Questions tagged [prompt-design]

Prompt design involves crafting prompts that are effective in eliciting the desired response from language models. Well-organized and clear prompts lead to accurate and high-quality language model responses. Thoughtful design is crucial for effective results. Use this tag on questions about how to craft prompts for a specific language model. Use together with the target language model or GenAI tool.

Filter by
Sorted by
Tagged with
1 vote
0 answers
17 views

How would you craft a prompt to tell Stable Diffusion (through Automatic1111) to change the color or surface effect of an an object

How would you craft a prompt to tell stable diffusion, using the Automatic1111 interface, to change the color or surface effect of an object without substantively changing the other details? For ...
Aaargh Zombies's user avatar
0 votes
1 answer
57 views

How to fix my knowledge base?

I use Langchain.js with HNSWLib. I am building a chat bot for an automotive dealer. here's is part of knowledge base .txt file I use as input to the model. Q: Where is this inventory item/boat/RV/...
Adam S's user avatar
  • 1
1 vote
0 answers
59 views

Is there a way to search for videos based on a customized prompt?

I'd like to search for videos that contain specific words in a foreign language. I wonder if it's possible to search for videos through keywords in a determined language. I also wonder if it's ...
Kevin's user avatar
  • 11
3 votes
2 answers
59 views

How can I prompt ChatGPT to give me a 1000-character Chinese essay?

For the Chinese HSK6 exam, the writing section is (at the time of writing) a single 缩写 ("abridge") exercise: you're given a 1000-character essay (usually there's a character who goes through ...
Rebecca J. Stones's user avatar
2 votes
0 answers
59 views

Rules for additional commas for Text-to-speech (ChatGPT)

For a more natural Text to speech output, it is necessary to add additional commas so that there are micropauses and the text sounds more like a human voice. Grammatical commas are already in the text....
OdessaUA's user avatar
1 vote
0 answers
152 views

Stable diffusion - Can you craft a prompt to remove something in a masked area

Within Stable Diffusion, is it possible to mask a particular area on an image, and craft a prompt to instruct the system to remove an element from it. For example, to take a picture of a man holding ...
Aaargh Zombies's user avatar
0 votes
0 answers
68 views

What is the meaning of the prompt "derpibooru_p_95", and what effect does it achieve?

When crafting a prompt for a generative AI image package - For example using Stable diffusion with the Automatic111 web ui - what is the meaning of the prompt fragment "derpibooru_p_95", and ...
Aaargh Zombies's user avatar
2 votes
1 answer
132 views

Prompt ideas on how to generate a character performing a kick in Midjourney?

I've been trying for hours to generate a kicking action in MJ, but can't find the right prompt, tried "karate, tae kwon do, flying kick, kicking, performing kick", but nothing seems to have ...
sigmaxf's user avatar
  • 123
0 votes
1 answer
421 views

How would I add a knowledge base to a llama prompt?

I know that the prompting format for LLAMA 2 looks like this: <s>[INST] <<SYS>> {your_system_message} <</SYS>> {user_message_1} [/INST] {model_reply_1}</s><s>...
user2741831's user avatar
1 vote
1 answer
726 views

How to prompt Llama2 for text classification?

Here is my script: from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-chat-hf") model = AutoModelForCausalLM....
etang's user avatar
  • 143
1 vote
1 answer
851 views

How to just get the answer from Llama-2 instead of repeating the whole prompt?

Here is my script: from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-chat-hf") model = AutoModelForCausalLM....
etang's user avatar
  • 143
8 votes
1 answer
270 views

Is it possible to change the "temperature" parameter of ChatGPT chats?

The OpenAI API has the possibility to set the temperature parameter (e.g. see this). Is it also possible to influence the temperature parameter of chats in the ChatGPT web UI? I tried setting it in &...
MaDev's user avatar
  • 196
4 votes
1 answer
115 views

What is a memetic proxy?

I came across this term with the negative impression on the AI Engineering which is: Try to avoid memetic proxy in the prompts If I assume something it would be like "Imagine you are a ...
Swesh's user avatar
  • 87
0 votes
0 answers
277 views

Prompt for rephrasing a question based on previous questions

I am trying to write a prompt on GPT 3.5 turbo to rephrase a question based on context of previous questions. I did write a prompt that is able to suffice 90% of the cases however at times LLM even ...
Raul's user avatar
  • 21
1 vote
0 answers
132 views

Crafting a prompt to create an image from a specific angle in Stable Diffusion Automatic1111 web UI

How should I go about crafting a prompt to generate an object viewed from a specific angle in Stable Diffusion using the Automatic1111 web UI? For example, if I wanted to generate an image of a bird ...
Aaargh Zombies's user avatar
3 votes
0 answers
102 views

How to provide faces of public characters as a visual clue to Leonardo.ai?

I am a beginner in generative prompting and I am experimenting with Leonardo.ai. I like it's photoreal and cinematic effect, but it does not support upload of an image as input, apparently. How can I ...
user305883's user avatar
0 votes
0 answers
64 views

Why does give ChatGPT exactly the same response to the prompt "ein hund kam in die küche"

I have never encountered this before, but ChatGPT (with GPT-4) behaves as I would have set its temperature to zero -- but I didn't. I just entered the following prompt "ein hund kam in die küche&...
Hans-Peter Stricker's user avatar
5 votes
0 answers
163 views

How can I prompt midjourney to generate images of D&D weapons other than swords?

I'm trying to generate some cool magical weapons for my D&D campaign using midjourney, but I'm having a real struggle getting it to do things other than swords. I couldn't get it to do a bow at ...
Derek Thurn's user avatar
5 votes
2 answers
340 views

Prompts that reliably result in unreliable completions

Assume you want to demonstrate how ChatGPT can give quite different answers to the same question, either different in the focus of the answers or even with the same focus but contradictory statements. ...
Hans-Peter Stricker's user avatar
2 votes
2 answers
576 views

What prompts are required to have a foreground object against a transparent\plain background in Stable Diffusion?

In Stable diffusion, what prompts are required in order to have a foreground object against a transparent background (or a plain one if transparent isn't possible), so that a user would not need to ...
Aaargh Zombies's user avatar
4 votes
3 answers
680 views

What are negative prompts in LLMs?

In stable diffusion, a negative prompt can be used to specify elements that should not be part of the generated image. Example: Prompt: Portrait photo of a man Negative Prompt: mustache The negative ...
Turamarth's user avatar
  • 201
1 vote
2 answers
154 views

What works better: An LLM trained on better texts or an LLM with better prompts?

Assume you have a very large corpus of high-quality documents related to a given topic, and assume you have a pretrained large language model (the foundation model) with training data not containing ...
Hans-Peter Stricker's user avatar
6 votes
1 answer
1k views

How to obtain trigger words from a LoRA file?

LoRAs are smaller models that can be used to add new concepts such as styles or objects to an existing stable diffusion model. These LoRAs often have specific trigger words that need to be added to ...
Turamarth's user avatar
  • 201
1 vote
0 answers
84 views

How can I get ChatGPT to enforce syntax rules when converting code between languages?

The goal is to convert Python to MATLAB while preserving a=1 keyword argument syntax (standard is 'a', 1). Worked: a bunch of code-related prompts in the same session, followed by From now on, when ...
OverLordGoldDragon's user avatar
1 vote
1 answer
142 views

How to generate exact word(s) in generated image?

I want to design a prompt where I already have the main thing in the image fixed, but I need to have a text included in the image with exact word(s) I put in there. For example, this is my prompt. a ...
holydragon's user avatar
4 votes
1 answer
2k views

What prompt is required to have a subject fully in frame using Stable Diffusion based AI image generation?

When using an AI image generation package based on Stable Diffusion (For example, Automatic1111 Stable Diffusion web UI, or Stable Diffusion Infinity), what prompt (+ or -) is required to have your ...
Aaargh Zombies's user avatar
1 vote
2 answers
147 views

How to make ChatGPT be better at designing / visual tasks?

I've been using OpenAI's ChatGPT for a variety of tasks, and it's proven highly effective for a bunch of thing. But when it comes to more creative and design-centric tasks (especially in coding and ...
Coder Gautam YT's user avatar
-1 votes
1 answer
113 views

How would I have got ChatGPT to say "these symbols are not allowed in Kotlin"?

I am trying to understand if there is any way I could have worded my inputs better to get an exact answer from ChatGPT. I am using the free web version by open ai (https://chat.openai.com/) I was ...
user13267's user avatar
  • 295
2 votes
2 answers
1k views

How can I get leonardo.ai to draw a kite (bird) and not a kite (toy)?

This is a kite: Since "kite" is more commonly used to refer to the light-weight toy flown in the sky, I can't think of how to ask leonardo.ai to draw a kite (the bird). It seems hard (or ...
Rebecca J. Stones's user avatar
2 votes
2 answers
140 views

How to get ChatGPT with Plug-ins to dig deeper into search results instead of just returning them to me?

When I use ChatGPT with Plug-ins that can search the web or read URLs, it has a tendency to act like a search engine and nothing more. I ask it a question and it searches the web, reads the first ...
endolith's user avatar
  • 160
4 votes
2 answers
327 views

File format for generating error-free structured data with LLMs

I'm working on a project that requires generating structured data with Large Language Models (LLMs) like GPT-4. I've encountered issues with the output, as the LLM sometimes produces invalid JSON ...
Léonard Henriquez's user avatar
5 votes
1 answer
102 views

How to make the text-to-video generation keep some components the same throughout the video?

I generated this below video from this website and converted it into a gif file and attached here. I would like to ask for a solution that can keep the armor and the headwear the same throughout the ...
holydragon's user avatar
4 votes
1 answer
169 views

Prompt engineering GPT for numerical scores?

Background: I am currently working on an NLP project using GPT 3.5 via the OpenAI python API. Engineering good prompts seems to be the most critical part of my pipeline so far. Crucially I have long ...
user avatar
3 votes
3 answers
282 views

How do I encourage ChatGPT to speak more like me?

Providing an email I drafted, I asked ChatGPT to rewrite it to be more concise, while also asking the style of language to remain similar to the original. ChatGPT sometimes does okay with this request,...
Eric Lang's user avatar
3 votes
1 answer
258 views

How to effectively prevent prompt leaking via injection?

With the rise of GenAI, prompt injection attacks have become increasingly concerning. Let's say I wanted to design a GenAI application that answers with the color of the user's inputted object. For ...
Michael M.'s user avatar
9 votes
1 answer
732 views

Does asking ChatGPT (or other LLMs) to "talk like a pirate" degrade performance?

Here, "talk like a pirate" is just an example. For a more practical example, there have been a few questions here about asking ChatGPT to phrase an answer differently, for instance this one ...
Kaia's user avatar
  • 36
77 votes
6 answers
56k views

How to get ChatGPT to Stop Apologizing?

Is there a way to stop ChatGPT from excessively apologizing, when challenged, even when ChatGPT is correct in its reply? ChatGPT will start apologizing and start the replies with sentences like: I ...
Arbel's user avatar
  • 861
9 votes
4 answers
5k views

Can you have ChatGPT 4 "explain" how it generated an answer?

While I understand that GPT-4 does not use logic in the same way that a human does, is there some way to have ChatGPT "explain" itself?
dave20's user avatar
  • 109
8 votes
3 answers
2k views

Reserved words or commands for ChatGPT

I was wondering if there is some syntax or reserved words, operators or commands to work with the ChatGPT. For example, how do you put an updated context based on the documentation of a library? ...
Teocci's user avatar
  • 181
2 votes
1 answer
500 views

How do users create these dense-keyword prompts for leonardo.ai?

I recently used leonardo.ai (freemium) for the first time. I tried it out with my own prompts; some looked okay, but others not so much, and then I ran out of my daily tokens. I then browsed some ...
Rebecca J. Stones's user avatar
5 votes
1 answer
2k views

Will you be banned for "Jailbreaking" ChatGPT? [closed]

I understand that people have been "jailbreaking" using different prompt injections etc. So my first question is: Does this break T&C and as a result could this lead to a ban? My second ...
MintBerryCRUNCH's user avatar
2 votes
1 answer
119 views

Could genAI be used to generate reasonable scientific hypotheses?

Suppose I have a trained genAI and I give it some different experiments, their results, and I were to ask it to generate a plausible hypotheses of what happend. Would it be able to do this well? If ...
tryst with freedom's user avatar
3 votes
3 answers
311 views

How can I draw three cups in a row, the middle one blue, the outside ones red, and with one red cup taller than the other two cups?

I want to use an image for this Chinese.SE question to make my answer more vivid. The question asks about the Chinese sentence: 旁边那个大点儿的杯子是我的 To the side, the cup which is slightly bigger is mine. ...
Rebecca J. Stones's user avatar
11 votes
2 answers
759 views

How do I create the start of a forest fire?

I can create a "forest"1 and a "forest fire"2. However the forest fire is extremely fiery. I'd like to have something in-between the two, preferably somewhere near the start of a ...
Peilonrayz's user avatar
3 votes
1 answer
206 views

How to make ChatGPT responses about calendar/dates accurate?

I asked ChatGPT: what is the next 29th February that is Monday? It responded: To find the next 29th of February that falls on a Monday, we need to consider the leap years in the Gregorian calendar. ...
holydragon's user avatar
1 vote
1 answer
94 views

How can I prevent ChatGPT from making labelled / definition lists?

I've noticed that ChatGPT often writes lists with labels like this: Lorem ipsum: dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut ...
starball's user avatar
  • 410
4 votes
1 answer
351 views

Some of my important points being ignored in text-to-image generation. How to emphasize it to be in the image?

I am using ClipDrop/Stable Diffusion to generate some images with this specific prompt. big number 4 at the center of the image with forest in the background and this is the result. As you can see, ...
holydragon's user avatar
3 votes
1 answer
363 views

Is it possible to prompt ChatGPT into playing a competent game of hangman?

I asked ChatGPT the following (some of the back-and-forth is omitted for space reasons): Can you play hangman? Can you think of a word? E And ChatGPT was like: Great guess! There is one "e&...
Rebecca J. Stones's user avatar
7 votes
1 answer
527 views

How can I effectively create a prompt to generate realistic limbs and fingers using Leonardo.ai?

Image generation - midjourney, leonardo, etc - are not good at generating realistic hands. It is common to see hands with extra fingers or in weird shapes. As an example, a basic prompt like this on ...
Andy's user avatar
  • 170
7 votes
1 answer
2k views

What do (parentheses) and [square brackets] do in image prompts?

I've seen a number of prompts that put parentheses or square brackets around certain words/phrases. This seems to be used across multiple frontends (Automatic1111, ComfyUI, NovelAI, ...) and ...
SirBenet's user avatar
  • 1,790