Live data from Hacker News

AI model for near-instant image creation on consumer-grade hardware

surrey.ac.uk

1–10 of 55 posts

Re: AI model for near-instant image creation on consumer-grade hardware

#5

Here is the demo https://huggingface.co/spaces/ChenDY/NitroFusion_1step_T2I I'm unable to get anything that looks as good as the images in the README, what's the trick for good image prompts?

I always just assume it's the magic of selection bias.

Re: AI model for near-instant image creation on consumer-grade hardware

#6

Here is the demo https://huggingface.co/spaces/ChenDY/NitroFusion_1step_T2I I'm unable to get anything that looks as good as the images in the README, what's the trick for good image prompts?

I get pretty close result with seed 0

paper https://i.imgur.com/l90WYrT.png

replication on hf https://i.imgur.com/MqN1Qwc.png

Re: AI model for near-instant image creation on consumer-grade hardware

#8

Here is the demo https://huggingface.co/spaces/ChenDY/NitroFusion_1step_T2I I'm unable to get anything that looks as good as the images in the README, what's the trick for good image prompts?

I get pretty close result with seed 0 paper https://i.imgur.com/l90WYrT.png replication on hf https://i.imgur.com/MqN1Qwc.png

the imgur link is bad, but I hadn't noticed the prompt tucked away in those reference images and that helps. Thanks

(I had asked for a rock climber dangling from a rope, eating a banana, and they were wildly nonsensical images)

Re: AI model for near-instant image creation on consumer-grade hardware

#9

Here is the demo https://huggingface.co/spaces/ChenDY/NitroFusion_1step_T2I I'm unable to get anything that looks as good as the images in the README, what's the trick for good image prompts?

I had the same issue, so I pulled in the SDXL refiner. Night and day better even at one step.

https://gist.github.com/deckar01/7a8bbda3554d5e7dd6b31618536...

Post reply on HN