Model reference · open weights
playground-1024px-aesthetic is an open-weight image model from playgroundai, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
Playground v2.5 – 1024px Aesthetic Model This repository contains a model that generates highly aesthetic images of resolution 1024x1024, as well as portrait and landscape aspect ratios. You can use the model with Hugging Face 🧨 Diffusers. Playground v2.5 is a diffusion-based text-to-image generative model, and a successor to Playground v2. Playground v2.5 is the state-of-the-art open-source model in aesthetic quality. Our user studies demonstrate that our model outperforms SDXL, Playground v2, PixArt-α, DALL-E 3, and Midjourney 5.2. For details on the development and training of our model, please refer to our blog post and technical report. Model Description - Developed by: Playground - Model type: Diffusion-based text-to-image generative model - License: Playground v2.5 Community License - Summary: This model generates images based on text prompts. It is a Latent Diffusion Model that uses two fixed, pre-trained text encoders (OpenCLIP-ViT/G and CLIP-ViT/L). It follows the same architecture as Stable Diffusion XL. Using the model with 🧨 Diffusers Install diffusers = 0.27.0 and the relevant dependencies. Notes: - The pipeline uses the EDMDPMSolverMultistepScheduler scheduler by default, for crisper fine details. It's an EDM formulation of the DPM++ 2M Karras scheduler. guidancescale=3.0 is a good default for this scheduler. - The pipeline also supports the EDMEulerScheduler scheduler. It's an EDM formulation of the Euler scheduler. guidancescale=5.0 is a good default for this scheduler. Then, run the following snippet: Using the model with Automatic1111/ComfyUI Support coming soon. We will update this model card with instructions when ready. User Studies This model card only provides a brief summary of our user study results. For extensive details on how we perform user studies, please check out our technical report. We conducted studies to measure overall aesthetic quality, as well as for the specific areas we aimed to improve with Playground v2.5, namely multi aspect ratios and human preference alignment. Comparison to State-of-the-Art The aesthetic quality of Playground v2.5 dramatically outperforms the current state-of-the-art open source models SDXL and PIX
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | playgroundai |
|---|---|
| Type | Image models |
| Parameters (lead) | 2.6B |
| Variants | 1 |
| Runs with | diffusers |
| Released | 2024-02-16 |
| Popularity | 365k downloads / month |
| Likes | 771 |
| Licence | Commercial licence needed |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| playground-v2.5-1024px-aesthetic | 2.6B | BF16 | ~5.9 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys playground-1024px-aesthetic for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (playground-1024px-aesthetic below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/images/generations \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"playground-1024px-aesthetic","prompt":"a red bicycle","size":"1024x1024"}'
Licence
The weights are open but its licence needs a commercial agreement for business use. AxForge can arrange that licence and host the model for you — you pay AxForge, we settle with the model’s maker. Ask us for a quote. Read the licence ↗