darkstorm2150/Protogen_Nova_Official_Release

Model

Table of contents

39

52 commits

1 linked in READMEs

updated Jul 8, 2025

See the code

README

Protogen Nova

Research Model by darkstorm2150

Table of contents

General info

The Protogen Nova is a checkpoint model that merges all the previous models into one

This merger includes

  • Protogen v2.2 (Anime)
  • Protogen x3.4 (Photorealism)
  • ProtoGen x5.3 (Photorealism)
  • ProtoGen x5.8 Rebuilt (Scifi+Anime)
  • ProtoGen x5.9 (Dragon)
  • ProtoGen x7.4 (Eclipse)

As part the of the checkpoint merging, Granular Adaptive Learning is a technique where traininig data is lessen selectively from 30% to 0.05%, and as the training is eventually saturated, the process reduces loss and introduces elements from various checkpoints

Granular Adaptive Learning

Granular adaptive learning is a machine learning technique that focuses on adjusting the learning process at a fine-grained level, rather than making global adjustments to the model. This approach allows the model to adapt to specific patterns or features in the data, rather than making assumptions based on general trends.

Granular adaptive learning can be achieved through techniques such as active learning, which allows the model to select the data it wants to learn from, or through the use of reinforcement learning, where the model receives feedback on its performance and adapts based on that feedback. It can also be achieved through techniques such as online learning where the model adjust itself as it receives more data.

Granular adaptive learning is often used in situations where the data is highly diverse or non-stationary and where the model needs to adapt quickly to changing patterns. This is often the case in dynamic environments such as robotics, financial markets, and natural language processing.

Setup

To run this model, download the model.ckpt and install it in your "stable-diffusion-webui\models\Stable-diffusion" directory

Space

CompVis

Diffusers

Checkpoint Merging Data Reference - PENDING DATA FOR MERGE, RPGv2 not accounted..

.myTable { border-collapse:collapse; } .myTable th { background-color:#663380; color:white; } .myTable td, .myTable th { padding:5px; border:1px solid #663380; }
ModelsProtogen v2.2 (Anime)Protogen x3.4 (Photo)Protogen x5.3 (Photo)Protogen x5.8 (Sci-fi/Anime)Protogen x5.9 (Dragon)Protogen x7.4 (Eclipse)Protogen x8.0 (Nova)Protogen x8.6 (Infinity)
seek_art_mega v152.50%42.76%42.63%25.21%14.83%
modelshoot v130.00%24.44%24.37%2.56%2.05%3.48%22.91%13.48%
elldreth v112.64%10.30%10.23%6.06%3.57%
photoreal v210.00%48.64%38.91%66.33%20.49%12.06%
analogdiffusion v14.75%4.50%1.75%1.03%
openjourney v24.51%4.28%4.75%2.26%1.33%
hassan1.42.63%2.14%2.13%1.26%0.74%
f2222.23%1.82%1.81%1.07%0.63%
hasdx20.00%16.00%4.07%5.01%2.95%
moistmix16.00%12.80%3.86%4.08%2.40%
roboDiffusion v14.29%12.80%10.24%3.67%4.41%2.60%
RPG v35.00%20.00%4.29%4.29%2.52%
anything&everything4.51%0.56%0.33%
dreamlikediff v15.0%0.63%0.37%
sci-fidiff v13.10%
synthwavepunk v23.26%
mashupv211.51%
dreamshaper 2524.04%
comicdiff v24.25%
artEros15.00%

License

By downloading you agree to the terms of these licenses

CreativeML Open RAIL-M

Dreamlike License

Seek Art Mega License

artistic
diffusers
endpoints_compatible
protogen
safetensors
stable-diffusion
stable-diffusion-diffusers
text-to-image

Contributors

darkstorm2150

44 commits

SFconvertbot

1 commits

valhalla

1 commits

darkstorm2150/Protogen_Nova_Official_Release

Model

Table of contents

39

52 commits

1 linked in READMEs

updated Jul 8, 2025

See the code

README

Protogen Nova

Research Model by darkstorm2150

Table of contents

General info

The Protogen Nova is a checkpoint model that merges all the previous models into one

This merger includes

  • Protogen v2.2 (Anime)
  • Protogen x3.4 (Photorealism)
  • ProtoGen x5.3 (Photorealism)
  • ProtoGen x5.8 Rebuilt (Scifi+Anime)
  • ProtoGen x5.9 (Dragon)
  • ProtoGen x7.4 (Eclipse)

As part the of the checkpoint merging, Granular Adaptive Learning is a technique where traininig data is lessen selectively from 30% to 0.05%, and as the training is eventually saturated, the process reduces loss and introduces elements from various checkpoints

Granular Adaptive Learning

Granular adaptive learning is a machine learning technique that focuses on adjusting the learning process at a fine-grained level, rather than making global adjustments to the model. This approach allows the model to adapt to specific patterns or features in the data, rather than making assumptions based on general trends.

Granular adaptive learning can be achieved through techniques such as active learning, which allows the model to select the data it wants to learn from, or through the use of reinforcement learning, where the model receives feedback on its performance and adapts based on that feedback. It can also be achieved through techniques such as online learning where the model adjust itself as it receives more data.

Granular adaptive learning is often used in situations where the data is highly diverse or non-stationary and where the model needs to adapt quickly to changing patterns. This is often the case in dynamic environments such as robotics, financial markets, and natural language processing.

Setup

To run this model, download the model.ckpt and install it in your "stable-diffusion-webui\models\Stable-diffusion" directory

Space

CompVis

Diffusers

Checkpoint Merging Data Reference - PENDING DATA FOR MERGE, RPGv2 not accounted..

.myTable { border-collapse:collapse; } .myTable th { background-color:#663380; color:white; } .myTable td, .myTable th { padding:5px; border:1px solid #663380; }
ModelsProtogen v2.2 (Anime)Protogen x3.4 (Photo)Protogen x5.3 (Photo)Protogen x5.8 (Sci-fi/Anime)Protogen x5.9 (Dragon)Protogen x7.4 (Eclipse)Protogen x8.0 (Nova)Protogen x8.6 (Infinity)
seek_art_mega v152.50%42.76%42.63%25.21%14.83%
modelshoot v130.00%24.44%24.37%2.56%2.05%3.48%22.91%13.48%
elldreth v112.64%10.30%10.23%6.06%3.57%
photoreal v210.00%48.64%38.91%66.33%20.49%12.06%
analogdiffusion v14.75%4.50%1.75%1.03%
openjourney v24.51%4.28%4.75%2.26%1.33%
hassan1.42.63%2.14%2.13%1.26%0.74%
f2222.23%1.82%1.81%1.07%0.63%
hasdx20.00%16.00%4.07%5.01%2.95%
moistmix16.00%12.80%3.86%4.08%2.40%
roboDiffusion v14.29%12.80%10.24%3.67%4.41%2.60%
RPG v35.00%20.00%4.29%4.29%2.52%
anything&everything4.51%0.56%0.33%
dreamlikediff v15.0%0.63%0.37%
sci-fidiff v13.10%
synthwavepunk v23.26%
mashupv211.51%
dreamshaper 2524.04%
comicdiff v24.25%
artEros15.00%

License

By downloading you agree to the terms of these licenses

CreativeML Open RAIL-M

Dreamlike License

Seek Art Mega License

artistic
diffusers
endpoints_compatible
protogen
safetensors
stable-diffusion
stable-diffusion-diffusers
text-to-image

Contributors

darkstorm2150

44 commits

SFconvertbot

1 commits

valhalla

1 commits