<h1 id="heading-187">Playground v2 – 1024px Aesthetic Model</h1>This repository contains a model that generates highly aesthetic images of resolution 1024x1024. You can use the model with Hugging Face 🧨 Diffusers.<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/e0040fec-964e-4301-bdbe-77975d596cb4/width=525/e0040fec-964e-4301-bdbe-77975d596cb4.jpeg" />Playground v2 is a diffusion-based text-to-image generative model. The model was trained from scratch by the research team at <a rel="ugc" href="https://playground.com">Playground</a>. Images generated by Playground v2 are favored 2.5 times more than those produced by Stable Diffusion XL, according to Playground’s user study.We are thrilled to release [intermediate checkpoints](#intermediate-base-models) at different training stages, including evaluation metrics, to the community. We hope this will encourage further research into foundational models for image generation.Lastly, we introduce a new benchmark, MJHQ-30K, for automatic evaluation of a model’s aesthetic quality.Please see our <a rel="ugc" href="https://blog.playgroundai.com/playground-v2">blog</a> for more details.<h3 id="heading-188">Model Description</h3>- Developed by: <a rel="ugc" href="https://playground.com">Playground</a>- Model type: Diffusion-based text-to-image generative model- License: <a rel="ugc" href="https://huggingface.co/playgroundai/playground-v2-1024px-aesthetic/blob/main/LICENSE.md">Playground v2 Community License</a><h3 id="heading-189">Using the model with 🧨 Diffusers</h3>Install diffusers &gt;= 0.24.0 and some dependencies:<pre><code>pip install transformers accelerate safetensors</code></pre>To use the model, run the following snippet.Note: It is recommend to use `guidance_scale=3.0`.<pre><code>from diffusers import DiffusionPipeline

import torch

pipe = DiffusionPipeline.from_pretrained(

 "playgroundai/playground-v2-1024px-aesthetic",

 torch_dtype=torch.float16,

 use_safetensors=True,

 add_watermarker=False,

 variant="fp16"

)

pipe.to("cuda")

prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"

image = pipe(prompt=prompt, guidance_scale=3.0).images[0]</code></pre><h3 id="heading-190">Using the model with Automatic1111/ComfyUI</h3>In order to use the model with software such as Automatic1111 or ComfyUI you can use <a rel="ugc" href="https://huggingface.co/playgroundai/playground-v2-1024px-aesthetic/blob/main/playground-v2.fp16.safetensors">playground-v2.fp16.safetensors</a> file.

Files with SHA256: 0411e988479884b1a3ecd184123efe38d051d8d0ef24270585a7d1d57499464a