Have AI write the code, you review!
PROMPT ENGINEERING
-
Claude API Hackathon in London: 200+ Developers Build
By
–
We’re excited to host over 200 developers at our London hackathon today! Hackers are creating projects with the Claude API, learning prompt engineering best practices, and connecting with our technical team. Stay tuned to see what they #BuildwithClaude!
-
Prompt Engineer: The World’s Fastest Disappearing Job
By
–
The fastest disappearing job in the world: 'Prompt Engineer'.
-
Human-AI Effort Distribution Remains at 80-20 Split
By
–
Hard to say. But probably still 80-20 in terms of human-AI effort.
-
Midjourney prompt complexity versus token efficiency explained
By
–
I hear this a lot, that MJ only listens to 50 tokens or what not. Might be technically true. But regardless, here is an example between a “simple” prompt (left) and an expressive and “complex” prompt (right) No matter how much I try to shorten the prompt. Even if I remove
-
Midjourney Token Weights Impact on Image Generation Output
By
–
Not true. Run them yourself and test. I’ve made 50.000+ images on MJ, and I can promise you there is subtle nuance. Even if the weights of tokens are displayed as super low they have influence over the final output.
-
Fine-tuning SDXL for Upside Down Image Generation
By
–
SDXL isn't very good at upside down images. I wanted to play on this, so I fine-tuned the model on some upside down people (but didn't caption them as upside down). It extrapolates the upside-down-edness in a fascinating way. https://
replicate.com/fofr/sdxl-upsi
de-down
… -
Halo Ring SDXL Fine-Tune Model Released for Image Generation
By
–
I had to take the bait from @SmokeAwayyy
. Here's a Halo Ring SDXL fine tune: https://
replicate.com/fofr/sdxl-halo
-ring
… Try with prompts like:
"A video game render of a TOK halo ring, low angle" -
Porting Regional Prompting Extension to Diffusers Framework
By
–
@hakomikanx Do you know how easy it would be to port your regional prompting extension to diffusers?