Protogen x3.4 (Photorealism) Official Release

Research Model by darkstorm2150

Table of contents

• General info
• Granular Adaptive Learning
• Trigger Words
• Setup
• Space
• CompVis
• Diffusers
• Checkpoint Merging Data Reference
• License

General info

Protogen x3.4

Protogen was warm-started with Stable Diffusion v1-5 and fine-tuned on various high quality image datasets. Version 3.4 continued training from ProtoGen v2.2 with added photorealism.

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.

Trigger Words

modelshoot style, analog style, mdjrny-v4 style, nousr robot

Trigger words are available for the hassan1.4 and f222, might have to google them :)

Setup

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

Space

We support a Gradio Web UI:

CompVis

CKPT

Download ProtoGen x3.4.ckpt (5.98GB)

Download ProtoGen X3.4-pruned-fp16.ckpt (1.89 GB)

Safetensors

Download ProtoGen x3.4.safetensors (5.98GB)

Download ProtoGen x3.4-pruned-fp16.safetensors (1.89GB)

? Diffusers

This model can be used just like any other Stable Diffusion model. For more information, please have a look at the Stable Diffusion Pipeline .

from diffusers import StableDiffusionPipeline, DPMSolverMultistepScheduler
import torch

prompt = (
"modelshoot style, (extremely detailed CG unity 8k wallpaper), full shot body photo of the most beautiful artwork in the world, "
"english medieval witch, black silk vale, pale skin, black silk robe, black cat, necromancy magic, medieval era, "
"photorealistic painting by Ed Blinkey, Atey Ghailan, Studio Ghibli, by Jeremy Mann, Greg Manchess, Antonio Moro, trending on ArtStation, "
"trending on CGSociety, Intricate, High Detail, Sharp focus, dramatic, photorealistic painting art by midjourney and greg rutkowski"
)

model_id = "darkstorm2150/Protogen_x3.4_Official_Release"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)
pipe = pipe.to("cuda")

image = pipe(prompt, num_inference_steps=25).images[0]

image.save("./result.jpg")

PENDING DATA FOR MERGE, RPGv2 not accounted..

Checkpoint Merging Data Reference

Models	Protogen 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 v1	52.50%	42.76%	42.63%	25.21%	14.83%
modelshoot v1	30.00%	24.44%	24.37%	2.56%	2.05%	3.48%	22.91%	13.48%
elldreth v1	12.64%	10.30%	10.23%	6.06%	3.57%
photoreal v2	10.00%	48.64%	38.91%	66.33%	20.49%	12.06%
analogdiffusion v1	4.75%	4.50%	1.75%	1.03%
openjourney v2	4.51%	4.28%	4.75%	2.26%	1.33%
hassan1.4	2.63%	2.14%	2.13%	1.26%	0.74%
f222	2.23%	1.82%	1.81%	1.07%	0.63%
hasdx	20.00%	16.00%	4.07%	5.01%	2.95%
moistmix	16.00%	12.80%	3.86%	4.08%	2.40%
roboDiffusion v1	4.29%	12.80%	10.24%	3.67%	4.41%	2.60%
RPG v3	5.00%	20.00%	4.29%	4.29%	2.52%
anything&everything	4.51%	0.56%	0.33%
dreamlikediff v1	5.0%	0.63%	0.37%
sci-fidiff v1	3.10%
synthwavepunk v2	3.26%
mashupv2	11.51%
dreamshaper 252	4.04%
comicdiff v2	4.25%
artEros	15.00%

License

By downloading you agree to the terms of these licenses

CreativeML Open RAIL-M

Seek Art Mega License

.hf-sanitized.hf-sanitized-Lx7h0YTDSArcV8kHYG5Rs .myTable {border-collapse: collapse;} .hf-sanitized.hf-sanitized-Lx7h0YTDSArcV8kHYG5Rs .myTable th {background-color: #663380; color: white;} .hf-sanitized.hf-sanitized-Lx7h0YTDSArcV8kHYG5Rs .myTable td, .myTable th {padding: 5px; border: 1px solid #663380;}