuidanceScale: 7.5     NumInferenceSteps: 30
 
-You can try out Latency Consistency Models directly on:
-[![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/SimianLuo/Latent_Consistency_Model)
+__________________________
+*An angel*
 
-To run the model yourself, you can leverage the 🧨 Diffusers library:
-1. Install the library:
-```
-pip install git+https://github.com/huggingface/diffusers.git
-pip install transformers accelerate
-```
+<img src="Assets/lcm_angel_30_7.5_2092464983.png" width="256" alt="Image of browser inferencing on sample images."/>
 
-2. Run the model:
-```py
-from diffusers import DiffusionPipeline
-import torch
+     Seed: 207582124     GuidanceScale: 7.5     NumInferenceSteps: 30
 
-pipe = DiffusionPipeline.from_pretrained("SimianLuo/LCM_Dreamshaper_v7", custom_pipeline="latent_consistency_txt2img", custom_revision="main", revision="fb9c5d")
+__________________________
+*A ninja*
 
-# To save GPU memory, torch.float16 can be used, but it may compromise image quality.
-pipe.to(torch_device="cuda", torch_dtype=torch.float32)
+<img src="Assets/lcm_ninja_30_7.5_2092464983.png" width="256" alt="Image of browser inferencing on sample images."/>
 
-prompt = "Self-portrait oil painting, a beautiful cyborg with golden hair, 8k"
+     Seed: 207582124     GuidanceScale: 7.5     NumInferenceSteps: 30
 
-# Can be set to 1~50 steps. LCM support fast inference even <= 4 steps. Recommend: 1~8 steps.
-num_inference_steps = 4 
+__________________________
+*a japanese dometic market sports car sitting in a showroom*
 
-images = pipe(prompt=prompt, num_inference_steps=num_inference_steps, guidance_scale=8.0, lcm_origin_steps=50, output_type="pil").images
-```
+<img src="Assets/lcm_car_30_7.5_2092464983.png" width="256" alt="Image of browser inferencing on sample images."/>
 
-## BibTeX
+     Seed: 207582124     GuidanceScale: 7.5     NumInferenceSteps: 30
 
-```bibtex
-@misc{luo2023latent,
-      title={Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference}, 
-      author={Simian Luo and Yiqin Tan and Longbo Huang and Jian Li and Hang Zhao},
-      year={2023},
-      eprint={2310.04378},
-      archivePrefix={arXiv},
-      primaryClass={cs.CV}
-}
-```
+__________________________