penelope-palette

Penelope Palette: Portrait Generation Model

Important note : Provisory Model card mostly a placeholder.

Model Description

Penelope Palette is an advanced AI model designed for creating lifelike portraits. It leverages the same architecture as Stable Diffusion 3, ensuring high-quality image generation with remarkable detail and style. Most of the description was copied from the stable diffusion 3 since the informations remains generally the same. The model is weaker than Stable Diffusion 3 medium , having trouble generating realistic content ; nudity and anatomy but it performs really good in portraits , having a unique style .

Model Description

Developed by: Penelope Systems

Model type: MMDiT text-to-image generative model

Model Description: This is a model that can be used to generate images based on text prompts. It is a Multimodal Diffusion Transformer (https://arxiv.org/abs/2403.03206) that uses three fixed, pretrained text encoders (OpenCLIP-ViT/G, CLIP-ViT/L and T5-xxl)

License

Apache llicense 2.0

Model Sources

For local or self-hosted use, we recommend ComfyUI for inference. It has built-in clip so it shoul be plug & play .

ComfyUI: https://github.com/comfyanonymous/ComfyUI

Training Dataset

We used synthetic data and filtered publicly available data to train our models. The model was pre-trained on 1 billion images. The fine-tuning data includes 30M high-quality aesthetic images focused on specific visual content and style, as well as 3M preference data images.

Uses

Intended Uses Intended uses include the following:

Generation of artworks and use in design and other artistic processes. Applications in educational or creative tools. Research on generative models, including understanding the limitations of generative models.

Out-of-Scope Uses

The model was not trained to be factual or true representations of people or events. As such, using the model to generate such content is out-of-scope of the abilities of this model.

Safety

Same safety measures used by Stable Diffusion 3 were deployed .

Use recommendations :

For best use we recommand : - steps : 32 - cfg : between 4.0 and 7.0 - sampler_name : dpmpp_2m - scheduler : sgm_uniform

# For best generations don't try to use realism | use words like "portrait" ; "art" ; "sketch" and so on .