fastsdxl.ai
AI
image generation
SHOW HN2024
444points
104comments
#93of 3,515 in 2024
Top 3%of 2024 by points
How HN took it
MixedNo clear lean
22 positive, 35 neutral or asking, 8 mixed, 11 critical, out of 76 comments about the project. Thread score +0.12.
Execution: 2 for, 10 againstPerformance: 8 for, 0 againstIdea: 3 for, 0 againstDesign: 3 for, 0 againstPricing: 1 for, 0 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Very fast generation speed
From 4 comments
Great speed! As for the quality, I borrowed the query ([1]) that people used to test Stable Diffusion 3 and other models today: "Photo of a red sphere on top of a blue cube.…
krasin on HNwow! this is really fast. this is actually at the speed I want image generation to be at. it makes me want to explore and use the tool. everything else has felt like begrudgingly…
SeanAnderson on HNThis is incredible. The reduction in latency has a profound effect in terms of the way I interact with this type of tool. The speed benefit is more than just more image…
danielecook on HNOoooookaaaaaay.... This is faster than autocomplete. Amazing.
rcarmo on HN
Fun and intuitive demo interface
From 2 comments
I love this demo. It's easily accessible, fast, and intuitive. It's stunning that we can get this level of quality so easily.
Reubend on HNAbsolutely love this. Wish URLs were shareable! `late 90s movie poster, 24 hour clock movie "2: Electric Boogaloo" dan aykroyd1` turned out great
airstrike on HN
Objections
Image quality and artifacts such as malformed limbs and wrong counts
From 3 comments
Still issues with limbs when using AI generative artwork... https://fastsdxl.ai/share/0y54bhvalknv
edf13 on HNLooking forward to it once it is refined. It still creates some strange artifacts. Within the HN message, the demo image of the baby raccoon in priest robes, one can count five…
ongytenes on HNWow this is fast! The results also look great, but the more I see AI generated images the more I believe it is not going to eat jobs. Almost none of the results are production…
tdudhhu on HN
Weak prompt adherence for spatial relations
From 2 comments
Great speed! As for the quality, I borrowed the query ([1]) that people used to test Stable Diffusion 3 and other models today: "Photo of a red sphere on top of a blue cube.…
krasin on HNSpatial prompt adherence is a general missing piece is SDXL (or previous versions of the SD). Hoping that the SD will get it into a good shape as your examples! Test the example…
treesciencebot on HN
Bias toward beautiful people in portraits
From 2 comments
And also what it is not capable of doing too... Simply try to get it to output an image with a female that's not a beauty queen. Even when specifically prompted to produce an…
lelag on HNI got some unattractive results easily: https://fastsdxl.ai/share/dfxtkr3r0w3z https://fastsdxl.ai/share/e70xgiudn8j0 But when I switched the prompt to include "portrait", yeah…
CapricornNoble on HN
Requests
Shareable URLs or seed display
From 2 comments
Absolutely love this. Wish URLs were shareable! `late 90s movie poster, 24 hour clock movie "2: Electric Boogaloo" dan aykroyd1` turned out great
airstrike on HNproviding the seed would have allowed it to be shared
scottmf on HN
Card-based or game variants
From 2 comments
Woah, that's pretty cool. Wondering if it can be converted into a card-based game
lakshyaag on HNI've had an idea for a cards vs humanity style game but using image generation instead, there's a central card for the round and you add something from your hand and then pick…
Zircom on HN
Fix seed-increment behaviour
From 2 comments
Insanely cool :) One bug though: when I increment the seed, it renders two image and it takes a bit of jumping up and down in seed numbers to get to the same image.
tiborsaas on HNlove it! I have to log off but I should let you know it seems like the generation is different depending on whether you arrow up or arrow down into the seed when the focus is on…
airstrike on HN
Questions
Cost per image and API pricing
From 2 comments
Any plans to make an API? I'm building a website to catalog fairly common objects, and could use images to spice it up. I was looking at pexels...but this is just so much better.…
smallerfish on HNThis is amazing. How much does it cost per image?
diego_sandoval on HN
Local hardware requirements
From 2 comments
What's the RAM and speed like for local inference?
01HNNWZ0MV43FF on HNIt's using ~15GB VRAM
r-k-jo on HN
Alternatives named
Replicate SDXL Lightning UI
From 1 comment
For posterity, SDXL Lightning is open source on Hugging Face with a relatively-permissive license: https://huggingface.co/ByteDance/SDXL-Lightning There are a few other UIs for…
minimaxir on HN
Stable Cascade
From 1 comment
Spatial prompt adherence is a general missing piece is SDXL (or previous versions of the SD). Hoping that the SD will get it into a good shape as your examples! Test the example…
treesciencebot on HN
Midjourney
From 1 comment
Midjouney is more advanced and some of the output is definitely job stealingly good. It can do excellent photo real, sketch, pixel art, diagrams, painting, digital painting, 3d,…
jjbinx007 on HN
SDXL Turbo
From 1 comment
What is the difference between SDXL turbo (released last november) and lightning (released 2 days ago?)? I havent seen any discussion of lightning on here the last few days and…
supermatt on HN