Stablediffy
A vicuna based prompt engineering tool for stable diffusion
generate awesome images without prompt knowledge
How it works
The file Stablediffy.txt is a prompt file for the Vicuna model, similar to the file chat-with-bob.txt. First, the situation is described. Secondly, some keywords like "dramatic lightning" are listed to teach them to Vicuna. Third, some sample responses from Stablediffy to the human's rough queries are listed to teach Vicuna how to respond.
Disclaimer
You can try the prompt-file with other AI language models too.
Examples
1. Suggest a prompt for an mysterious house
Request
### Human:suggest a prompt for an mysterious house
### Assistant: Mysterious house, haunted mansion, spooky, intricate, sharp details, octane render, unreal engine, photograph, realistic skin texture, photorealistic, hyper realism, highly detailed, 85mm portrait photography, award winning, hard rim lighting photography, dramatic lighting, cinematic lighting, gritty atmosphere, urban, noir style, night scene"
2. Suggest a prompt for a mysterious lake in the night
Request
### Human:suggest a prompt for a mysterious lake in the night
### Assistant: Mysterious lake, night scene, dark and moody, atmospheric, spooky, gothic, creepy, haunting, eerie, suspenseful, dramatic lightning, cinematic lightning, octane render, unreal engine, realistic reflections, water reflections, moonlight, starry sky, mysterious atmosphere, dark and gritty
3. Suggest a prompt for a ghost ship on the ocean
Request
### Human:suggest a prompt for a ghost ship on the ocean
### Assistant: Ghost ship, abandoned ship, creepy atmosphere, spooky, dark, ominous, mysterious, cinematic lightning, dramatic lightning, octane render, unreal engine, realistic, highly detailed, textured, 3D modeling, digital art, 3D illustration
4. Suggest a prompt for a portrait of Danial Craig
Request
### Human:suggest a prompt for a portrait of Danial Craig
### Assistant: Daniel Craig portrait, actor, famous, well-known, blue eyes, chiseled jawline, suave, sophisticated, realistic, hyper-realistic, highly detailed, 85mm lens, photography, realistic skin texture, photorealistic, noir style, cinematic lightning, dramatic lightning, portrait photography, sharp focus, colorful"
Installation
To install Vicuna, follow the instructions on this repo: https://github.com/vicuna-tools/vicuna-installation-guide/
Once that's done, navigate to the llama.cpp/prompts folder
Now, download the Stablediffy.txt file with wget
wget "https://raw.githubusercontent.com/vicuna-tools/Stablediffy.txt/main/Stablediffy.txt"
Usage
Navigate back to the llama.cpp folder
Run the vicuna model with the Stablediffy.txt prompt-file (13B)
./main -m models/ggml-vic13b-q5_1.bin -f 'prompts/Stablediffy.txt' -r 'USER:'
Run the vicuna model with the Stablediffy.txt prompt-file (7B)
./main -m models/ggml-vic7b-q5_1.bin -f 'prompts/Stablediffy.txt' -r 'USER:'
This should start processing the Stablediffy.txt file After the last processed conversation example:
USER: Car in 1950, highly detailed, classic car, 1950's...