Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Stop relying on generic AI output Train a model on your world, your character, your style, and reuse it forever That is the idea behind LTX Trainer, an open-source training framework that lets you train reusable IC-LoRAs for specific video transformations like colorization, deblur, decompression, reference sheet control, and... show more

Amira Zairi

58,602 subscribers

28,574 views • 3 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Midjourney sref + Sora 2 Pro is the sauce. With one Midjourney style image, you can give a specific style for your entire project. I created two different 12-second clips and edited them together. Some details aren’t fully consistent, like the iPod or AirPods because the clips were made separately from a single image (Character in a specific style). It could be fixed in post-production, but that would take more time, and this was more of an experimental test. It would be great to add the actual product image with the current one to maintain product consistency. I feel like if there were a way to add 2–4 images into this workflow, it could open up a lot more possibilities and consistency. With an API, it could be possible. Or let’s see what Veo 3.1 has to offer.

Midjourney sref + Sora 2 Pro is the sauce. With one Midjourney style image, you can give a specific style for your entire project. I created two different 12-second clips and edited them together. Some details aren’t fully consistent, like the iPod or AirPods because the clips were made separately from a single image (Character in a specific style). It could be fixed in post-production, but that would take more time, and this was more of an experimental test. It would be great to add the actual product image with the current one to maintain product consistency. I feel like if there were a way to add 2–4 images into this workflow, it could open up a lot more possibilities and consistency. With an API, it could be possible. Or let’s see what Veo 3.1 has to offer.

Allar Haltsonen

10,141 views • 11 months ago

So this is the dream: A video world model that takes an image as input and renders an environment you can explore and interact with. It could be a constant video stream - like your own lofi girl! Or you could jump in and “play” as a character.

So this is the dream: A video world model that takes an image as input and renders an environment you can explore and interact with. It could be a constant video stream - like your own lofi girl! Or you could jump in and “play” as a character.

Justine Moore

95,492 views • 1 year ago

POWER IS PLANE-SPECIFIC! In other words, you’re going to develop much more sport-specific POWER by training in planes closely related to your sport. Baseball is a sport that relies heavily on being powerful, and efficient in the frontal and transverse plane. With that being said, a lot of our training focuses on developing power in these planes.

POWER IS PLANE-SPECIFIC! In other words, you’re going to develop much more sport-specific POWER by training in planes closely related to your sport. Baseball is a sport that relies heavily on being powerful, and efficient in the frontal and transverse plane. With that being said, a lot of our training focuses on developing power in these planes.

Alex Simone

28,220 views • 11 months ago

hani saying that the reason why his relationship with woongki recently got better is because they’ve been talking a lot and he thinks he’s relying on him a lot more ☹️ it really feels like they are relying on each other and watching out for one another a lot more. oh my hanki, i hope every conversation you share and every memories you build together only strengthens your bond and that you continue to have each other’s back 🥹💗

hani saying that the reason why his relationship with woongki recently got better is because they’ve been talking a lot and he thinks he’s relying on him a lot more ☹️ it really feels like they are relying on each other and watching out for one another a lot more. oh my hanki, i hope every conversation you share and every memories you build together only strengthens your bond and that you continue to have each other’s back 🥹💗

hana 🫧

17,235 views • 1 month ago

We've got a new audio-conditioned video model 👀 LTX Studio now lets you upload or generate audio, and then creates a lip-synced video. This is going to be HUGE for consistent character voices + AI influencers. I tested it w/ an animation of my pets. More on how to use it 👇

We've got a new audio-conditioned video model 👀 LTX Studio now lets you upload or generate audio, and then creates a lip-synced video. This is going to be HUGE for consistent character voices + AI influencers. I tested it w/ an animation of my pets. More on how to use it 👇

Justine Moore

18,562 views • 8 months ago

📈 Copilot in Word gives you more control to fine-tune your document. Easily edit text, lists, and tables like a pro. It's like an assistant making your job easier. Available on the web and desktop: #AI

📈 Copilot in Word gives you more control to fine-tune your document. Easily edit text, lists, and tables like a pro. It's like an assistant making your job easier. Available on the web and desktop: #AI

Microsoft 365

19,264 views • 2 years ago

Fine-tune DeepSeek-OCR on your own language! (100% local) DeepSeek-OCR is a 3B-parameter vision model that achieves 97% precision while using 10× fewer vision tokens than text-based LLMs. It handles tables, papers, and handwriting without killing your GPU or budget. Why it matters: Most vision models treat documents as massive sequences of tokens, making long-context processing expensive and slow. DeepSeek-OCR uses context optical compression to convert 2D layouts into vision tokens, enabling efficient processing of complex documents. The best part? You can easily fine-tune it for your specific use case on a single GPU. I used Unsloth to run this experiment on Persian text and saw an 88.26% improvement in character error rate. ↳ Base model: 149% character error rate (CER) ↳ Fine-tuned model: 60% CER (57% more accurate) ↳ Training time: 60 steps on a single GPU Persian was just the test case. You can swap in your own dataset for any language, document type, or specific domain you're working with. I've shared the complete guide in the next tweet - all the code, notebooks, and environment setup ready to run with a single click. Everything is 100% open-source!

Fine-tune DeepSeek-OCR on your own language! (100% local) DeepSeek-OCR is a 3B-parameter vision model that achieves 97% precision while using 10× fewer vision tokens than text-based LLMs. It handles tables, papers, and handwriting without killing your GPU or budget. Why it matters: Most vision models treat documents as massive sequences of tokens, making long-context processing expensive and slow. DeepSeek-OCR uses context optical compression to convert 2D layouts into vision tokens, enabling efficient processing of complex documents. The best part? You can easily fine-tune it for your specific use case on a single GPU. I used Unsloth to run this experiment on Persian text and saw an 88.26% improvement in character error rate. ↳ Base model: 149% character error rate (CER) ↳ Fine-tuned model: 60% CER (57% more accurate) ↳ Training time: 60 steps on a single GPU Persian was just the test case. You can swap in your own dataset for any language, document type, or specific domain you're working with. I've shared the complete guide in the next tweet - all the code, notebooks, and environment setup ready to run with a single click. Everything is 100% open-source!

Akshay 🚀

126,250 views • 10 months ago

I don't care about what you want. I care about what you repeat. Because your brain does not run on intention. It runs on repetition. Every thought you keep returning to, your brain treats as a signal. And the more you send that signal, the stronger and faster that neural pathway becomes. Here is the science behind it. When you repeatedly activate a neural pathway, your brain wraps a fatty substance called myelin around it. Think of it like insulation around an electrical wire. The more myelin, the faster the signal travels. The faster the signal travels, the more automatic that thought or behavior becomes. This is Hebb's Law. Neurons that fire together, wire together. And here is the part most people miss. Your brain does not care what you are reinforcing. It does not filter for good or bad. It just responds to what you keep repeating. Repeat confidence. Your brain builds it. Repeat self-doubt. Your brain builds that too. The same biological process that wires in focus, discipline, and certainty is the exact same one wiring in anxiety, fear, and limitation. You are not wired a certain way forever. You are wired for whatever you keep practicing. So stop asking what you want to change. Start asking what you are willing to repeat. ✨🙌🏾💫

I don't care about what you want. I care about what you repeat. Because your brain does not run on intention. It runs on repetition. Every thought you keep returning to, your brain treats as a signal. And the more you send that signal, the stronger and faster that neural pathway becomes. Here is the science behind it. When you repeatedly activate a neural pathway, your brain wraps a fatty substance called myelin around it. Think of it like insulation around an electrical wire. The more myelin, the faster the signal travels. The faster the signal travels, the more automatic that thought or behavior becomes. This is Hebb's Law. Neurons that fire together, wire together. And here is the part most people miss. Your brain does not care what you are reinforcing. It does not filter for good or bad. It just responds to what you keep repeating. Repeat confidence. Your brain builds it. Repeat self-doubt. Your brain builds that too. The same biological process that wires in focus, discipline, and certainty is the exact same one wiring in anxiety, fear, and limitation. You are not wired a certain way forever. You are wired for whatever you keep practicing. So stop asking what you want to change. Start asking what you are willing to repeat. ✨🙌🏾💫

🧬Maxpein🧬

54,705 views • 1 month ago

Most video tools can generate clips. Very few can maintain identity. That has been the real bottleneck in AI video creation. Kling O1 changes that. For the first time, creators can carry a character, style, and visual language across scenes without constant fixes. You can reference past clips, assets, or images and the output stays consistently on-model. No visual drift. No rework loops. No “this doesn’t look like the last shot” moments. It feels less like prompting a tool and more like working with a creative collaborator that remembers context. The impact is practical, not theoretical: → Faster production cycles → Lower iteration costs → Noticeably higher output quality This is what mature AI tooling looks like. Not louder features. Not bigger claims. Just reliability where it actually matters. Consistency is no longer the problem.

Most video tools can generate clips. Very few can maintain identity. That has been the real bottleneck in AI video creation. Kling O1 changes that. For the first time, creators can carry a character, style, and visual language across scenes without constant fixes. You can reference past clips, assets, or images and the output stays consistently on-model. No visual drift. No rework loops. No “this doesn’t look like the last shot” moments. It feels less like prompting a tool and more like working with a creative collaborator that remembers context. The impact is practical, not theoretical: → Faster production cycles → Lower iteration costs → Noticeably higher output quality This is what mature AI tooling looks like. Not louder features. Not bigger claims. Just reliability where it actually matters. Consistency is no longer the problem.

Darshal Jaitwar

141,038 views • 8 months ago

Seedance 2.5 gives you more to work with. Reference up to 50 multimodal inputs in a single generation. Keep your marketing content consistent from concept to final video. Skip the repeated generations and get everything right in one go. More inputs, more consistency, and a smoother path from idea to video. Create once. Get it right.

Seedance 2.5 gives you more to work with. Reference up to 50 multimodal inputs in a single generation. Keep your marketing content consistent from concept to final video. Skip the repeated generations and get everything right in one go. More inputs, more consistency, and a smoother path from idea to video. Create once. Get it right.

Pollo AI

270,715 views • 1 month ago

We’re making it more affordable to buy a home. We eliminated the GST for first-time home buyers across the country, saving Canadians up to $50,000 — so you can get the keys to a place of your own faster and take control of your future.

We’re making it more affordable to buy a home. We eliminated the GST for first-time home buyers across the country, saving Canadians up to $50,000 — so you can get the keys to a place of your own faster and take control of your future.

Mark Carney

97,419 views • 1 month ago

Player stats UI animation with GPT Image 2 and MiniMax H3. This model is amazing for UI animations. Give GPT Image 2 your character image and ask it to create a stats UI. Then use that UI as a reference for MiniMax H3. You can check the prompt in the replies.

Player stats UI animation with GPT Image 2 and MiniMax H3. This model is amazing for UI animations. Give GPT Image 2 your character image and ask it to create a stats UI. Then use that UI as a reference for MiniMax H3. You can check the prompt in the replies.

Kōda

42,502 views • 1 month ago

Driven by a UK Government push to open up transport data and boost public transport use nationwide, Google Maps has officially integrated live public transport tracking. By mandating that operators share their live GPS data, tech apps can now let you literally watch your specific bus moving along the map in real-time. As seen in the screenshot above, you can tap on your route (like the 207 towards White City) and see exactly where the bus is on the road, how many minutes away it is, and when the data was last updated. No more relying on broken countdown boards. No more running for a “ghost bus” that never actually shows up. No more standing in the rain guessing if you have time to grab a coffee. Have you noticed this government-backed feature on your phone yet? And more importantly... which West London bus route is the most unreliable and needs this the most? Let us know below #UB1UB2 #London #Southall #Hayes #Ealing

Driven by a UK Government push to open up transport data and boost public transport use nationwide, Google Maps has officially integrated live public transport tracking. By mandating that operators share their live GPS data, tech apps can now let you literally watch your specific bus moving along the map in real-time. As seen in the screenshot above, you can tap on your route (like the 207 towards White City) and see exactly where the bus is on the road, how many minutes away it is, and when the data was last updated. No more relying on broken countdown boards. No more running for a “ghost bus” that never actually shows up. No more standing in the rain guessing if you have time to grab a coffee. Have you noticed this government-backed feature on your phone yet? And more importantly... which West London bus route is the most unreliable and needs this the most? Let us know below #UB1UB2 #London #Southall #Hayes #Ealing

UB1UB2 West London (Southall)

21,165 views • 5 months ago

I handed a dance video over to AI... Try this exact workflow yourself: I used PixVerse Depth Map Control to seamlessly map the original choreography onto a completely fresh character. The visual outcome is incredibly fascinating 👀 Instead of generating a scene from absolute zero, this specific setup helps you lock down crucial details from your base clip: • movement • body position • spatial structure Your source footage dictates the precise action, while a single reference picture establishes the new aesthetic. It is a brilliant way to level up your AI video experiments — granting you far more precision over how your animations move and shift.

I handed a dance video over to AI... Try this exact workflow yourself: I used PixVerse Depth Map Control to seamlessly map the original choreography onto a completely fresh character. The visual outcome is incredibly fascinating 👀 Instead of generating a scene from absolute zero, this specific setup helps you lock down crucial details from your base clip: • movement • body position • spatial structure Your source footage dictates the precise action, while a single reference picture establishes the new aesthetic. It is a brilliant way to level up your AI video experiments — granting you far more precision over how your animations move and shift.

LX™

59,128 views • 1 month ago

MiniMax H3 is now on Magnific and honestly, there’s a lot you can do with it. You can mix text, images, videos and audio in a single prompt up to 9 images, 3 videos and 3 audio references. Start creating now: It can generate up to 15s of 2K video with synced sound, including voice, music and effects. And you can go beyond generation too: edit clips, remove objects, transfer motion, and control the camera, character and voice. But the multi-reference workflow is probably my favorite. Give it your product, character, environment and motion references, and H3 pulls everything together. It feels like a much easier way to go from an idea to an actual finished video.

MiniMax H3 is now on Magnific and honestly, there’s a lot you can do with it. You can mix text, images, videos and audio in a single prompt up to 9 images, 3 videos and 3 audio references. Start creating now: It can generate up to 15s of 2K video with synced sound, including voice, music and effects. And you can go beyond generation too: edit clips, remove objects, transfer motion, and control the camera, character and voice. But the multi-reference workflow is probably my favorite. Give it your product, character, environment and motion references, and H3 pulls everything together. It feels like a much easier way to go from an idea to an actual finished video.

Kalsoom (ghotai )

47,888 views • 1 month ago

Introducing RL Environment Creator Skill Now any one can create RL environments $ npx skills add adithya-s-k/RL_Envs_101 > You can create environments across multiple frameworks like OpenEnv, OpenReward, Verifiers, NemoGym ... > the repo has live working examples of environments that your coding agent can reference > The skill is design to first understand what type of model you are training and create an environment while keeping that in mind ps. There’s a lot more to building RL environments that can be used for training. One major aspect is the data, which this skill can’t directly solve. However, the skill will help with implementing tools, rewards, and other components of an RL environment, making it easier to go from idea to implementation quickly across different frameworks. Let me know if you’d be interested in a detailed, end-to-end blog/tutorial on building an environment and actually training a model for a useful use case.

Introducing RL Environment Creator Skill Now any one can create RL environments $ npx skills add adithya-s-k/RL_Envs_101 > You can create environments across multiple frameworks like OpenEnv, OpenReward, Verifiers, NemoGym ... > the repo has live working examples of environments that your coding agent can reference > The skill is design to first understand what type of model you are training and create an environment while keeping that in mind ps. There’s a lot more to building RL environments that can be used for training. One major aspect is the data, which this skill can’t directly solve. However, the skill will help with implementing tools, rewards, and other components of an RL environment, making it easier to go from idea to implementation quickly across different frameworks. Let me know if you’d be interested in a detailed, end-to-end blog/tutorial on building an environment and actually training a model for a useful use case.

Adithya S K

47,002 views • 4 months ago

NVIDIA open-sourced a 600M model that transcribes 40 languages in real-time at 80ms latency and it costs $0. that's faster than you can blink. across mandarin, arabic, hindi, portuguese, tagalog, whatever,from a SINGLE checkpoint. → 17x more concurrent streams than buffered ASR on the same H100. → punctuation + capitalization built-in. no post-processing. → runs on your own GPU. no API bill 100% Open Source.

NVIDIA open-sourced a 600M model that transcribes 40 languages in real-time at 80ms latency and it costs $0. that's faster than you can blink. across mandarin, arabic, hindi, portuguese, tagalog, whatever,from a SINGLE checkpoint. → 17x more concurrent streams than buffered ASR on the same H100. → punctuation + capitalization built-in. no post-processing. → runs on your own GPU. no API bill 100% Open Source.

Superman

104,663 views • 2 months ago

🧑‍🚀 Day 4 of the Cursor #vibejam Proudly sponsored by Cursor + bolt.new + GLIF So the new sponsor is GLIF: Glif is like Claude Code for AI videos and content generation: you can build launch videos for your game, explore asset styles with 100+ AI models/tools and train it on your favorite workflows via skills! Use it to make trailers, game assets, promo videos and more for your Vibe Jam submission! Tomorrow fabian from Glif will share more to help you create promotion materials for your games! Because it'd be cool if after the Vibe Jam your games will take off and become actual games Again browsing the #vibejam tag on X today and there's so many people building cool, cute and fun games so it was hard, but I picked my favorite 4 ones from today: - A literal 🪰 "fly" simulator, not flight simulator 😂 by Gabriel - What looks like a multiplayer Roman combat simulator by Tim Trussner - LeBeau Motel (another?) Habbo Hotel remix by Vincent - Roomba Wars by Thijs which is descriptive enough to not need an explanation 😁 Reply in this thread with updates on your current games to share your progress! Do you want to participate? You can still start now and submit your game any time before May 1! There's $35,000 in prizes you can win, see threads below for more info!

🧑‍🚀 Day 4 of the Cursor #vibejam Proudly sponsored by Cursor + bolt.new + GLIF So the new sponsor is GLIF: Glif is like Claude Code for AI videos and content generation: you can build launch videos for your game, explore asset styles with 100+ AI models/tools and train it on your favorite workflows via skills! Use it to make trailers, game assets, promo videos and more for your Vibe Jam submission! Tomorrow fabian from Glif will share more to help you create promotion materials for your games! Because it'd be cool if after the Vibe Jam your games will take off and become actual games Again browsing the #vibejam tag on X today and there's so many people building cool, cute and fun games so it was hard, but I picked my favorite 4 ones from today: - A literal 🪰 "fly" simulator, not flight simulator 😂 by Gabriel - What looks like a multiplayer Roman combat simulator by Tim Trussner - LeBeau Motel (another?) Habbo Hotel remix by Vincent - Roomba Wars by Thijs which is descriptive enough to not need an explanation 😁 Reply in this thread with updates on your current games to share your progress! Do you want to participate? You can still start now and submit your game any time before May 1! There's $35,000 in prizes you can win, see threads below for more info!

@levelsio

126,975 views • 5 months ago