Exactly! Train on photorealistic first then use that base to train styles and then use that base for img2img or even Dreambooth. Endless possibilities to try
PROMPT ENGINEERING
-
Code Comments: From Human Documentation to AI Assistant Training
By
–
My code comments were there to help the humans. Now they are there to help the copilot.
Before they were for humans, now they aid the AI,
It's a new way of coding, I can't deny. -
Improving AI Prompts: Beyond Trial and Error Approaches
By
–
can you do better with my prompt, even altering the words but preserving the intent? I tried quite a bit, didn’t even report all the fails, and there were no full successes.
-
Personalizing AI for Individual Needs Within Societal Bounds
By
–
Going to be really important that we can each get AI to do what we individually want (within the broad bounds of what society deems acceptable) as AI becomes part of daily life. Will take iteration & research to get it right, hoping to share initial ideas soon.
-
Reasoning and Pattern Recognition as Transferable Abilities
By
–
Reasoning and pattern recognition are abilities, not problem types. They're what you use to solve problems in different settings, they're not inherent to the problems themselves.
-
Detect GPT Chrome Extension Identifies AI Generated Content
By
–
Detect GPT by @tompec is a chrome extension that lets you see if the page you are on contains AI generated content. https://
futurepedia.io/tool/detect-gpt #ChatGPT #GPTwitter -
Claim of ChatGPT political shift criticized for weak evidence
By
–
There's a popular thread claiming ChatGPT's political opinions shifted centrist after its Dec. 15 update. Evidence given for this is weak (4 online political tests given only once in each period), and the prompting method inappropriately forces in-test consistency of answers:
-
GPT-3 Math Capabilities: Comparing GPT-3 with PAL Tool Integration
By
–
Can GPT3 do math? Or do you need to hook it up to other tools to allow it to best do so? A really cool demo by @JavaFXpert allowing you to easily compare GPT3 vs GPT3 with PAL on @huggingface spaces!
-
PAL: Combining LLMs with Python Interpreter for Better Reasoning
By
–
PAL (
https://
arxiv.org/pdf/2211.10435
.pdf
…) is a method from @urialon1 @luyu_gao @aman_madaan combining LLMs with a python interpreter to achieve better results on numeric and reasoning tasks Check out the LangChain implementation/documentation here: https://
langchain.readthedocs.io/en/latest/exam
ples/chains/pal.html
… -
Testing Model Guidance Levels Finding Optimal Sweet Spot
By
–
randomly had this page open so tried it on the published model. guidances at 7, 10, and 13 from bottom to top. looks like 10 is sweet spot