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.

fal's Gorkem Yurtseven on the Blender, Astra, and H3 Max workflow professionals are using to get exactly the shot they wanted: "Using Blender with one of these AI models together is an extremely popular workflow for professional work." "You render a low resolution of your scene, what you want... to do, using Blender, previous non-AI technology. And once you add that video as a reference to an AI model, you basically get close to 100% controllability." "This is an incredibly popular workflow for VFX artists, people who are doing this professionally, because they want to get exactly what they put into the model." "A week after we launched H3 Max, people started generating these beautiful scenes using an LLM, Astra, in Blender, and all of a sudden it unlocked a whole new pipeline. Using an LLM to create a Blender scene and then passing that to the H3 Max model." "It works very well with H3 Max because it's extremely fast and you can try many things all at once in parallel." Gorkem Yurtseven batuhan the fal guy fal Jennifer Lishow more

a16z

1,077,425 subscribers

34,883 views • 7 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

14 Comments

Arnold6 days ago

This is a better picture of professional AI use than prompt-and-pray. Conventional tools provide structure; the model supplies speed and variation.

QueenBEE🐝7 days ago

Practical workflow, not hype—exactly why @Nainahf and I keep coming back for your insights.

GrowthwithHonoris7 days ago

The real edge here is control..AI becomes much more useful when you already know what you want to create.

TriDung.sol7 days ago

The control aspect is the real game changer here, makes AI feel like a tool

Shuohao Liao7 days ago

The Blender scene belongs in the handoff too. If the client later wants a different camera path, an editable scene gives them a starting point for another render. The finished clip alone loses that control.

Nilesh Maurya7 days ago

This hybrid workflow is the durable pattern: keep deterministic tools for composition and use models for high-variance exploration. It preserves control while expanding the search space—an important distinction for professional adoption versus novelty demos.

Nam Đầu Tư7 days ago

Render bản nháp trong Blender rồi dùng AI xử lý giúp VFX kiểm soát chính xác từng khung hình.

Carol Rehor6 days ago

Blender + Astra + H3 Max as the pro shot pipeline is the unsexy workflow post that actually matters. Exact control beats another demo reel.

Deep7 days ago

blocking the camera move in blender first is the trick. AI models still guess way too much on their own.

theophine Elussa Ravololonirina7 days ago

I stopped rushing every step, and things came together. I'm enjoying a much softer landing tonight.

icefrog.◎6 days ago

Blender to AI pipeline is the real superpower right now

Minh Tài Chính7 days ago

close to 100% controllability" là phóng đại. AI vẫn sinh ra chi tiết không mong muốn, và nghệ sĩ chuyên nghiệp vẫn phải chỉnh sửa nhiều lần.

Derek Byrne6 days ago

Great to see open source progress

Sophie d6 days ago

Low-res AI upscaling hides more than it fixes, so pros still rebuild detail by hand. Where do you draw the line between speed and final quality?

Related Videos

fal's Gorkem Yurtseven and Batuhan Taskaya on how faster-than-real-time generation unlocked continuous, interactive AI video: "One of our engineers, Rehan, started streaming a live stream of continuous generations of H3 Max from his laptop. He was doing some prompt tricks, trying to keep a coherent story, and then he started livestreaming that on Twitch." "Our ML team was essentially trying to take every single video model and apply these optimizations and tricks... You never could generate five seconds under five seconds. Once H3 Max unlocked it, the ML team was like, 'This is insane.'" "You can essentially stream infinitely. We capped it at an hour... I think it's the only model that can generate up to 60 minutes of continuous video that is action-controlled." "You can start with a prompt, say there's an office setting and someone is working, and then 30 seconds later it just imagines by itself. 30 seconds later, you can say, 'A woman walks in through the door.' It can take the prompt and reflect it immediately, which is the most fun part." "And the office is still the same office. The camera can pan back to the original person, and the original person is still there in the same state." Gorkem Yurtseven batuhan the fal guy fal

fal's Gorkem Yurtseven and Batuhan Taskaya on how faster-than-real-time generation unlocked continuous, interactive AI video: "One of our engineers, Rehan, started streaming a live stream of continuous generations of H3 Max from his laptop. He was doing some prompt tricks, trying to keep a coherent story, and then he started livestreaming that on Twitch." "Our ML team was essentially trying to take every single video model and apply these optimizations and tricks... You never could generate five seconds under five seconds. Once H3 Max unlocked it, the ML team was like, 'This is insane.'" "You can essentially stream infinitely. We capped it at an hour... I think it's the only model that can generate up to 60 minutes of continuous video that is action-controlled." "You can start with a prompt, say there's an office setting and someone is working, and then 30 seconds later it just imagines by itself. 30 seconds later, you can say, 'A woman walks in through the door.' It can take the prompt and reflect it immediately, which is the most fun part." "And the office is still the same office. The camera can pan back to the original person, and the original person is still there in the same state." Gorkem Yurtseven batuhan the fal guy fal

a16z

36,202 views • 7 days ago

.fal's Gorkem Yurtseven and Batuhan Taskaya on making an open source video model 35x faster, and what Hollywood wanted after they built it: Last month, MiniMax released H3, an open source video model. fal rebuilt it - they cut down the steps the model takes to make a video, rewrote the code under each stage, and got the GPUs to 70-80% of their theoretical ceiling instead of their usual 30-40%. No quality loss. Video now generates faster than you can film it. The models have gotten so cheap and fast that end users aren't even asking for improvements in either category anymore. The gap has moved to quality, or how closely the model follows the prompt. Hollywood wasn't a customer a year ago and is now fal's fastest growing segment. Studios love it for the little things - extending a shot, moving the camera, changing the lighting. Those edits land 80-90% of the time. fal is chasing 99.9%. In this conversation with a16z's Jennifer Li: 00:00 Intro 01:45 The first open model worth rebuilding 03:45 The industry ran out of compute in April 06:25 35x faster without losing quality 11:05 5s of video generated in 1.5s 14:25 The weekend fal dropped everything 16:15 3 viral projects nobody planned 18:20 Teaching a video model to remember 20:25 An hour of video that's consistent 23:30 2x the usage of other models in 3 weeks 26:35 The case for giving video away for free 29:00 Blender sketch in, finished shot out 30:40 Chasing 99.9% reliability 34:15 Hollywood, fal's fastest-growing customer 36:50 Why studios wouldn't touch it until now YouTube: Gorkem Yurtseven batuhan the fal guy fal Jennifer Li

.fal's Gorkem Yurtseven and Batuhan Taskaya on making an open source video model 35x faster, and what Hollywood wanted after they built it: Last month, MiniMax released H3, an open source video model. fal rebuilt it - they cut down the steps the model takes to make a video, rewrote the code under each stage, and got the GPUs to 70-80% of their theoretical ceiling instead of their usual 30-40%. No quality loss. Video now generates faster than you can film it. The models have gotten so cheap and fast that end users aren't even asking for improvements in either category anymore. The gap has moved to quality, or how closely the model follows the prompt. Hollywood wasn't a customer a year ago and is now fal's fastest growing segment. Studios love it for the little things - extending a shot, moving the camera, changing the lighting. Those edits land 80-90% of the time. fal is chasing 99.9%. In this conversation with a16z's Jennifer Li: 00:00 Intro 01:45 The first open model worth rebuilding 03:45 The industry ran out of compute in April 06:25 35x faster without losing quality 11:05 5s of video generated in 1.5s 14:25 The weekend fal dropped everything 16:15 3 viral projects nobody planned 18:20 Teaching a video model to remember 20:25 An hour of video that's consistent 23:30 2x the usage of other models in 3 weeks 26:35 The case for giving video away for free 29:00 Blender sketch in, finished shot out 30:40 Chasing 99.9% reliability 34:15 Hollywood, fal's fastest-growing customer 36:50 Why studios wouldn't touch it until now YouTube: Gorkem Yurtseven batuhan the fal guy fal Jennifer Li

a16z

133,755 views • 7 days ago

🚨 STOP learning Blender !! Learning Blender in 2026..... Is officially obsolete. MiniMax Design can now automate Blender to create ANY 3d SCENE !! I just gave it a PROMPT.... And MiniMax Design used GPT-6 Astra to handle everything like: 1️⃣ Opening Blender 2️⃣ Generating the 3D elements 3️⃣ Fixing lighting 4️⃣ Camera Tracking Data etc.... It built the entire scene inside Blender. Finally, I used MiniMax H3 Max to add colors to the 3d SCENE !! Then I just rendered the 3d scene !! Best part? Using GPT-6 Astra through MiniMax Design is way more affordable than running it directly.

🚨 STOP learning Blender !! Learning Blender in 2026..... Is officially obsolete. MiniMax Design can now automate Blender to create ANY 3d SCENE !! I just gave it a PROMPT.... And MiniMax Design used GPT-6 Astra to handle everything like: 1️⃣ Opening Blender 2️⃣ Generating the 3D elements 3️⃣ Fixing lighting 4️⃣ Camera Tracking Data etc.... It built the entire scene inside Blender. Finally, I used MiniMax H3 Max to add colors to the 3d SCENE !! Then I just rendered the 3d scene !! Best part? Using GPT-6 Astra through MiniMax Design is way more affordable than running it directly.

Darshal Jaitwar

86,087 views • 10 days ago

I used to think 3D was way too much work for a quick creative idea Then I tried this workflow in MiniMax Design GPT-6 Astra can work with Blender to build the 3D scene from a natural-language prompt, which honestly changes how I think about 3D creation I don’t need to start by figuring out every Blender operation myself I can just describe the scene I have in mind and let Astra handle the technical side Then I can take that 3D result straight into H3 Max Turbo and turn it into a video And the speed here is no joke 15s video → 20s generation Starting at $0.018/s That makes experimenting with different ideas feel so much less expensive in terms of time But the more I use MiniMax Design, the more I realize 3D is only one part of it GPT Image 2.5 opens up another route — generate the visuals and storyboards first, then use H3 Max Turbo to bring those shots together into a video So now I’m basically playing with two different creative paths: Astra + Blender → 3D → H3 Max Turbo GPT Image 2.5 → Storyboard → H3 Max Turbo And having all of these connected inside MiniMax Design makes the whole process feel much more flexible Honestly, I started this just wanting to see what Astra could do with 3D Now I’m way more curious about what happens when I start mixing all these workflows together

I used to think 3D was way too much work for a quick creative idea Then I tried this workflow in MiniMax Design GPT-6 Astra can work with Blender to build the 3D scene from a natural-language prompt, which honestly changes how I think about 3D creation I don’t need to start by figuring out every Blender operation myself I can just describe the scene I have in mind and let Astra handle the technical side Then I can take that 3D result straight into H3 Max Turbo and turn it into a video And the speed here is no joke 15s video → 20s generation Starting at $0.018/s That makes experimenting with different ideas feel so much less expensive in terms of time But the more I use MiniMax Design, the more I realize 3D is only one part of it GPT Image 2.5 opens up another route — generate the visuals and storyboards first, then use H3 Max Turbo to bring those shots together into a video So now I’m basically playing with two different creative paths: Astra + Blender → 3D → H3 Max Turbo GPT Image 2.5 → Storyboard → H3 Max Turbo And having all of these connected inside MiniMax Design makes the whole process feel much more flexible Honestly, I started this just wanting to see what Astra could do with 3D Now I’m way more curious about what happens when I start mixing all these workflows together

haytam

83,103 views • 13 days ago

I might’ve found a way to make yesterday’s Blender to Real video ~5,000x faster (and better imo) lol. I put the scene together with GPT-6 Astra and PATINA in about 30 minutes. But it had around 7 million polygons, so rendering took a while. I split it into chunks across 8 GPUs and rendered it in about 30min. My estimate for an M4 Pro was around 40 hours. Obviously, I could’ve optimized the settings, but that’s for the version I posted yesterday. Since then, I’ve been trying different prompts to get H3 Max to follow the Blender animation while making the buildings and materials actually look real. I think I finally got it. The 30s video took about 30s to generate with H3 Max. Compared to that estimated 41h render, that’s roughly 5000x faster :) The part I’m most excited about is how much control this gives me. GPT-6 Astra can build a detailed 3D prototype in minutes, and I can use Blender to set up the camera and movement however I want, then have H3 Max follow it.

I might’ve found a way to make yesterday’s Blender to Real video ~5,000x faster (and better imo) lol. I put the scene together with GPT-6 Astra and PATINA in about 30 minutes. But it had around 7 million polygons, so rendering took a while. I split it into chunks across 8 GPUs and rendered it in about 30min. My estimate for an M4 Pro was around 40 hours. Obviously, I could’ve optimized the settings, but that’s for the version I posted yesterday. Since then, I’ve been trying different prompts to get H3 Max to follow the Blender animation while making the buildings and materials actually look real. I think I finally got it. The 30s video took about 30s to generate with H3 Max. Compared to that estimated 41h render, that’s roughly 5000x faster :) The part I’m most excited about is how much control this gives me. GPT-6 Astra can build a detailed 3D prototype in minutes, and I can use Blender to set up the camera and movement however I want, then have H3 Max follow it.

ilker

57,631 views • 18 days ago

ok promising (but rough) start on an interactive video project using fal's H3 Max (and now Max Turbo) basically it's a first person POV 'date simulator' but the woman across from you is a secret agent using Blendi's basic interactive frame work (and a lot of other additional fable 5.1 work) each run is unique, depending on your choices throughout the dinner lots of issues with physics and drift but... there's def some sort of new medium here. and it's kind of magic to see the video just keep going in real time. trying to get calls as tight as possible (calls claude for story, nanobanana for facial consistency, h3 max for three different clips so they're ready to go when you select your path) and you can see my timing and when things trigger in the bottom right of the screen shout out to Tina Sang and the fal team for dropping me a few extra credits to keep working on this

ok promising (but rough) start on an interactive video project using fal's H3 Max (and now Max Turbo) basically it's a first person POV 'date simulator' but the woman across from you is a secret agent using Blendi's basic interactive frame work (and a lot of other additional fable 5.1 work) each run is unique, depending on your choices throughout the dinner lots of issues with physics and drift but... there's def some sort of new medium here. and it's kind of magic to see the video just keep going in real time. trying to get calls as tight as possible (calls claude for story, nanobanana for facial consistency, h3 max for three different clips so they're ready to go when you select your path) and you can see my timing and when things trigger in the bottom right of the screen shout out to Tina Sang and the fal team for dropping me a few extra credits to keep working on this

Gavin Purcell

24,080 views • 22 days ago

Let me share a long-awaited behind-the-scenes video of how Simulon works. It all starts with setting up a scene. You set the location, lighting conditions and capture the light map with a few turns. After that, you can capture the environment mesh using the Lidar scanner. That's the moment the fun begins. You can bring in your #3D models with animations and capture a video of up to 50" using the #AR preview on screen. After that is done, you send the footage to the cloud and in a couple of minutes you get back an incredible #CGI shot. And this is just the beginning. Follow Gabriele Romagnoli to see how Simulon integrates with #Blender and in a full #VFX workflow. A special thanks to Divesh Naidoo for sharing early access and for building something 🤯

Let me share a long-awaited behind-the-scenes video of how Simulon works. It all starts with setting up a scene. You set the location, lighting conditions and capture the light map with a few turns. After that, you can capture the environment mesh using the Lidar scanner. That's the moment the fun begins. You can bring in your #3D models with animations and capture a video of up to 50" using the #AR preview on screen. After that is done, you send the footage to the cloud and in a couple of minutes you get back an incredible #CGI shot. And this is just the beginning. Follow Gabriele Romagnoli to see how Simulon integrates with #Blender and in a full #VFX workflow. A special thanks to Divesh Naidoo for sharing early access and for building something 🤯

Gabriele Romagnoli

142,757 views • 2 years ago

I still can't believe this works! Every filmmaker needs to try the hybrid AI filmmaking + Blender previs workflow for precise camera control. AI dialogue is still flat but I'm going to dive into solving that next. My workflow: 1. Generate a start frame in Midjourney 2. Block out the scene in Blender, animate the camera 3. Feed both to Seedance So much of cinematic storytelling is composition, timing, and giving the viewer a spatial understanding of the scene. You can solve all of that before you ever touch the video model.

I still can't believe this works! Every filmmaker needs to try the hybrid AI filmmaking + Blender previs workflow for precise camera control. AI dialogue is still flat but I'm going to dive into solving that next. My workflow: 1. Generate a start frame in Midjourney 2. Block out the scene in Blender, animate the camera 3. Feed both to Seedance So much of cinematic storytelling is composition, timing, and giving the viewer a spatial understanding of the scene. You can solve all of that before you ever touch the video model.

Reid Hannaford

17,468 views • 2 months ago

Seedance 2.0 is insane. Blender previs is having a moment in AI filmmaking for a reason. I wanted to see how far I could push the workflow beyond a simple camera move in an ambush scene. The workflow: 1. Make a start image in Midjourney 2. Block it out in Blender, animate the camera 3. Feed both to Seedance The more I test this pipeline, the more convinced I am that hybrid pipelines are the future. The conversation is moving fast but previs is one of the clearest unlocks so far. Seedance still isn't perfect at matching the reference but it's close. You can experiment with staging, timing, and camera movement before you ever touch the video model. Solve the scene before you generate the shot.

Seedance 2.0 is insane. Blender previs is having a moment in AI filmmaking for a reason. I wanted to see how far I could push the workflow beyond a simple camera move in an ambush scene. The workflow: 1. Make a start image in Midjourney 2. Block it out in Blender, animate the camera 3. Feed both to Seedance The more I test this pipeline, the more convinced I am that hybrid pipelines are the future. The conversation is moving fast but previs is one of the clearest unlocks so far. Seedance still isn't perfect at matching the reference but it's close. You can experiment with staging, timing, and camera movement before you ever touch the video model. Solve the scene before you generate the shot.

Reid Hannaford

226,893 views • 2 months ago

fal's Gorkem Yurtseven says Hollywood went from almost no AI usage to their fastest-growing segment in one year: "There's a lot of noise about how AI might disrupt Hollywood, but Hollywood usage was nonexistent a year ago. In the past year, it grew, and now it's the fastest-growing segment." "Amazon MGM Studios, at their conference, released their Project Nara tool. It's mostly backed by fal infrastructure behind the scenes. We are seeing incredible pull coming from Hollywood." "What they need are these small point solutions rather than generating everything from scratch. They want to be able to extend the video a little bit. They want to be able to change the camera controls. They want to change the lighting. Someone has to build these solutions for them." "What Hollywood needs, what creators actually need, and what the research labs are working on, there's a little bit of a disconnect there. We believe we can come in and do these little post-training projects to close that gap." Gorkem Yurtseven fal

fal's Gorkem Yurtseven says Hollywood went from almost no AI usage to their fastest-growing segment in one year: "There's a lot of noise about how AI might disrupt Hollywood, but Hollywood usage was nonexistent a year ago. In the past year, it grew, and now it's the fastest-growing segment." "Amazon MGM Studios, at their conference, released their Project Nara tool. It's mostly backed by fal infrastructure behind the scenes. We are seeing incredible pull coming from Hollywood." "What they need are these small point solutions rather than generating everything from scratch. They want to be able to extend the video a little bit. They want to be able to change the camera controls. They want to change the lighting. Someone has to build these solutions for them." "What Hollywood needs, what creators actually need, and what the research labs are working on, there's a little bit of a disconnect there. We believe we can come in and do these little post-training projects to close that gap." Gorkem Yurtseven fal

a16z

34,340 views • 7 days ago

▪️Using an open-source model = 20 years in jail. ▪️All known AI researchers = under Government surveillance. Another PauseAI volunteer, Max Winga, who's also a research engineer at Conjecture, presents more "creative" ideas on how to save us all from the AI apocalypse. Trump and Xi need to mutually decide to "stop AI progress" and then: 1. "Using any open-source model is a huge crime - downloading it, having it in your possession on your hard drive, certainly running the model, distributing the model - make these significant crimes. Any of these things, 20 years in jail. Or even harsher penalties." 2. "You could stop all research. You could scrub the internet of the papers, and you can take all the people who were working on the models, and, at most draconian worse, 'we are saving the world, we will make some sacrifices,' you assign a spy or a government watch person to every single one of these people and ensure that they aren't designing AI models." "Ultimately, when the fate of all of humanity is at stake, these are extremely small sacrifices to make."

▪️Using an open-source model = 20 years in jail. ▪️All known AI researchers = under Government surveillance. Another PauseAI volunteer, Max Winga, who's also a research engineer at Conjecture, presents more "creative" ideas on how to save us all from the AI apocalypse. Trump and Xi need to mutually decide to "stop AI progress" and then: 1. "Using any open-source model is a huge crime - downloading it, having it in your possession on your hard drive, certainly running the model, distributing the model - make these significant crimes. Any of these things, 20 years in jail. Or even harsher penalties." 2. "You could stop all research. You could scrub the internet of the papers, and you can take all the people who were working on the models, and, at most draconian worse, 'we are saving the world, we will make some sacrifices,' you assign a spy or a government watch person to every single one of these people and ensure that they aren't designing AI models." "Ultimately, when the fate of all of humanity is at stake, these are extremely small sacrifices to make."

Nirit Weiss-Blatt, PhD

139,346 views • 1 year ago

MiniMax H3 is the SOTA open weight model... but the large model comes with slow gens (depending on your hardware). You can be waiting for minutes just for the generation to miss the mark Here's a ComfyUI workflow to get the most out of H3 without the wait. → H3 Turbo LoRA (4–8 steps) → Model Preview Override + Tiny AutoEncoder H3 for a fast composition preview → Bad preview? stop it, tweak the prompt or seed → Save your precious gpu time Workflow and model links below 👇

MiniMax H3 is the SOTA open weight model... but the large model comes with slow gens (depending on your hardware). You can be waiting for minutes just for the generation to miss the mark Here's a ComfyUI workflow to get the most out of H3 without the wait. → H3 Turbo LoRA (4–8 steps) → Model Preview Override + Tiny AutoEncoder H3 for a fast composition preview → Bad preview? stop it, tweak the prompt or seed → Save your precious gpu time Workflow and model links below 👇

rob - comfyui

26,990 views • 1 month ago

How can you solve complex tasks using a Large Language Model? Here is a 2-minute introduction to everything you need to know to 10x the quality of your results. Let's talk about three techniques, in order of complexity, starting with the easiest one: • In-Context Learning • Indexing + In-Context Learning • Fine-tuning In-Context Learning The team that trained GPT-3 found something they couldn't explain: You can condition a model using examples of how you want it to behave. I included an example prompt in the attached video. You can "teach" the model how you want it to interpret questions, select the correct answers, and format the results by giving a few examples. You can also give specific knowledge to the model that will be helpful when formulating answers. We call this approach "grounding the model." There's another example in the video. Indexing + In-Context Learning Unfortunately, there is a limit to how much data you can include in a prompt. We call this the "context size." One version of GPT-4 supports a context of approximately 6,000 words, while the other supports 25,000 words. Although this sounds like a lot, many applications need more than that. Imagine you wrote a book and want to build an application to answer any questions about your story. What happens if your book is longer than the context? That's where Indexing comes in. Using a model, you can turn every book passage into an embedding. These are vectors, numbers that "encode" the passage's text. You can then store these embeddings in a particular database that supports fast retrieval of these vectors. You can then turn any question into an embedding and search the database for the list of passages that are similar to that query. Instead of using the entire book to ask the model, you can now use the relevant passages as in-context information, effectively working around the context size limitation. Fine-tuning Fine-tuning can give you an extra boost to get reliable outputs from your LLM. It is, however, the most complex approach on the list. There are different approaches to fine-tuning a model with your data. A popular technique is to process your data with your LLM and use the outputs to train a new classifier that solves your specific task. Notice that here you aren't modifying the LLM. Instead, you are chaining it with your trained classifier. Another approach is to modify the parameters of the LLM using your data. Think of this as "rewiring" the model in a way that solves your particular task. The results and costs will vary depending on how many layers you want to fine-tune from the original model. Many companies think that fine-tuning is the solution to their problems. In my experience, many will benefit from exploring the other two approaches. I love explaining Machine Learning and Artificial Intelligence ideas. If you enjoy in-depth content like this, follow me Santiago so you don't miss what comes next.

How can you solve complex tasks using a Large Language Model? Here is a 2-minute introduction to everything you need to know to 10x the quality of your results. Let's talk about three techniques, in order of complexity, starting with the easiest one: • In-Context Learning • Indexing + In-Context Learning • Fine-tuning In-Context Learning The team that trained GPT-3 found something they couldn't explain: You can condition a model using examples of how you want it to behave. I included an example prompt in the attached video. You can "teach" the model how you want it to interpret questions, select the correct answers, and format the results by giving a few examples. You can also give specific knowledge to the model that will be helpful when formulating answers. We call this approach "grounding the model." There's another example in the video. Indexing + In-Context Learning Unfortunately, there is a limit to how much data you can include in a prompt. We call this the "context size." One version of GPT-4 supports a context of approximately 6,000 words, while the other supports 25,000 words. Although this sounds like a lot, many applications need more than that. Imagine you wrote a book and want to build an application to answer any questions about your story. What happens if your book is longer than the context? That's where Indexing comes in. Using a model, you can turn every book passage into an embedding. These are vectors, numbers that "encode" the passage's text. You can then store these embeddings in a particular database that supports fast retrieval of these vectors. You can then turn any question into an embedding and search the database for the list of passages that are similar to that query. Instead of using the entire book to ask the model, you can now use the relevant passages as in-context information, effectively working around the context size limitation. Fine-tuning Fine-tuning can give you an extra boost to get reliable outputs from your LLM. It is, however, the most complex approach on the list. There are different approaches to fine-tuning a model with your data. A popular technique is to process your data with your LLM and use the outputs to train a new classifier that solves your specific task. Notice that here you aren't modifying the LLM. Instead, you are chaining it with your trained classifier. Another approach is to modify the parameters of the LLM using your data. Think of this as "rewiring" the model in a way that solves your particular task. The results and costs will vary depending on how many layers you want to fine-tune from the original model. Many companies think that fine-tuning is the solution to their problems. In my experience, many will benefit from exploring the other two approaches. I love explaining Machine Learning and Artificial Intelligence ideas. If you enjoy in-depth content like this, follow me Santiago so you don't miss what comes next.

Santiago

384,510 views • 3 years ago

Check out this free Blender add-on by our Environment Artist, Niels Couvreur. SoftViz Pro is a high-performance viewport overlay for Blender to bridge the feedback gap in the Proportional Editing workflow. It calculates and renders a per-vertex heatmap directly onto the geometry, providing feedback similar to what you get in 3ds Max and Maya! Check it out:

Check out this free Blender add-on by our Environment Artist, Niels Couvreur. SoftViz Pro is a high-performance viewport overlay for Blender to bridge the feedback gap in the Proportional Editing workflow. It calculates and renders a per-vertex heatmap directly onto the geometry, providing feedback similar to what you get in 3ds Max and Maya! Check it out:

Sierra Division

22,181 views • 5 months ago

You can now fine-tune Llama 3 without writing a single line of code! We are moving at breakneck speed. I recorded a video to show you how to fine-tune any open-source model in a few minutes. I'm using a GPT capable of taking a problem and turning it into a fine-tuned model that will solve it. You don't have to write any code. You only need to explain to a GPT what problem you want to solve and tell it you want to use Llama 3. For example, "fine-tune Llama 3" or "deploy zephyr." It feels magic. The system will recommend a dataset and fine-tune the model for you. I'm using Monster API, a platform that specializes in making fine-tuning and deploying open-source models easy and fast. Their stack is well-optimized to maximize fine-tuning efficiency using techniques like Q-Lora and vLLM. They are behind the GPT. Here is what you need to do: 1. Create an account at 2. Load the GPT with the link below This is as simple as it gets. When you are done, you can click a button to deploy the model and start using it. I have 10,000 free credits for anyone using the code "SANTIAGO" in the dashboard. You can use these credits to access, fine-tune, and deploy these open-source models. You can also keep up with their latest updates, and get free credits and special offers on their Discord server:

You can now fine-tune Llama 3 without writing a single line of code! We are moving at breakneck speed. I recorded a video to show you how to fine-tune any open-source model in a few minutes. I'm using a GPT capable of taking a problem and turning it into a fine-tuned model that will solve it. You don't have to write any code. You only need to explain to a GPT what problem you want to solve and tell it you want to use Llama 3. For example, "fine-tune Llama 3" or "deploy zephyr." It feels magic. The system will recommend a dataset and fine-tune the model for you. I'm using Monster API, a platform that specializes in making fine-tuning and deploying open-source models easy and fast. Their stack is well-optimized to maximize fine-tuning efficiency using techniques like Q-Lora and vLLM. They are behind the GPT. Here is what you need to do: 1. Create an account at 2. Load the GPT with the link below This is as simple as it gets. When you are done, you can click a button to deploy the model and start using it. I have 10,000 free credits for anyone using the code "SANTIAGO" in the dashboard. You can use these credits to access, fine-tune, and deploy these open-source models. You can also keep up with their latest updates, and get free credits and special offers on their Discord server:

Santiago

324,621 views • 2 years ago

Ok, this is absurd. You can choreograph a complex action scene in Blender with basic shapes, then let Seedance make it real. You need to try this AI filmmaking workflow: 1. Generate a start frame in Midjourney 2. Block out the action in Blender 3. Feed both to Seedance My Blender reference was just rough timing, camera shake, and spatial choreography, and Seedance tracked the speed, motion, and action way better than I expected. This is the difference between describing a shot and directing one.

Ok, this is absurd. You can choreograph a complex action scene in Blender with basic shapes, then let Seedance make it real. You need to try this AI filmmaking workflow: 1. Generate a start frame in Midjourney 2. Block out the action in Blender 3. Feed both to Seedance My Blender reference was just rough timing, camera shake, and spatial choreography, and Seedance tracked the speed, motion, and action way better than I expected. This is the difference between describing a shot and directing one.

Reid Hannaford

536,307 views • 3 months ago

h3 max multi-angle is insane because it's essentially a world model, and producing results like this in 3 seconds makes it amongst the fastest! i made this little app if you want to try this specific 'freeze-frame' type of effect, but the model can be used for any controllable camera motion in a 3D scene

h3 max multi-angle is insane because it's essentially a world model, and producing results like this in 3 seconds makes it amongst the fastest! i made this little app if you want to try this specific 'freeze-frame' type of effect, but the model can be used for any controllable camera motion in a 3D scene

Blendi

10,857 views • 14 days ago

This is probably one of the coolest things I've ever made in Blender! I set up a rig using some complicated Driver magic and it allows me to choose exactly what expression I want! It's so fun to play around with! #blender #b3d #LoisLane #bnpr

This is probably one of the coolest things I've ever made in Blender! I set up a rig using some complicated Driver magic and it allows me to choose exactly what expression I want! It's so fun to play around with! #blender #b3d #LoisLane #bnpr

Niall

72,919 views • 3 years ago

AI can now help you create beautiful animations. Here’s one of my recent tests. Workflow: - Generate images using Midjourney. - Use Sora or Flux Kontext to create additional camera angles. - Animate the images using Kling AI and/or Midjourney’s new video generator. - Generate music with Suno AI. - Put everything together using your favorite video editing tool. The potential is huge. This took less than an hour to complete from start to finish. Imagine what you could do with more time and a story to tell.

AI can now help you create beautiful animations. Here’s one of my recent tests. Workflow: - Generate images using Midjourney. - Use Sora or Flux Kontext to create additional camera angles. - Animate the images using Kling AI and/or Midjourney’s new video generator. - Generate music with Suno AI. - Put everything together using your favorite video editing tool. The potential is huge. This took less than an hour to complete from start to finish. Imagine what you could do with more time and a story to tell.

Hashem Al-Ghaili

29,424 views • 1 year ago