Пікірлер
@moresignal 15 күн бұрын
Thanks (and happy birthday) Jesus!
@MH-xx6df 15 күн бұрын
This is genius. Love the stack and innovation here
@giorgiosegalla2155 Ай бұрын
Simple and really useful video!
@braudhadoch3432 Ай бұрын
So instead of a keyboard and a mouse we can talk to our computers? Would be great to have a swarm of drones to protect me and commendable by voice. THat I would buy.
@EddiksonPena Ай бұрын
I love love love this and thank you for sharing, how did you build your tools ?
@joshewa1682 Ай бұрын
Great now my AI is going to get all emotional on me when I get upset from its hallucinations
@dalidoe4537 Ай бұрын
Gorgeous lady 😍
@mquant001 Ай бұрын
espectacular
@mquant001 Ай бұрын
brutal
@marcesmack Ай бұрын
Que copado!
@jesuscopado-en Ай бұрын
jajajaja muchas gracias! :D
@timstevens3361 Ай бұрын
i dont want Anything to do with openai ! they can keep their keys n apis n chatcrap to themselves. i like actual open ai like ollama n llama based models. one day ppl will say openai who ?
@jesuscopado-en Ай бұрын
I'm also a big fan of open-source, if I can I'll use that instead of OpenAI/Claude, but it's undeniable they have the edge when it comes to these innovations like Realtime API
@Samt2b Ай бұрын
I have seen your KZbin it's amazing. I have a question can you combine your all videos and make an AI Sementa live video when you asked her she responded that instead of audio make her a video with the expiration from the previous girl that you make emotion picture to video
@jesuscopado-en Ай бұрын
I'm glad you like my channel :) That'd be complicated, cause the avatar video models and lip sync models are still very slow, but soon in for future for sure this will be possible!
@simonaero Ай бұрын
brilliant! keep up the good work.
@jesuscopado-en Ай бұрын
Thanks a lot! Will do for sure :)
@hectorprx Ай бұрын
Very Nice, All The Best
@jesuscopado-en Ай бұрын
Appreciate it :)
@hectorprx Ай бұрын
Thank you; your explanation of the process and implementation nails it. All the Best
@jesuscopado-en Ай бұрын
Thanks a lot :)
@aubisoka Ай бұрын
i need to use lora there
@Samt2b Ай бұрын
i hop you soon show us how to develop sono or Audio like ai
@jesuscopado-en Ай бұрын
I'll work on that for sure soon!
@waqarnawaz5012 Ай бұрын
Nice explanation 👌 looking forward to more from you.
@jesuscopado-en Ай бұрын
Thanks a lot :)
@LacunzaOriginal Ай бұрын
Great vid!!! in what program and how do you make your subtitles with that style?
@almudenagrande8505 Ай бұрын
Video increible!!' Muchas gracias por la ayuda!!!
@danielpenades3749 Ай бұрын
Jesus, what is the video you are referring to here? 7. Demo my app: prompt generator with Groq API + TogetherAPI FLUX API • API access means we can build applications on top of it • Refer to video where I build this live in less than 15 mins using ChatGPT Canvas and Copilot (100% Python)
@danielpenades3749 Ай бұрын
Jesus, excellent! Yes, please, a video about prompt engineering to prompt more details. Thank you very much!!
@jesuscopado-en Ай бұрын
Thanks Daniel! And I'll work on that one for sure soon :)
@ababiya_worku Ай бұрын
nice one! you can also add extra sauce codes using claude! but remember, this is their daily play at openai, they can rly make this in seconds or the real Samantha at this point, but they don't wanna freak the society! not yet! I'm pretty sure sama is using Skies voice exclusively on his phone, I'm talking about the real Samantha, but no one sees him using ChatGPT!
@rincondesalva Ай бұрын
Buenas, muy bien este vídeo también. Sí, sería estupendo profundizar en ingeniería de prompts, a mí me interesa perfiles femeninos con enfoque fashion, pero no solo retrato, también half y full body. Gracias…
@jesuscopado-en Ай бұрын
Genial que te haya gustado el vídeo! Pues dentro de poquito haré vídeo sobre ello, gracias por el feedback :)
@LearnPythonWithMuiz Ай бұрын
Good job mate.
@jesuscopado-en Ай бұрын
Thanks! :)
@LearnPythonWithMuiz Ай бұрын
You should have more subscribes mate.
@LearnPythonWithMuiz Ай бұрын
@@jesuscopado-en Im using your AI for my work right now
@Recuper8 Ай бұрын
any high quality open source image-to-video options?
@jesuscopado-en Ай бұрын
Yep, just recently Mochi1 was released. Check their repo: github.com/genmoai/models And playground: www.genmo.ai/play
@ProlVid Ай бұрын
I like your work. This is awesome. How can I build this for myself usisng the tools you provided? I watched the other video but still can't figure out the process. Where to start from?
@jesuscopado-en Ай бұрын
Glad you like it :) Hhmm I'd honestly recommend to ChatGPT your way into understanding. If you're new to Python or programming, ask for the basics, then take screenshots or copy paste errors and ask for clarification, that would both help you learn and progress in the projects.
@matthiasjaro100 Ай бұрын
Great content. You got a follow, good sir ❤
@jesuscopado-en Ай бұрын
Appreciate that 🫶
@yapyh2872 Ай бұрын
Nice. Do you have a tutorial for creating different angles of a character similar to this realness so that it can be later used for model training?
@jesuscopado-en Ай бұрын
Will create one in the next days/weeks for sure! A LoRA tutorial for the best character consistency
@rabelmarketing Ай бұрын
Hi brother, I really appreciate the content of both videos. The question is, I have a model created with artificial intelligence and I want to make it more realistic and with better quality, then make a video with that image. How could it be done that way? Thanks!
@jesuscopado-en Ай бұрын
Glad you liked the videos :) You mean you already fine-tuned a stable diffusion or flux model but you don't get realistic images? I'd say maybe work more on those images for your LoRA. I'll be posting a video just about that in the next days/weeks
@Throttlemouth001 Ай бұрын
Hi, getting stuck at Connected to OpenAI realtime: - the mic turns on and nothing else happens, no error codes even. API Keys set.
@Throttlemouth001 Ай бұрын
btw Together now only offers $1 of free credits.
@jesuscopado-en Ай бұрын
Ah dang... Dunno what to tell you. Annoying to not have the error trace yeah. Maybe the endpoint is not correctly set... I'll soon update the repo with the latest Chainlit version (not the alpha) and maybe that helps.
@Throttlemouth001 Ай бұрын
@@jesuscopado-en Cheers! :D
@soumikganguly8038 Ай бұрын
Looks like gpt-4o-realtime-preview, 2024-10-01 is available only in eastus2 and swedencentral
@Prh34434 Ай бұрын
Great video Jesus! Thanks for sharing. 🙏 Subscribed!
@jesuscopado-en Ай бұрын
Glad you liked the video! :)
@soamjena Ай бұрын
Nice explanation! What tool are you using for the subtitles ? It looks nice.
@jesuscopado-en Ай бұрын
Glad you liked the explanation! :) I'm using screen.studio, a MacOS app. But that app uses internally the Whisper speech-to-text model from OpenAI to create those subs. And I'm sure many other tools implement Whisper as well
@soamjena Ай бұрын
@ I use screen studio for videos yes! But I liked the captions here. You mean screen studio auto generated the captions for you ? Seems I need to double check my features list haha ha
@jesuscopado-en Ай бұрын
@@soamjena hahaha, yep, directly in screen studio
@belencastillodiaz4514 Ай бұрын
Woah I’m in shock!!! 😮😮
@florianlepriol Ай бұрын
Great video !
@jesuscopado-en Ай бұрын
Thanks a lot! :)
@ihebakermi943 Ай бұрын
can you create project like this without using azure ?
@jesuscopado-en Ай бұрын
Yess, also directly using OpenAI API :) Just need to configure those env variables
@baz813 2 ай бұрын
The interuptability looks really good, 'she' shuts up quickly when you start talking
@jesuscopado-en Ай бұрын
Yess, that's crazy good, and contributes a lot to the feeling of having a human-like conversation :D
@TeExorcizoConHardTecno 2 ай бұрын
Excellent synthesis of the sites from which to work with images and video using AI. There isn’t much content on KZbin yet that explains so clearly how to understand and apply iterations with AI at this level. With so much progress in just a few months, it’s difficult to keep up with everything! The moustache plays a key and differential role here tho
@saipreethamreddy4340 2 ай бұрын
I just want to know like, after developing this how did you test it for robustness and fairness?
@edinsonriveraaedo292 2 ай бұрын
amazing work man, I pretty appreciate your efforts and new ideas that you are sharing
@jesuscopado-en 2 ай бұрын
I appreciate that! :)
@adrianpetrescu8583 2 ай бұрын
At this time Samantha have memory ? can she remember what you talk in last chat or 3 days ago ?
@jesuscopado-en 2 ай бұрын
Noup, not yet, but I'll implement that soon! In a similar fashion of how ChatGPT does it now
@Pavetl 2 ай бұрын
anyone knows why Groq is not letting me creating an organization and consequently an API Key?
@jesuscopado-en 2 ай бұрын
Huh... Dunno... :/. But I'll be uploading a video soon showing how to create the Groq API key
@sambit5526 2 ай бұрын
always getting "Failed to connect to OpenAI realtime:"
@jesuscopado-en 2 ай бұрын
Ah dang, everybody that I know has been able to replicate it, if you send me the full log trace of the error I can try to help
@Stephan808 2 ай бұрын
wow amazing! But I didnt get it. you use flux for image creation which is absolute awesome! Do you run it locally? Im running it in forge on runpod. Do you have an idea, how I can connect that frum runpod to samantha?
@jesuscopado-en 2 ай бұрын
It's running through the TogetherAI API. Well, you could pull the repo from runpod and then open a ngrok tunnel to use it from your machine
@Stephan808 Ай бұрын
@@jesuscopado-en ahh thx! good idea!
@KevinKreger 2 ай бұрын
More subs for Jesús
@jesuscopado-en 2 ай бұрын
Appreciate that! :)
@LePsyclone 2 ай бұрын
Great project man. I can't get it to run though. The voice/mic button doesnt appear and i get errors. Do you have a community I can join to trouble shoot? I would love to build on this project!
@jesuscopado-en 2 ай бұрын
Ah dang, if it's related to the mic try searching in Chainlit open issues -> github.com/Chainlit/chainlit/issues
@toshailendra 2 ай бұрын
cool… i can see the agentic future is here
@jesuscopado-en 2 ай бұрын
Completely agree!!
@TheYules 2 ай бұрын
That looks awesome Jesús ! Would it be possible to use local LLM (with Ollama for example) and local stable diffusion models (using forge webui or comfyui)?
@jesuscopado-en 2 ай бұрын
Yess, absolutely, if you're lucky enough to have a beefy GPU for that hehe. You'd need to change the llm instantiation that uses Groq for Ollama -> python.langchain.com/api_reference/ollama/llms/langchain_ollama.llms.OllamaLLM.html#ollamallm
@TheYules Ай бұрын
@@jesuscopado-en Thanks for the tps, will look into that :) You don't need a super beefy GPU to run all LLMs some mistral or llama models are useable on more modest configs too!
@jesuscopado-en Ай бұрын
@@TheYules yeah, you're right! But you gotta stick to less than 7b parameter quantized models which are not that great. I usually test them on LM Studio app on my mac, great app actually! I always find simpler to go to Groq/OpenAI APIs as I don't worry about privacy (yet) and value the better performance
@MMABeijing 2 ай бұрын
you look shy when you talk to her, that's cute
@jesuscopado-en 2 ай бұрын
hahahaha, wait till I configure her with Scarlett Johansson's voice :D
@joeg3117 2 ай бұрын
wow very impressive !! love your content, and keep it up !
@jesuscopado-en 2 ай бұрын
Thanks a lot! :)