I was never able to get appreciably better results from 11 labs than using some (minorly) trained RVC model :/ The long scripts problem is something pretty much any text-to-something model suffers from. The longer the context the lower the cohesion ends up.
I do rotoscoping with SDXL i2i and controlnet posing together. Without I found it tends to smear. Do you just do image2image?
Coqui for TTS, RVC UI for matching the TTS to the actor’s intonation, and DWPose -> controlnet applied to SDXL for rotoscoping
All the models I’ve used that do TTS/RVC and rotoscoping have definitely not produced professional results.
This isn’t really accurate either. At the moment of generation, an LLM only has context for the input string and the network of text tokens it’s been assigned. It pulls from a “pool” of these tokens based on what it’s already output and the input context, nothing more.
Most LLMs have what are called “Top P”, “Top K” etc, these are the number of tokens that it ends up selecting from based on the previous token, alongside the input tokens. It then randomly chooses one based on temperature settings.
It’s why if you turn these models’ temperature settings really high they output pure nonsense both conceptually and grammatically, because the tenuous thread linking the previous token’s context to the next token has been widened enough that it completely loses any semblance of cohesiveness.
Why would I save something for posterity when I could save it for posterior?
Saving this comment for posterior
I still think hydrogen cells are a better long-term solution than BEVs. It’s way ahead of it’s time considering tbe infrastructure requirements, but I assume at some point after everyone is using BEVs and realizing the comparative downsides it’ll see a revival.
You wouldn’t necessarily punish the person that modified Linux either, you’d punish the person that uses it for a nefarious purpose.
Important distinction is the intention to deceive, not that the code/model was modified to be able to be used for nefarious purposes.
In regards to the open source models, while it makes sense that if a developer takes the model and does a significant portion of the fine tuning, they should be liable for the result of that…
This kind of goes against the model that open source has operated on for a long time, as providing source doesn’t represent liability. So providing a fine-tuned model shouldn’t either.
The ISS is aging, and for safety’s sake, NASA intends to incinerate the immense facility around 2031. To accomplish the job, the agency will pay SpaceX up to $843 million, according to a statement released on June 26.
See you guys in 2040
This is interesting but I’ll reserve judgement until I see comparable performance past 8 billion params.
All sub-4 billion parameter models all seem to have the same performance regardless of quantization nowadays, so 3 billion is a little hard to see potential in.
I seriously doubt the viability of this, but I’m looking forward to being proven wrong.
Judging by my bank account I’m transitioning to non-profit status as well.
In my experience these open models is where the real work is being done. The large supervised models like DALL-E etc are more flashy but there’s a lot more going on behind the scenes than the model itself so it feels like it’s hard to gauge the real progress being done
thinking about Werner Von Braun and the peenemunde Yea I’m not sure anyone has a leg to stand on when it comes to “stolen” technology and space
It’s usually not the water itself but the energy used to “systemize” water from out-of-system sources
Pumping, pressurization, filtering, purifying all take additional energy.
The problem is notably “powerful”, AIs need pretty significant hardware to run well
As an example the snapdragon NPUs I think can barely handle 7B models.
This is because all LLMs function primarily based on the token context you feed it.
The best way to use any LLM is to completely fill up it’s history with relevant context, then ask your question.
Facebook is trying to burn the forest around OpenAI and other closed models by removing the market for “models” by themselves, by releasing their own freely to the community. A lot of money is already pivoting away towards companies trying to find products that use the AI instead of the AI itself. Unless OpenAI pivots to something more substantial than just providing multimodal prompt completion they’re gonna find themselves without a lot of runway left.