---
license: apache-2.0
language:
- en
---
# 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 .

![image/png](https://cdn-uploads.huggingface.co/production/uploads/632776ce8624baac667ecb01/NAQiWjoYqdqjcgER8QKys.png)
![image/png](https://cdn-uploads.huggingface.co/production/uploads/632776ce8624baac667ecb01/KjpWPX-ruB1MLQJpMU-sU.png)
![image/png](https://cdn-uploads.huggingface.co/production/uploads/632776ce8624baac667ecb01/Fkmkb9Db50i07N76182Ih.png)
![image/png](https://cdn-uploads.huggingface.co/production/uploads/632776ce8624baac667ecb01/c4IOnm7pW3JU4_ogU6A-H.png)
![image/png](https://cdn-uploads.huggingface.co/production/uploads/632776ce8624baac667ecb01/CO8agFO7rCCsjrplz_ukZ.png)
![image/png](https://cdn-uploads.huggingface.co/production/uploads/632776ce8624baac667ecb01/ZCAKZ6lZouNFgHIOESKnM.png)
![image/png](https://cdn-uploads.huggingface.co/production/uploads/632776ce8624baac667ecb01/Z8SC0qcBrdZkW8cp9Uvyb.png)