Mindsetware
@mindsetware.bsky.social
Solopreneur Engineer. 🧠 mindset + 🦾 automations + 📣 marketing
👎 Most talking AI models break when you add multiple people to a conversation.
✅ MultiTalk shows a lot of potential to solve this, using a new approach that correctly binds multi-stream audio to specific characters.
Github repo 👇
✅ MultiTalk shows a lot of potential to solve this, using a new approach that correctly binds multi-stream audio to specific characters.
Github repo 👇
June 22, 2025 at 12:48 AM
👎 Most talking AI models break when you add multiple people to a conversation.
✅ MultiTalk shows a lot of potential to solve this, using a new approach that correctly binds multi-stream audio to specific characters.
Github repo 👇
✅ MultiTalk shows a lot of potential to solve this, using a new approach that correctly binds multi-stream audio to specific characters.
Github repo 👇
I just discovered MAGREF.
This fine-tuned Wan 2.1 model keeps faces and objects consistent across video scenes.
Single subject or multi-reference mode - both work surprisingly well.
This fine-tuned Wan 2.1 model keeps faces and objects consistent across video scenes.
Single subject or multi-reference mode - both work surprisingly well.
June 20, 2025 at 4:47 PM
I just discovered MAGREF.
This fine-tuned Wan 2.1 model keeps faces and objects consistent across video scenes.
Single subject or multi-reference mode - both work surprisingly well.
This fine-tuned Wan 2.1 model keeps faces and objects consistent across video scenes.
Single subject or multi-reference mode - both work surprisingly well.
Big fan of Wan2GP by DeepBeepMeep for running video generation on low-end GPUs. The name might be misleading, but it actually supports multiple open-source models including Wan (plus its derivatives), Hunyuan Video, and LTV Video.
Link to the repo, if you are interested 👇
Link to the repo, if you are interested 👇
June 17, 2025 at 11:52 PM
Big fan of Wan2GP by DeepBeepMeep for running video generation on low-end GPUs. The name might be misleading, but it actually supports multiple open-source models including Wan (plus its derivatives), Hunyuan Video, and LTV Video.
Link to the repo, if you are interested 👇
Link to the repo, if you are interested 👇
🔥 5-min guide: Build your personal AI research assistant that automatically searches & saves everything to Notion. From research to organized notes, automatically. Here's how → 🧵 #ResearchTools
December 3, 2024 at 7:20 PM
🔥 5-min guide: Build your personal AI research assistant that automatically searches & saves everything to Notion. From research to organized notes, automatically. Here's how → 🧵 #ResearchTools
Supercharge your AI systems with the CODE method 🧠
How I turned Tiago Forte's Second Brain framework into a powerful data pipeline for AI automation. 🧵👇
How I turned Tiago Forte's Second Brain framework into a powerful data pipeline for AI automation. 🧵👇
December 3, 2024 at 3:37 AM
Supercharge your AI systems with the CODE method 🧠
How I turned Tiago Forte's Second Brain framework into a powerful data pipeline for AI automation. 🧵👇
How I turned Tiago Forte's Second Brain framework into a powerful data pipeline for AI automation. 🧵👇
"The problem isn't your goals. It's your systems"
A thread on why successful people focus on systems, not goals (and how it transformed by dev workflow)🧵
A thread on why successful people focus on systems, not goals (and how it transformed by dev workflow)🧵
December 1, 2024 at 10:55 PM
"The problem isn't your goals. It's your systems"
A thread on why successful people focus on systems, not goals (and how it transformed by dev workflow)🧵
A thread on why successful people focus on systems, not goals (and how it transformed by dev workflow)🧵
👋😄 Engineering solo businesses with AI automation. Would you like to follow my journey of building efficient systems from scratch? ⚡
November 30, 2024 at 11:16 PM
👋😄 Engineering solo businesses with AI automation. Would you like to follow my journey of building efficient systems from scratch? ⚡