Discover and read the best of Twitter Threads about #prompting
Most recents (3)
Welcome to #chatbotvoice2023 from Berlin.
I'm throwing up some tidbits around #conversationalai live from the 5th World Chatbots & Voice Summit from Berlin.
I'm throwing up some tidbits around #conversationalai live from the 5th World Chatbots & Voice Summit from Berlin.
Testing is an impossible manual task and it needs to be automated. Done wrong, it can cost heavily. So it is a huge, but important challenge. 
Each of these images are the exact same prompt except the next one has 1 extra prompt set in the series.... a thread
#AI #AIart #Prompting #PromptsMastery #MasteringPrompting
Exact same seed & SD setup (no starter img)
#AI #AIart #Prompting #PromptsMastery #MasteringPrompting
Exact same seed & SD setup (no starter img)
Each of these images are the exact same prompt except the next one has 1 extra prompt set in the series.... (cont thread)
#AI #AIart #Prompting #PromptsMastery #MasteringPrompting
Exact same seed & SD setup (no starter img) (cont)
#AI #AIart #Prompting #PromptsMastery #MasteringPrompting
Exact same seed & SD setup (no starter img) (cont)
Each of these images are the exact same prompt except these have exactly 1 extra prompt set in the series so far (cont thread)
#AI #AIart #Prompting #PromptsMastery #MasteringPrompting
Exact same seed & SD setup (no starter img) but each image is a different SD version
#AI #AIart #Prompting #PromptsMastery #MasteringPrompting
Exact same seed & SD setup (no starter img) but each image is a different SD version
📢 New paper alert! How does one adapt a pre-trained visual model to novel downstream tasks without task-specific finetuning or any model modification? Inspired by #prompting in NLP, our new paper investigates Visual Prompting. (1/5)
Given input-output image example(s) of a new task a new input image, the goal is to produce the output image, consistent with the given examples. Posing this problem as simple image inpainting, literally just filling in a hole in a concatenated grid-like visual prompt image (2/5)
The secret ingredient to get this to work is the training data. To obtain image data that better resembles our visual prompts, we curated 88k unlabeled figures from paper sources on Arxiv. (3/5)
