Загрузка видео...

Не удалось загрузить видео

На главную

MiniMax M3 just dropped — their first natively multimodal model. So I ran it through my form-filling test. (The model has to place each element at the right pixel position on a blank form image, not type into a field.) Verdict: it got everything on the paper. > Name,...

stevibe's profile picture

stevibe

22,939 subscribers

27,383 просмотров • 2 месяцев назад •via X (Twitter)

ИскусствоОбразованиеНаука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

MiniMax M3 might be the most underrated coding model right now. I gave it nothing but a screenshot of a chaotic 90s GeoCities-style fan page, no HTML source, just the image + the asset files, and told it to rebuild the whole thing as a sleek Apple-style 2026 site. One shot. Through OpenCode. The result is genuinely stunning. It kept the soul (the "stevibe's HyperHome" identity, the visitor counter, the guestbook, the webmaster portrait) and translated every section into clean modern design, gradient hero, proper typography, dark theme, the works.
0:19

MiniMax M3 might be the most underrated coding model right now. I gave it nothing but a screenshot of a chaotic 90s GeoCities-style fan page, no HTML source, just the image + the asset files, and told it to rebuild the whole thing as a sleek Apple-style 2026 site. One shot. Through OpenCode. The result is genuinely stunning. It kept the soul (the "stevibe's HyperHome" identity, the visitor counter, the guestbook, the webmaster portrait) and translated every section into clean modern design, gradient hero, proper typography, dark theme, the works.

stevibe

21,206 просмотров • 2 месяцев назад

Woow Google has just rolled out the AI model Flash Thinking 2.0 This is the first reasoning model capable of accessing YouTube and it changes everything: - Search for a video on your topic - Ask Gemini to think about the video - You'll have a tailor-made result in 10 sec. And it's even connected to Google Search and Maps!
0:19

Woow Google has just rolled out the AI model Flash Thinking 2.0 This is the first reasoning model capable of accessing YouTube and it changes everything: - Search for a video on your topic - Ask Gemini to think about the video - You'll have a tailor-made result in 10 sec. And it's even connected to Google Search and Maps!

Paul Couvert

79,488 просмотров • 1 год назад

✨ Grok's new Imagine video model also comes with an Edit model We know edit models for images, you submit an image, write a prompt what to change, but this is the first time I've seen a proper edit model for video And it kinda works, not great yet though but it does something Here I had to remove the old name "Nomad List" in the video for my site First it said "Go nomad -> Nomad List", so I prompted it "remove the text Nomad List. do not change anything else", it didn't remove it but it replaced it with just "Go nomad" again, okay good enough Useful because otherwise I'd have to scour my backups for the original video in Final Cut Pro, and this is faster One thing you see is it changes the pattern on the door also, but that's okay for now if I fade it in
0:17

✨ Grok's new Imagine video model also comes with an Edit model We know edit models for images, you submit an image, write a prompt what to change, but this is the first time I've seen a proper edit model for video And it kinda works, not great yet though but it does something Here I had to remove the old name "Nomad List" in the video for my site First it said "Go nomad -> Nomad List", so I prompted it "remove the text Nomad List. do not change anything else", it didn't remove it but it replaced it with just "Go nomad" again, okay good enough Useful because otherwise I'd have to scour my backups for the original video in Final Cut Pro, and this is faster One thing you see is it changes the pattern on the door also, but that's okay for now if I fade it in

@levelsio

73,183 просмотров • 6 месяцев назад

✨ Made a new mini feature on Photo AI: [ Grab from 3d model ] So the problem is we're at that stage in time (typical for AI) where image-to-3d models are not good enough but are fun to play with, but we know they'll be good enough in 1-2 years With [ Make 3d model ] you already can turn any Photo AI pic into a 3d model but it still looks hyper clunky and deformed, but it works! One cool idea I had to make that more useful and made now: Let people make a 3d model then change the view of the it with the 3d viewer, then press [ o ] and it grabs a frame of the 3d That image you can then [ Remix ] (img2img), and it becomes a real photo again and that in turn you can then turn into a video again with [ Make video ] So that essentially gives you a fully freeform camera position control to take photos with One thing I need to fix is the background/skybox, I kinda need to take the original photo and remove the person and just get the background for the 3d model viewer, in this case it should be white, but it's a start!
0:51

✨ Made a new mini feature on Photo AI: [ Grab from 3d model ] So the problem is we're at that stage in time (typical for AI) where image-to-3d models are not good enough but are fun to play with, but we know they'll be good enough in 1-2 years With [ Make 3d model ] you already can turn any Photo AI pic into a 3d model but it still looks hyper clunky and deformed, but it works! One cool idea I had to make that more useful and made now: Let people make a 3d model then change the view of the it with the 3d viewer, then press [ o ] and it grabs a frame of the 3d That image you can then [ Remix ] (img2img), and it becomes a real photo again and that in turn you can then turn into a video again with [ Make video ] So that essentially gives you a fully freeform camera position control to take photos with One thing I need to fix is the background/skybox, I kinda need to take the original photo and remove the person and just get the background for the 3d model viewer, in this case it should be white, but it's a start!

@levelsio

119,210 просмотров • 1 год назад

Don't train the model, evolve the harness. I read a brilliant blog post from Hugging Face where they took a frozen open model scoring 0% on a hard legal agent benchmark, left its weights alone, and let an automated loop rewrite only the code around it. That code layer is the harness, the runtime wrapper that feeds the model context, runs its tool calls, and decides when a run ends. By the time the loop finished, the system had essentially matched Sonnet 4.6 on the benchmark's headline metric, at roughly 7x lower cost per task. Zero weights changed. The gain existed because of where the model was failing. The judge only grades files saved in the right place under the exact requested filename, and the model kept doing the legal analysis correctly, then saving it under the wrong name, dropping it in a scratch folder, or never writing it at all. So the 0% was never measuring legal reasoning. It was measuring the harness. Hand-tuning that layer is slow and model-specific, so they automated it. A Claude proposer adds exactly one mechanism per iteration, and an outer loop keeps it only if it clearly beats the current best, so accepted mechanisms compound. What the loop discovered says a lot about where agents actually fail. → The biggest single gain was file handling, not intelligence. An automatic step that lands the deliverable exactly where the judge expects it beat every prompt change, with zero extra model tokens. → Code fixes transferred across models, prompt playbooks did not. The same harness lifted a smaller model from the same family by 14 points, but the tuned prompts hurt a different model family on tasks it could already finish. → The harness mattered more than anything else. Same model, same judge, same tasks, and five different harnesses scored anywhere between 3.5% and 80.1%. The gains do eventually flatten, and the remaining misses look like real capability gaps. At some point the wrapper runs out of tricks and the model has to carry the work. But the lesson holds. A benchmark score measures the model and its harness together, and until the harness is fixed, it's impossible to know which one failed. I highly recommend reading this: I also wrote a deep dive on agent harness engineering a while back, covering the orchestration loop, tools, memory, context management, and everything that turns a stateless LLM into a capable agent. The article is quoted below.
0:18

Don't train the model, evolve the harness. I read a brilliant blog post from Hugging Face where they took a frozen open model scoring 0% on a hard legal agent benchmark, left its weights alone, and let an automated loop rewrite only the code around it. That code layer is the harness, the runtime wrapper that feeds the model context, runs its tool calls, and decides when a run ends. By the time the loop finished, the system had essentially matched Sonnet 4.6 on the benchmark's headline metric, at roughly 7x lower cost per task. Zero weights changed. The gain existed because of where the model was failing. The judge only grades files saved in the right place under the exact requested filename, and the model kept doing the legal analysis correctly, then saving it under the wrong name, dropping it in a scratch folder, or never writing it at all. So the 0% was never measuring legal reasoning. It was measuring the harness. Hand-tuning that layer is slow and model-specific, so they automated it. A Claude proposer adds exactly one mechanism per iteration, and an outer loop keeps it only if it clearly beats the current best, so accepted mechanisms compound. What the loop discovered says a lot about where agents actually fail. → The biggest single gain was file handling, not intelligence. An automatic step that lands the deliverable exactly where the judge expects it beat every prompt change, with zero extra model tokens. → Code fixes transferred across models, prompt playbooks did not. The same harness lifted a smaller model from the same family by 14 points, but the tuned prompts hurt a different model family on tasks it could already finish. → The harness mattered more than anything else. Same model, same judge, same tasks, and five different harnesses scored anywhere between 3.5% and 80.1%. The gains do eventually flatten, and the remaining misses look like real capability gaps. At some point the wrapper runs out of tricks and the model has to carry the work. But the lesson holds. A benchmark score measures the model and its harness together, and until the harness is fixed, it's impossible to know which one failed. I highly recommend reading this: I also wrote a deep dive on agent harness engineering a while back, covering the orchestration loop, tools, memory, context management, and everything that turns a stateless LLM into a capable agent. The article is quoted below.

Akshay 🚀

244,567 просмотров • 1 месяц назад

Which local models can actually handle tool calling? I built a framework to find out. 15 scenarios. 12 tools. Mocked responses. Temperature 0. No cherry-picking. Tested every Qwen3.5 size from 0.8B to 397B, and since some of you asked after the distillation tests: yes, I included Jackrong's Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled too. Only two models went all green: the 27B dense and the distilled 27B. The 397B? Failed two tests. The 122B? Failed one. The 35B? Failed two. The timed-out results — mostly on the smaller models, are cases where the model got stuck in a loop, repeating the same tool call until it hit the 30-second limit. The test that exposed the most models: "Search for Iceland's population, then calculate 2% of it." Simple, but 35B, 122B, and 397B all used a rounded number from memory instead of the actual search result. They didn't trust their own tool output. Small models hallucinate data. Big models ignore data. The 27B just threaded it through.
0:11

Which local models can actually handle tool calling? I built a framework to find out. 15 scenarios. 12 tools. Mocked responses. Temperature 0. No cherry-picking. Tested every Qwen3.5 size from 0.8B to 397B, and since some of you asked after the distillation tests: yes, I included Jackrong's Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled too. Only two models went all green: the 27B dense and the distilled 27B. The 397B? Failed two tests. The 122B? Failed one. The 35B? Failed two. The timed-out results — mostly on the smaller models, are cases where the model got stuck in a loop, repeating the same tool call until it hit the 30-second limit. The test that exposed the most models: "Search for Iceland's population, then calculate 2% of it." Simple, but 35B, 122B, and 397B all used a rounded number from memory instead of the actual search result. They didn't trust their own tool output. Small models hallucinate data. Big models ignore data. The 27B just threaded it through.

stevibe

431,569 просмотров • 4 месяцев назад

THE DEPTH MAP TRICK THAT FIXED DANCE ACCURACY IN SEEDANCE 2.0 Feed the model a video of someone dancing and it tries to interpret everything- the person, the clothes, the lighting, the room, and somewhere in there, the movement. Feed it a depth map and there's nothing left to interpret but the motion. Most creators trying to transfer a dance to a character reference the source footage directly, then wonder why the choreography drifts. The problem isn't the model - it's that you handed it ten variables when you only wanted one. Here's the workflow 1. Lock the character reference in GPT Image 2 first -face, build, costume, so identity holds independently of whatever motion gets applied to it 2. Convert the source dance footage into a depth map instead of using the raw video -this strips out the original performer's appearance, clothing, and environment entirely 3. Feed the depth map as the motion reference and the character sheet as the identity reference- two separate inputs doing two separate jobs, not one input trying to do both 5. Let the depth map carry only spatial movement -the model receives body position and momentum with no competing information about who's moving or what they look like 6. Keep the character and motion inputs isolated throughout - the moment you mix appearance data into the motion reference, the model starts negotiating between two identities Why this works • Raw footage passes the model everything at once- performer, wardrobe, room, lighting -and the choreography competes with all of it for attention • A depth map is pure spatial information, so the only thing left to transfer is movement • Separating identity from motion means the character can stay locked while the dance stays accurate - normally you're trading one for the other • The accuracy gain isn't the model getting better, it's the model getting fewer decisions to make Use cases: ⁃ Dance and choreography transfer onto original characters ⁃ Motion capture-style workflows without motion capture ⁃ Any sequence where a specific movement needs to survive intact ⁃ Character showcase content built on existing performance footage The character sheet answers who's dancing. The depth map answers how - and keeping those two questions separate is the whole trick.
0:15

THE DEPTH MAP TRICK THAT FIXED DANCE ACCURACY IN SEEDANCE 2.0 Feed the model a video of someone dancing and it tries to interpret everything- the person, the clothes, the lighting, the room, and somewhere in there, the movement. Feed it a depth map and there's nothing left to interpret but the motion. Most creators trying to transfer a dance to a character reference the source footage directly, then wonder why the choreography drifts. The problem isn't the model - it's that you handed it ten variables when you only wanted one. Here's the workflow 1. Lock the character reference in GPT Image 2 first -face, build, costume, so identity holds independently of whatever motion gets applied to it 2. Convert the source dance footage into a depth map instead of using the raw video -this strips out the original performer's appearance, clothing, and environment entirely 3. Feed the depth map as the motion reference and the character sheet as the identity reference- two separate inputs doing two separate jobs, not one input trying to do both 5. Let the depth map carry only spatial movement -the model receives body position and momentum with no competing information about who's moving or what they look like 6. Keep the character and motion inputs isolated throughout - the moment you mix appearance data into the motion reference, the model starts negotiating between two identities Why this works • Raw footage passes the model everything at once- performer, wardrobe, room, lighting -and the choreography competes with all of it for attention • A depth map is pure spatial information, so the only thing left to transfer is movement • Separating identity from motion means the character can stay locked while the dance stays accurate - normally you're trading one for the other • The accuracy gain isn't the model getting better, it's the model getting fewer decisions to make Use cases: ⁃ Dance and choreography transfer onto original characters ⁃ Motion capture-style workflows without motion capture ⁃ Any sequence where a specific movement needs to survive intact ⁃ Character showcase content built on existing performance footage The character sheet answers who's dancing. The depth map answers how - and keeping those two questions separate is the whole trick.

Nexlow

84,925 просмотров • 25 дней назад

Claude Code's new dynamic workflow is the real deal. 🤖 Why it matters: It's not just a chain of prompts — it's an autonomous agent swarm. 1. Set model to Opus 4.8 + reasoning effort /ultracode 2. Claude detects complexity, writes orchestration script on the fly 3. Spawns a parallel fleet of coordinated subagents Operator takeaway: This is the first time I've seen an agent actually decompose and delegate autonomously without a rigid framework. Have you tried it yet? 🚀
0:13

Claude Code's new dynamic workflow is the real deal. 🤖 Why it matters: It's not just a chain of prompts — it's an autonomous agent swarm. 1. Set model to Opus 4.8 + reasoning effort /ultracode 2. Claude detects complexity, writes orchestration script on the fly 3. Spawns a parallel fleet of coordinated subagents Operator takeaway: This is the first time I've seen an agent actually decompose and delegate autonomously without a rigid framework. Have you tried it yet? 🚀

EK

197,752 просмотров • 2 месяцев назад

the thing you rent for $200 a month just became something you can own for $1,700 once but the money is not even the real story for the first time a 200 billion parameter model is not in a datacenter, it is sitting on a desk the cloud spent years convincing you a model this size needed their servers, their meter, their monthly bill people are stacking four subscriptions into a $440 a month bill to rent what one box this size now owns outright it needed a box the size of a book the moment the model moves from their datacenter to your desk, the whole game changes it stops being about who has the best AI it becomes about who ships it on every desk the cloud told you this needed a datacenter it needed a desk i did the full math on what this kills in the article below
0:15

the thing you rent for $200 a month just became something you can own for $1,700 once but the money is not even the real story for the first time a 200 billion parameter model is not in a datacenter, it is sitting on a desk the cloud spent years convincing you a model this size needed their servers, their meter, their monthly bill people are stacking four subscriptions into a $440 a month bill to rent what one box this size now owns outright it needed a box the size of a book the moment the model moves from their datacenter to your desk, the whole game changes it stops being about who has the best AI it becomes about who ships it on every desk the cloud told you this needed a datacenter it needed a desk i did the full math on what this kills in the article below

John Doe

25,981 просмотров • 1 месяц назад

"I'm not a human." Fed it to Qwen 3.5 0.8B running locally on my Mac Studio M2 Ultra. It solved it. The CAPTCHA is fake. But sending images to the local model? Very real. I'm not breaking the internet. Yet.
0:12

"I'm not a human." Fed it to Qwen 3.5 0.8B running locally on my Mac Studio M2 Ultra. It solved it. The CAPTCHA is fake. But sending images to the local model? Very real. I'm not breaking the internet. Yet.

stevibe

69,433 просмотров • 5 месяцев назад

Alhamdulilah. Now this is what we call a huge web3 did What a wonderful journey it has been. Almost done with my first house. And honestly, it doesn’t feel like just a structure being completed… it feels like a reflection of everything that came before it. time, discipline, mistakes, exposure all quietly compounding. › 2023 The Beginning It started with no real direction. I was grinding, exploring, trying things without fully understanding where it all leads. There was no structure yet… just curiosity, repetition, and a lot of learning through trial and error. I was simply moving, even when I didn’t fully know what I was moving toward. › 2024 Things Start to Form Then things began to shift. Not overnight but gradually, through exposure and experience. I entered deeper into the space and connected with OGs in the TON ecosystem And slowly, one important lesson became clear: it’s not just effort that matters… it’s information, timing, and the people you learn from. › So I also started trading as well Trading became a major part of my learning curve. Forex & Perps showed me risk in its raw form mehnn 🙂‍↔️ taught me discipline and patience. Memecoins show me shege rugs up and down Along the way, I learned from different people PMO, not just strategies, but perspectives. Each one added something I didn’t have before. › Late 2024 Structure Appears Then came a different phase. I signed my first structured deal with sign a monthly arrangement that brought a new level of stability into my journey. For the first time, things were not just random wins and losses… there was structure, expectation, and consistency. Then came the TGE. Execution was clean. The ecosystem moved properly. And as early participants, we experienced meaningful upside not just financially, but in understanding how systems actually work when they’re built well. › Now The Reflection Almost done with something physical. But the deeper truth is this: the house is just the surface. what actually got built was the person. through risk, through losses, through discipline, through time. This is not a story about outcomes. It is a story about becoming. And I am still becoming. Grateful for the journey so far. Still building.
0:11

Alhamdulilah. Now this is what we call a huge web3 did What a wonderful journey it has been. Almost done with my first house. And honestly, it doesn’t feel like just a structure being completed… it feels like a reflection of everything that came before it. time, discipline, mistakes, exposure all quietly compounding. › 2023 The Beginning It started with no real direction. I was grinding, exploring, trying things without fully understanding where it all leads. There was no structure yet… just curiosity, repetition, and a lot of learning through trial and error. I was simply moving, even when I didn’t fully know what I was moving toward. › 2024 Things Start to Form Then things began to shift. Not overnight but gradually, through exposure and experience. I entered deeper into the space and connected with OGs in the TON ecosystem And slowly, one important lesson became clear: it’s not just effort that matters… it’s information, timing, and the people you learn from. › So I also started trading as well Trading became a major part of my learning curve. Forex & Perps showed me risk in its raw form mehnn 🙂‍↔️ taught me discipline and patience. Memecoins show me shege rugs up and down Along the way, I learned from different people PMO, not just strategies, but perspectives. Each one added something I didn’t have before. › Late 2024 Structure Appears Then came a different phase. I signed my first structured deal with sign a monthly arrangement that brought a new level of stability into my journey. For the first time, things were not just random wins and losses… there was structure, expectation, and consistency. Then came the TGE. Execution was clean. The ecosystem moved properly. And as early participants, we experienced meaningful upside not just financially, but in understanding how systems actually work when they’re built well. › Now The Reflection Almost done with something physical. But the deeper truth is this: the house is just the surface. what actually got built was the person. through risk, through losses, through discipline, through time. This is not a story about outcomes. It is a story about becoming. And I am still becoming. Grateful for the journey so far. Still building.

Tajudeen ♟️

37,936 просмотров • 3 месяцев назад

Unpopular opinion: Most agent evals are theatre. You run them once before the deployment. It'll take 800ms+ as another LLM would be judging your LLM. Most annoying part - no one tells where in the chain things went wrong. I wasted a lot of time in this loop. And then I came across Future AGI bringing 5 different tools under one umbrella, best part - the platform is completely open source. They open sourced their entire platform and the eval layer is noticeably different. It is multimodal - works on everything text, image, audio, pdf. Not an LLM-as-judge adding latency but an agent with memory and tools. The biggest win are learned classifiers trained on actual production failure patterns to run evals at low cost. It also runs across the full reasoning chain, not just the final response. Check out → Try it here →
0:13

Unpopular opinion: Most agent evals are theatre. You run them once before the deployment. It'll take 800ms+ as another LLM would be judging your LLM. Most annoying part - no one tells where in the chain things went wrong. I wasted a lot of time in this loop. And then I came across Future AGI bringing 5 different tools under one umbrella, best part - the platform is completely open source. They open sourced their entire platform and the eval layer is noticeably different. It is multimodal - works on everything text, image, audio, pdf. Not an LLM-as-judge adding latency but an agent with memory and tools. The biggest win are learned classifiers trained on actual production failure patterns to run evals at low cost. It also runs across the full reasoning chain, not just the final response. Check out → Try it here →

Swapna Kumar Panda

50,102 просмотров • 3 месяцев назад

🚨Gemini 3.6 Flash is trash I tested it on a 3D Golden Gate Bridge, and the results were awful. • I had to re-prompt it three times because it repeatedly ignored the instructions. • First attempt, instead of creating the requested .html file, it first tried to build the experience inside the Gemini app using simulations. • Then second attempt it started placing images from the web into the chat rather than actually producing the file. • Even after getting it to complete the task, the final output was dramatically worse than Gemini 3.1 Pro, which is 5 months old and now not even a top 10 model on leaderboards. This feels like a regression from Gemini 3.5 Flash and honestly, it is one of the weakest models I have tested in the past few months. Has anyone else tested Gemini 3.6 Flash yet, and are you seeing the same thing?
0:15

🚨Gemini 3.6 Flash is trash I tested it on a 3D Golden Gate Bridge, and the results were awful. • I had to re-prompt it three times because it repeatedly ignored the instructions. • First attempt, instead of creating the requested .html file, it first tried to build the experience inside the Gemini app using simulations. • Then second attempt it started placing images from the web into the chat rather than actually producing the file. • Even after getting it to complete the task, the final output was dramatically worse than Gemini 3.1 Pro, which is 5 months old and now not even a top 10 model on leaderboards. This feels like a regression from Gemini 3.5 Flash and honestly, it is one of the weakest models I have tested in the past few months. Has anyone else tested Gemini 3.6 Flash yet, and are you seeing the same thing?

Lumina

72,213 просмотров • 20 дней назад

📖THE STEP MOST CREATORS SKIP IS WHY THEIR AI ANIMATION LOOKS INCONSISTENT Consistency across clips doesn't come from prompting — it comes from the reference image. The pipeline, step by step: ▪ Start with ChatGPT Image 2 — generate a full character design sheet first, not just a single frame. Multiple angles, expressions, and outfit variations in one image keeps the character consistent across every scene ▪ Build a storyboard inside ChatGPT Image 2 as well — define each shot, camera angle, action, and mood before touching Seedance at all. This is the step most people skip and it's the reason clips look disconnected ▪ Define a color palette and lighting mood early — golden afternoon light, soft warm tones, dramatic shadows. Lock those values and repeat them across every prompt ▪ Take each storyboard frame into Seedance 2.0 as the reference image — one frame becomes one clip ▪ Write the Seedance prompt around the character action, not the scene description. The scene is already in the image. The prompt handles motion, camera behavior, and timing ▪ Keep clip duration between 4-6 seconds per shot — shorter clips give more control over pacing and reduce motion drift on character faces ▪ Match camera movement type across consecutive clips — if one shot dollies in, the next should hold or pull back, not dolly again The consistency across these frames comes from the character design sheet, not from luck. Seedance reads the reference image and the prompt together — if the reference is detailed enough, the output stays on-model. This video was created by ALOKXMEHTA 📥 tomorrow: the exact ChatGPT Image 2 prompt structure used to generate a multi-angle character design sheet like this one 🔖One article covers the entire workflow — it is pinned below, do not scroll past it.
0:12

📖THE STEP MOST CREATORS SKIP IS WHY THEIR AI ANIMATION LOOKS INCONSISTENT Consistency across clips doesn't come from prompting — it comes from the reference image. The pipeline, step by step: ▪ Start with ChatGPT Image 2 — generate a full character design sheet first, not just a single frame. Multiple angles, expressions, and outfit variations in one image keeps the character consistent across every scene ▪ Build a storyboard inside ChatGPT Image 2 as well — define each shot, camera angle, action, and mood before touching Seedance at all. This is the step most people skip and it's the reason clips look disconnected ▪ Define a color palette and lighting mood early — golden afternoon light, soft warm tones, dramatic shadows. Lock those values and repeat them across every prompt ▪ Take each storyboard frame into Seedance 2.0 as the reference image — one frame becomes one clip ▪ Write the Seedance prompt around the character action, not the scene description. The scene is already in the image. The prompt handles motion, camera behavior, and timing ▪ Keep clip duration between 4-6 seconds per shot — shorter clips give more control over pacing and reduce motion drift on character faces ▪ Match camera movement type across consecutive clips — if one shot dollies in, the next should hold or pull back, not dolly again The consistency across these frames comes from the character design sheet, not from luck. Seedance reads the reference image and the prompt together — if the reference is detailed enough, the output stays on-model. This video was created by ALOKXMEHTA 📥 tomorrow: the exact ChatGPT Image 2 prompt structure used to generate a multi-angle character design sheet like this one 🔖One article covers the entire workflow — it is pinned below, do not scroll past it.

Zentrix⌚️

12,846 просмотров • 1 месяц назад

As always everyone is blind staring at the progress of LLMs for coding and chat But meanwhile the new SOTA video model Seedance 2.5 has been slowly rolling out and it's really quite exceptional It's made by ByteDance (TikTok) who of course have lots of training data With just a few reference pics, it can get quite close to how you look IRL and you can do quite professional video shots with just a prompt I'd say it's the first video model that's now at the level of image models with the level of character likeness, cracking that in image models also took about 3 years (2022-2025) Generating 15 seconds takes about 4 minutes I put it live now on Photo AI, you can use it under [ Make video ] from the sidebar with just a prompt and your model selected! So you don't need to take an AI photo first and then turn that into a video! Saves lots of time :D It's more expensive than but I kept the credits the same (30 for 1 video) It also works inside the new video editor and you can make changes in your video with [ Magic edit ] in both the main app and the video editor Also a message for my server guy Daniel Lockyer (it can do voice too and you can even submit a voice sample of yourself, but I didn't here)
0:15

As always everyone is blind staring at the progress of LLMs for coding and chat But meanwhile the new SOTA video model Seedance 2.5 has been slowly rolling out and it's really quite exceptional It's made by ByteDance (TikTok) who of course have lots of training data With just a few reference pics, it can get quite close to how you look IRL and you can do quite professional video shots with just a prompt I'd say it's the first video model that's now at the level of image models with the level of character likeness, cracking that in image models also took about 3 years (2022-2025) Generating 15 seconds takes about 4 minutes I put it live now on Photo AI, you can use it under [ Make video ] from the sidebar with just a prompt and your model selected! So you don't need to take an AI photo first and then turn that into a video! Saves lots of time :D It's more expensive than but I kept the credits the same (30 for 1 video) It also works inside the new video editor and you can make changes in your video with [ Magic edit ] in both the main app and the video editor Also a message for my server guy Daniel Lockyer (it can do voice too and you can even submit a voice sample of yourself, but I didn't here)

@levelsio

681,039 просмотров • 1 день назад

Tested Claude + Blender today with two real workflows. Sharing what actually happened. First one was a simple demo. Gave it one sentence to build a cyberpunk room. Geometry, lighting, camera, render. It got there, though not everything in the prompt landed perfectly. Good enough to show the concept, not a stress test. Second one was more interesting. Threw a raw photogrammetry scan at it. Massey Ferguson tractor, 250k faces, grass background everywhere, debris floating all over the place. Asked Claude to clean it up autonomously. It did the work. Removed 106 floating chunks, cut face count by 87%, stripped the grass, flipped the model upright, set up studio lighting and rendered. Technically it worked. But honest answer: the result wasn't clean enough for production. This kind of cleanup still needs the right tools and someone who knows what they're doing. So here's where it actually fits. Not the precise technical stuff. The setup work. The repetitive stuff. The things that take forever if you don't already know Blender. It won't replace your 3D artist. It replaces the boring part before they start.
0:11

Tested Claude + Blender today with two real workflows. Sharing what actually happened. First one was a simple demo. Gave it one sentence to build a cyberpunk room. Geometry, lighting, camera, render. It got there, though not everything in the prompt landed perfectly. Good enough to show the concept, not a stress test. Second one was more interesting. Threw a raw photogrammetry scan at it. Massey Ferguson tractor, 250k faces, grass background everywhere, debris floating all over the place. Asked Claude to clean it up autonomously. It did the work. Removed 106 floating chunks, cut face count by 87%, stripped the grass, flipped the model upright, set up studio lighting and rendered. Technically it worked. But honest answer: the result wasn't clean enough for production. This kind of cleanup still needs the right tools and someone who knows what they're doing. So here's where it actually fits. Not the precise technical stuff. The setup work. The repetitive stuff. The things that take forever if you don't already know Blender. It won't replace your 3D artist. It replaces the boring part before they start.

KIRI Engine - 3D Scanner App

61,093 просмотров • 3 месяцев назад

Robotics keeps hitting the same wall. Single task RL works, but... it does not scale to hundreds of tasks or new embodiments. This new paper looks like a real step toward fixing that. The team introduces MMBench, a benchmark with 200 tasks across many domains and robots, and Newt, a language conditioned world model trained online across all 200 tasks at once. The simple idea behind Newt: The model learns from demos to get the right priors It trains across many tasks through online interaction It uses language to ground the goal It adapts fast when a new task shows up What stood out to me: ✅ One model trained on 200 tasks at the same time ✅ Language conditioned control for both states and RGB ✅ Better data efficiency than strong baselines ✅ Strong open loop control ✅ Fast adaptation to new tasks and embodiments ✅ Full release of 200 checkpoints, 4000 demos, code, and benchmark This is a good push toward general control instead of one model per task. If you want the full paper: Project page: —- Weekly robotics and AI insights. Subscribe free:
0:11

Robotics keeps hitting the same wall. Single task RL works, but... it does not scale to hundreds of tasks or new embodiments. This new paper looks like a real step toward fixing that. The team introduces MMBench, a benchmark with 200 tasks across many domains and robots, and Newt, a language conditioned world model trained online across all 200 tasks at once. The simple idea behind Newt: The model learns from demos to get the right priors It trains across many tasks through online interaction It uses language to ground the goal It adapts fast when a new task shows up What stood out to me: ✅ One model trained on 200 tasks at the same time ✅ Language conditioned control for both states and RGB ✅ Better data efficiency than strong baselines ✅ Strong open loop control ✅ Fast adaptation to new tasks and embodiments ✅ Full release of 200 checkpoints, 4000 demos, code, and benchmark This is a good push toward general control instead of one model per task. If you want the full paper: Project page: —- Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

70,090 просмотров • 8 месяцев назад

You don't understand... Higgsfield MCP + Claude just automated AI film making. Every single step you used to grind through to make an AI movie, you can now do 10x faster. Drop the script into Claude Opus 4.8 and say: "Here's my script. Break it into a full shotlist. Shot number, scene, shot type, camera move and the action in each frame." Now the whole film is mapped, shot by shot. - Pull your assets. Ask Claude: "From this shotlist, list every character, every location and every prop across the whole film." That's your build list. The stuff you would need to generate and give as references in next steps. - Build the character sheets. Higgsfield MCP is connected, so Claude has hands now to do stuff directly. It generates the images itself. Have the full body, back view and close up in the character sheet. One per character. Each sheet becomes the locked reference for that face. Same move for locations, generate the empty plate for each one before anyone steps into it. - Generate the frames. Feed Claude the references plus the shot and have it write and fire the Seedance 2.0 prompt. "Using the lead's character sheet and the alley plate, generate shot 4 in Seedance 2.0. Low angle, slow push-in, rain." Claude builds the prompt, calls Seedance 2.0 and the frame lands back in chat. Use a Seedance 2.0 skill to teach Claude how to prompt it properly. Now, there are 3 ways to make the shots. Pick one per scene. - Pure prompting. Fastest one. You describe the action in words and let Seedance interpret it. For consistency across a sequence, feed it a frame from the previous shot so the look carries. - Storyboarding. You hand it a panel and it matches that composition exactly. Way more control over how the shot is framed. The tradeoff is that it can introduce more cuts than you actually want. - Path Control System This is the latest technique Seedance 2.0 technique. Generate a still base plate of the scene. Draw a red line across it to mark the exact path of the movement, then describe what's happening. Seedance follows that line for the action. Also ask Claude to remove the red line when animating. This is the one for anything where motion has to land precisely. The output reads like real live action. - Lastly, generate every clip you need, then cut them together. Get it to Capcut for editing and audio design. And that's it. The pipeline that used to need a full crew and a studio can now run from one Claude chat. 2026 is gonna be wild
0:14

You don't understand... Higgsfield MCP + Claude just automated AI film making. Every single step you used to grind through to make an AI movie, you can now do 10x faster. Drop the script into Claude Opus 4.8 and say: "Here's my script. Break it into a full shotlist. Shot number, scene, shot type, camera move and the action in each frame." Now the whole film is mapped, shot by shot. - Pull your assets. Ask Claude: "From this shotlist, list every character, every location and every prop across the whole film." That's your build list. The stuff you would need to generate and give as references in next steps. - Build the character sheets. Higgsfield MCP is connected, so Claude has hands now to do stuff directly. It generates the images itself. Have the full body, back view and close up in the character sheet. One per character. Each sheet becomes the locked reference for that face. Same move for locations, generate the empty plate for each one before anyone steps into it. - Generate the frames. Feed Claude the references plus the shot and have it write and fire the Seedance 2.0 prompt. "Using the lead's character sheet and the alley plate, generate shot 4 in Seedance 2.0. Low angle, slow push-in, rain." Claude builds the prompt, calls Seedance 2.0 and the frame lands back in chat. Use a Seedance 2.0 skill to teach Claude how to prompt it properly. Now, there are 3 ways to make the shots. Pick one per scene. - Pure prompting. Fastest one. You describe the action in words and let Seedance interpret it. For consistency across a sequence, feed it a frame from the previous shot so the look carries. - Storyboarding. You hand it a panel and it matches that composition exactly. Way more control over how the shot is framed. The tradeoff is that it can introduce more cuts than you actually want. - Path Control System This is the latest technique Seedance 2.0 technique. Generate a still base plate of the scene. Draw a red line across it to mark the exact path of the movement, then describe what's happening. Seedance follows that line for the action. Also ask Claude to remove the red line when animating. This is the one for anything where motion has to land precisely. The output reads like real live action. - Lastly, generate every clip you need, then cut them together. Get it to Capcut for editing and audio design. And that's it. The pipeline that used to need a full crew and a studio can now run from one Claude chat. 2026 is gonna be wild

Rez Karim

10,951 просмотров • 2 месяцев назад

there is so much real data just sitting in the open right now it's almost funny. four years of starlight on every star, a NASA archive that's been free for over a decade, detectors still recording the sky tonight, and barely anyone has a net pointed at any of it. so i pointed one. this is me pulling the planet data, the data loading is the boring part. the net i built to read it, the wall it hit, and what that taught me about where AI goes next, that's the full story, and it drops tonight. the data's public, the tools are free, the box fits on a desk. what's stopping you. you can just do things anon.
0:11

there is so much real data just sitting in the open right now it's almost funny. four years of starlight on every star, a NASA archive that's been free for over a decade, detectors still recording the sky tonight, and barely anyone has a net pointed at any of it. so i pointed one. this is me pulling the planet data, the data loading is the boring part. the net i built to read it, the wall it hit, and what that taught me about where AI goes next, that's the full story, and it drops tonight. the data's public, the tools are free, the box fits on a desk. what's stopping you. you can just do things anon.

Sudo su

60,445 просмотров • 2 месяцев назад

I made a second version of the transformation video. This time I moved the character into a real environment instead of using a plain white background. I also changed the opening and showed the final transformation result first. The overall flow feels much stronger now. Full workflow + prompts: The interesting part is that this type of video is much easier to make than it looks. You only need a base image, then generate the next keyframe through simple edits or outfit changes on the canvas. The entire transformation sequence is built from those keyframes.
0:18

I made a second version of the transformation video. This time I moved the character into a real environment instead of using a plain white background. I also changed the opening and showed the final transformation result first. The overall flow feels much stronger now. Full workflow + prompts: The interesting part is that this type of video is much easier to make than it looks. You only need a base image, then generate the next keyframe through simple edits or outfit changes on the canvas. The entire transformation sequence is built from those keyframes.

underwood

313,847 просмотров • 2 месяцев назад