Table of contents
- General info
- Granular Adaptive Learning
- Setup
- Space
- CompVis
- Diffusers
- Checkpoint Merging Data Reference
- License
General info
Protogen x5.3 - One Step Closer to Reality by darkstorm2150
Protogen was warm-started with Stable Diffusion v1-5 and continued fine-tuned from darkstorm2150/Protogen_x3.4_Official_Release Robodiffusion has been removed and 10% Dreamlike-PhotoReal V.2 added, the result is better sampling at 768px to 1024px of humans and surroundings, The results are immediate!!!
Also this bad boy comes with a license, so do please read it, thank you!
- Model control
Now its recommended that you add nude, naked to your negative prompts, its a horny model, well 10% but still....cant be too careful!
As for realism, you can use this template
modelshoot style, (extremely detailed 8k wallpaper),a medium shot photo of a (what you want here), Intricate, High Detail, dramatic
It should also be very "dreambooth-able", being able to generate high fidelity faces with a little amount of steps (see dreambooth).
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
We support a Gradio Web UI:
CompVis
CKPT
Download ProtoGen x5.3.ckpt (4.27GB)
Download ProtoGen x5.3-pruned-fp16.ckpt (1.89GB)
Safetensors
Download ProtoGen x5.3.safetensors (4.27GB)
Download ProtoGen x5.3-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_v5.3_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
License
By downloading you agree to the terms of these licenses
CreativeML Open RAIL-M
Dreamlike License
Seek Art Mega License