AI Sound and Foley Production
Creators are enthusiastic about the potential for professional film sound effects and foley, despite concerns regarding high subscription pricing for premium tools.
While creators appreciate the performance benchmarks and sound production capabilities, critics strongly condemn the ethical fraud in real estate staging and the model's environmental impact.
Creators are enthusiastic about the potential for professional film sound effects and foley, despite concerns regarding high subscription pricing for premium tools.
Critics argue that AI-generated property photos are misleading and fraudulent, creating unrealistic expectations for buyers by hiding property imperfections.
Users highlight impressive generation speeds and low costs compared to competitors, though some dismiss public benchmarks as easily manipulated.
Skeptics label the technology as 'AI slop' and criticize the heavy environmental cost of data centers for outputs they deem purposeless.
Bro……I wonder if there’s a path to us being able to upload a video with no sound and the ai doing all the foley and sound effects USING the video…. Omfg if that happens, THAT would be a game changer of massive, massive proportions.
audio sounds really nice
I'm way behind in imagegen - only using it occasionally for roleplaying tokens, goofing around, and random personal assets. To me, this is nuts. It's able to create images in like 2 seconds... before with chatgpt it would take 30s-1m for the same quality image. I don't get the negative comments here
Llama was great for research and propelling the opensource community but they haven't been a serious competitor in a while. Whereas Google is one of the top 3 AI labs in America.
Such impressive outputs, great work and breakdown as always Tim.
Nano Banana 2 Lite 😍
Bro……I wonder if there’s a path to us being able to upload a video with no sound and the ai doing all the foley and sound effects USING the video…. Omfg if that happens, THAT would be a game changer of massive, massive proportions.
audio sounds really nice
I'm way behind in imagegen - only using it occasionally for roleplaying tokens, goofing around, and random personal assets. To me, this is nuts. It's able to create images in like 2 seconds... before with chatgpt it would take 30s-1m for the same quality image. I don't get the negative comments here
Llama was great for research and propelling the opensource community but they haven't been a serious competitor in a while. Whereas Google is one of the top 3 AI labs in America.
Such impressive outputs, great work and breakdown as always Tim.
Nano Banana 2 Lite 😍
Thanks for telling me abt nano banana after the trend 👍👍
Only for the price of 100L of water and data centers that impact the environment more than nothing the world has ever seen you can now produce AI slop that has no purpose or value.
This!! 2 months ago while looking for apartments, the majority of the pics shown were generated by AI. The pictures generated by AI often looked much more brighter, cleaner and larger and when I visited them in person, they were the opposite. I wasted so much time visiting due to this. I understand the intention but the pictures are so wrong most of the time and hide so much imperfection that it should be illegal for false advertisement.
The first example of generating home interiors fills me with indescribable hatred. Recently real estate agents have taken to running every dilapidated unsellable apartment through these AI filters, and you have to scroll through a dozen of these Ikea-chic images of what the apartment presumably could look like, before you are allowed to see the horrors they are trying to peddle at insane prices.
It’s not a universal win, but grok outperforms on 2 of the metrics, and is close on a third. Image editing: banana 1308, grok 1329 Image generation: banana 1251, grok 1174 (grok loses, but is close) Cost: banana 3.4 cents, grok 2 cents Grok is a good image model, so it isn’t totally surprising, but it’s weird that they’d pick a set of metrics where they’re not the clear winner.
Public AI benchmarks are fucking stupid and can be completely ignored. Too gamed. However, your advice is right. KREA2 and Ideogram4. The latter being less commercially usable without what I would surely assume is a pain in the ass.
Tell us about Nano Banana now? 😂😂😂 You're 6 months late 💁♂️
I was surprised with how well grok imagine performed when reviewing fast image generation. It balances quality, speed and cost really well with under $0.02 per 1K image within a few seconds.
In a sane world, this would be a clear cut case of false advertisement, and the real estate agents would be held liable for fraud. Sadly, we don't live in a sane world.
gemini is so far behind. starting to wonder if their strategy is launching the low cost alternative to image/text models. last release was 3.5 flash
Graph based on sampled comments per item (n≤30)
Theoretically Media
minimaxir
BerriAI/litellm
BerriAI/litellm
thedepartmentofexternalservices/digit-comfyui
emono/loop
achimala/samebot-zero
Portkey-AI/models
ehamiter/aicalart
openclaw/openclaw
HeyPuter/puter
AtlasCloudAI/atlascloud_comfyui
Comfy-Org/docs
lobehub/lobe-icons
a5c-ai/babysitter
mnthe/gemini-mcp-server
TGYD-helige/pi
HeyPuter/puter
bitroot-org/bitroot-org-website
TanStack/ai
promptfoo/promptfoo
TanStack/ai
Banhang-Chogao/zola
vjpixel/diaria-studio
poe-platform/poe-code
Mysios-Labs-inc/nazca
Comfy-Org/workflow_templates