正在加载视频...

视频加载失败

返回首页

#Viggle is back with an open model — Viggle-Animate — and it’s pretty damn capable. For the first time, they’re releasing weights + code. It replaces characters in video using MiniMax H3. Take a video, grab one frame, manually redraw the character as anything you want, and the model...

VORTEX_Promos's profile picture

VORTEX: AI Bros & AI Arena, Peak AI Buzz

125,637 subscribers

47,030 次观看 • 12 天前 •via X (Twitter)

#Viggle
LIVE

Anya Rossi• Live Now

Private livecam show

5 条评论

Yun Chen 的头像
Yun Chen12 天前

for anyone interested

Eylül demir 的头像
Eylül demir12 天前

Wait so you can swap a character from just one edited frame? thats actually insane. whats the link to this app

Derin Lale 的头像
Derin Lale12 天前

link please, i wanna test it. been trying random ai apps and most of them were overhyped tbh

Gökhan Demir 的头像
Gökhan Demir12 天前

this looks wild, link please

sema🇹🇷 的头像
sema🇹🇷12 天前

this is cool but also kinda scary ngl. if it’s open weights what stops people from making fake vids way too easily

相关视频

MiniMax H3 is native in ComfyUI, day zero with the weights. Model highlights: → Text-to-video, prompt only → Image-to-video → First-and-last-frame - control the opening frame, the closing frame, or both → Reference-to-video - carry a subject, a motion, or a voice through the clip → In-place editing - modify a shot you already have instead of regenerating it The capability MiniMax (official) leads with is multimodal context understanding, and it's what collapses those five tasks into one model. H3 takes images, audio, and video together and resolves them against a prompt that explains how they relate. Download the workflows & learn more in our blog 👇
1:06

MiniMax H3 is native in ComfyUI, day zero with the weights. Model highlights: → Text-to-video, prompt only → Image-to-video → First-and-last-frame - control the opening frame, the closing frame, or both → Reference-to-video - carry a subject, a motion, or a voice through the clip → In-place editing - modify a shot you already have instead of regenerating it The capability MiniMax (official) leads with is multimodal context understanding, and it's what collapses those five tasks into one model. H3 takes images, audio, and video together and resolves them against a prompt that explains how they relate. Download the workflows & learn more in our blog 👇

ComfyUI

234,529 次观看 • 1 个月前

I’m testing the new 4-step Turbo LoRA for MiniMax. With just 16GB of VRAM, I can generate 15 seconds of 480p video in around 1 minute and 30 seconds! I also noticed something pretty funny if you use a song as an audio reference and tell the character to dance to it, the character actually follows the rhythm of the music surprisingly well.
0:30

I’m testing the new 4-step Turbo LoRA for MiniMax. With just 16GB of VRAM, I can generate 15 seconds of 480p video in around 1 minute and 30 seconds! I also noticed something pretty funny if you use a song as an audio reference and tell the character to dance to it, the character actually follows the rhythm of the music surprisingly well.

Alex

50,293 次观看 • 1 个月前

So Runway Aleph 2.0 just dropped, and it introduces a pretty interesting workflow for AI video footage editing. Rather than repeatedly prompting a video model and hoping it makes the change you want, you can edit a specific frame first, then use that frame to guide the video generation. For this test, I take an existing footage inside Runway: • Picked a frame from the original video • Used Nano Banana Pro to add a new effect/object • Brought that frame into Aleph 2.0 to generate the updated video It feels like a more controllable and potentially cheaper way to make targeted edits to existing footage than current AI video omni models available like Seedance and Gemini.
2:59

So Runway Aleph 2.0 just dropped, and it introduces a pretty interesting workflow for AI video footage editing. Rather than repeatedly prompting a video model and hoping it makes the change you want, you can edit a specific frame first, then use that frame to guide the video generation. For this test, I take an existing footage inside Runway: • Picked a frame from the original video • Used Nano Banana Pro to add a new effect/object • Brought that frame into Aleph 2.0 to generate the updated video It feels like a more controllable and potentially cheaper way to make targeted edits to existing footage than current AI video omni models available like Seedance and Gemini.

Curious Refuge

11,410 次观看 • 3 个月前

Every time an AI video goes viral, someone asks the same thing: what was the prompt? Usually nobody knows. So I built a tool that finds out: It runs on MOSS-VL, open-weight 11B model (open source on GitHub: Upload a reference clip, it watches it frame by frame and reverse-engineers a generation prompt from what's actually in the video, not a guess. Refine it for a style, then generate something new from it. MOSS-VL is built for continuous video streams. Quantized versions deploy locally on a single RTX 4090, and it can be fine-tuned through LlamaFactory if you need it to understand something specific, like your own product's UI. I used the hosted API here, analyzing an uploaded clip instead of a live stream. Two ways to use it yourself: deploy it locally for real-time stream processing, or grab a free API key and use the hosted API on your own clips. API:
1:23

Every time an AI video goes viral, someone asks the same thing: what was the prompt? Usually nobody knows. So I built a tool that finds out: It runs on MOSS-VL, open-weight 11B model (open source on GitHub: Upload a reference clip, it watches it frame by frame and reverse-engineers a generation prompt from what's actually in the video, not a guess. Refine it for a style, then generate something new from it. MOSS-VL is built for continuous video streams. Quantized versions deploy locally on a single RTX 4090, and it can be fine-tuned through LlamaFactory if you need it to understand something specific, like your own product's UI. I used the hosted API here, analyzing an uploaded clip instead of a live stream. Two ways to use it yourself: deploy it locally for real-time stream processing, or grab a free API key and use the hosted API on your own clips. API:

Manish Kumar Shah

65,991 次观看 • 16 天前

19 year old from Warsaw made $11,200 in a month without ever showing his face films 1 movement on his phone → drops an AI character into it → uploads it as a faceless channel his entire "actor" is one photo from ChatGPT + an image gen model then Wan 2.2 Animate transfers expressions and full body motion onto that character $0 on a studio. $0 on actors. $0 on an editor. Week 1 > $1,340 Week 2 > $2,980 Week 3 > $6,880 1 month > $11,200 the secret is Animate Mix -> it replaces you in the frame but keeps your lighting and background the instruction is already publicly available
8:10

19 year old from Warsaw made $11,200 in a month without ever showing his face films 1 movement on his phone → drops an AI character into it → uploads it as a faceless channel his entire "actor" is one photo from ChatGPT + an image gen model then Wan 2.2 Animate transfers expressions and full body motion onto that character $0 on a studio. $0 on actors. $0 on an editor. Week 1 > $1,340 Week 2 > $2,980 Week 3 > $6,880 1 month > $11,200 the secret is Animate Mix -> it replaces you in the frame but keeps your lighting and background the instruction is already publicly available

Ridark

18,842 次观看 • 3 个月前

Another Hailuo AI (MiniMax) H3 test, this time looking at audio reference and performance (A little NSFW language on end of this one!). I recorded the dialogue as an audio track and fed that in as a reference with a image reference of the man. In the text prompts I gave some direction to the actor (Like the look to camera at the end). I think the model did a brilliant job of matching the performance to the words and emotion that were in the audio ref. Unlike Seedance 2.0 I didn't have to feed in black video or write the words in the prompt to get the words correct. It seemed to use the exact audio from the reference I provided, which is what you want when using voice actors. Things are getting real... fast
0:29

Another Hailuo AI (MiniMax) H3 test, this time looking at audio reference and performance (A little NSFW language on end of this one!). I recorded the dialogue as an audio track and fed that in as a reference with a image reference of the man. In the text prompts I gave some direction to the actor (Like the look to camera at the end). I think the model did a brilliant job of matching the performance to the words and emotion that were in the audio ref. Unlike Seedance 2.0 I didn't have to feed in black video or write the words in the prompt to get the words correct. It seemed to use the exact audio from the reference I provided, which is what you want when using voice actors. Things are getting real... fast

Uncanny Harry AI

14,036 次观看 • 1 个月前

I've been playing more with this depth map motion transfer workflow, and if you're trying to recreate really specific body movements from a reference video, this works surprisingly well. Here's the workflow: 1. Grab your reference video, then create your character and environment references. 2. Run the video through Depth Anything on fal to generate a depth map: 3. Drop that depth map into Seedance Omni as your motion reference along with your character and environment references. You don't even need the original video. I also tested this against using the original video as the motion reference in Seedance, and there's definitely a noticeable difference. One thing I found, though, is that this works much better for body movement than facial performance since the depth map can't really capture subtle facial motion. I'm running more tests to see if there's a good way to control both body movement and facial performance. If you have any workflows I should try, do share in the comments!
0:52

I've been playing more with this depth map motion transfer workflow, and if you're trying to recreate really specific body movements from a reference video, this works surprisingly well. Here's the workflow: 1. Grab your reference video, then create your character and environment references. 2. Run the video through Depth Anything on fal to generate a depth map: 3. Drop that depth map into Seedance Omni as your motion reference along with your character and environment references. You don't even need the original video. I also tested this against using the original video as the motion reference in Seedance, and there's definitely a noticeable difference. One thing I found, though, is that this works much better for body movement than facial performance since the depth map can't really capture subtle facial motion. I'm running more tests to see if there's a good way to control both body movement and facial performance. If you have any workflows I should try, do share in the comments!

Curious Refuge

16,487 次观看 • 1 个月前

SOMEONE VIBE CODED A VIDEO STREAM THAT IS SECRETLY 100% TEXT SO IT CANT BE BLOCKED it plays 360p video at 30fps, but theres no actual video on the page. every frame is just colored text characters being repainted on a canvas to the browser its not media at all, its javascript updating some text its called asciline, and here's the trick: > the server decodes the real video and streams it as binary packed text over websockets > the browser paints thousands of colored block characters fast enough to look like 360p > ad blockers and autoplay blockers cant catch it because theres no video element to catch > it streams in kilobytes since its just strings, so it runs on trash internet since the video is literally text, you can apply css glows to it, let people copy paste a moving frame, or feed it straight to a local llm however, an unblockable stream is also an unblockable ad as well
0:32

SOMEONE VIBE CODED A VIDEO STREAM THAT IS SECRETLY 100% TEXT SO IT CANT BE BLOCKED it plays 360p video at 30fps, but theres no actual video on the page. every frame is just colored text characters being repainted on a canvas to the browser its not media at all, its javascript updating some text its called asciline, and here's the trick: > the server decodes the real video and streams it as binary packed text over websockets > the browser paints thousands of colored block characters fast enough to look like 360p > ad blockers and autoplay blockers cant catch it because theres no video element to catch > it streams in kilobytes since its just strings, so it runs on trash internet since the video is literally text, you can apply css glows to it, let people copy paste a moving frame, or feed it straight to a local llm however, an unblockable stream is also an unblockable ad as well

Om Patel

1,860,617 次观看 • 3 个月前

Qwen3.8 27B wrote this game, Minimax H3 turned my gameplay into this video, and Minimax Music 3 wrote the soundtrack. Three local models, one apartment, zero cloud. Sound on. The chain: Qwen3.8 built the shooter in DeepSeek Harness, thats the 687 step log from my last post. I recorded a run, gave the recording to H3 as a video reference, and it rebuilt the level in its own render. Then Music 3 wrote the EBM track under it, two minutes per candidate, I picked one out of a stack. I wanted a frame for frame redraw first and it did not happen. The reference mode treats the anchor as a hint, so stitched chunks tore at the seams. The cut that worked: 10 seconds rebuilt straight from my recording, then 25 seconds where the model continues the level on its own, every chunk starting hard from the previous last frame. A bit visible seams, and honestly the invented half moves better than my footage. 35 seconds at 1344x768 took about an hour on the rig. The reference part burns roughly 7x the compute per second of plain generation, the free continuation is the cheap half. The game engine ate two 3090s. The video and the music took the other cards. One rig in one apartment now covers the whole credits list: code, footage, score. 18 months ago each of these steps was a company. Now they hand work to each other on my desk overnight. Qwen MiniMax (official)
0:35

Qwen3.8 27B wrote this game, Minimax H3 turned my gameplay into this video, and Minimax Music 3 wrote the soundtrack. Three local models, one apartment, zero cloud. Sound on. The chain: Qwen3.8 built the shooter in DeepSeek Harness, thats the 687 step log from my last post. I recorded a run, gave the recording to H3 as a video reference, and it rebuilt the level in its own render. Then Music 3 wrote the EBM track under it, two minutes per candidate, I picked one out of a stack. I wanted a frame for frame redraw first and it did not happen. The reference mode treats the anchor as a hint, so stitched chunks tore at the seams. The cut that worked: 10 seconds rebuilt straight from my recording, then 25 seconds where the model continues the level on its own, every chunk starting hard from the previous last frame. A bit visible seams, and honestly the invented half moves better than my footage. 35 seconds at 1344x768 took about an hour on the rig. The reference part burns roughly 7x the compute per second of plain generation, the free continuation is the cheap half. The game engine ate two 3090s. The video and the music took the other cards. One rig in one apartment now covers the whole credits list: code, footage, score. 18 months ago each of these steps was a company. Now they hand work to each other on my desk overnight. Qwen MiniMax (official)

Alexey Fateev

34,605 次观看 • 1 个月前

SITUATION EXPLAINED: MiniMax released H3 with open weights, and it's already #1 in video editing. • Priced at $7.80 per minute of 2K video, against Seedance 2.0 at $22.45 and Kling 3.0 at $20.16 • It ranks #1 on Artificial Analysis for video editing, #2 for text-to-video behind Gemini Omni Flash, and #3 for image-to-video • H3 takes text, images, video, and audio in a single context and generates 5-15 second clips at native 2K, 24fps, with native stereo audio • MiniMax is releasing the weights under its Community License within days, which would make it the strongest open-weights video model by a wide margin • It launched the same week ByteDance rolled out Seedance 2.5, which now generates 30-second 4K video from a single prompt • Seedance 2.5's face consistency across a full 30 seconds is the visible jump, earlier models drifted into a different face partway through • Voices are still the obvious tell, the video reads as real long before the audio does • Smaller labs building purpose-built video models are now beating frontier labs at this specific task Theo Jaffee: "This is gonna be one of the biggest examples of things that people are gonna do with these models, historical simulations, basically. Nostalgia videos for zoomers."
7:17

SITUATION EXPLAINED: MiniMax released H3 with open weights, and it's already #1 in video editing. • Priced at $7.80 per minute of 2K video, against Seedance 2.0 at $22.45 and Kling 3.0 at $20.16 • It ranks #1 on Artificial Analysis for video editing, #2 for text-to-video behind Gemini Omni Flash, and #3 for image-to-video • H3 takes text, images, video, and audio in a single context and generates 5-15 second clips at native 2K, 24fps, with native stereo audio • MiniMax is releasing the weights under its Community License within days, which would make it the strongest open-weights video model by a wide margin • It launched the same week ByteDance rolled out Seedance 2.5, which now generates 30-second 4K video from a single prompt • Seedance 2.5's face consistency across a full 30 seconds is the visible jump, earlier models drifted into a different face partway through • Voices are still the obvious tell, the video reads as real long before the audio does • Smaller labs building purpose-built video models are now beating frontier labs at this specific task Theo Jaffee: "This is gonna be one of the biggest examples of things that people are gonna do with these models, historical simulations, basically. Nostalgia videos for zoomers."

MTS

55,187 次观看 • 1 个月前

Restyling games is much harder than generating a video. Games can’t unintentionally “reset” at every frame: • Your character should stay the same when the camera moves • Damage, lighting, and objects must persist • A room should look the same when you look away and look back And it all has to run in real-time. Reverie v0.1.0 is our first stab at a real-time generative model for playable worlds. Below is a comparison with ours (left) with MirageLSD v2 (right). It’s early and far from perfect but watch what stays consistent as the video continues. 🧵 Prompts below (GPT-5.2).
0:31

Restyling games is much harder than generating a video. Games can’t unintentionally “reset” at every frame: • Your character should stay the same when the camera moves • Damage, lighting, and objects must persist • A room should look the same when you look away and look back And it all has to run in real-time. Reverie v0.1.0 is our first stab at a real-time generative model for playable worlds. Below is a comparison with ours (left) with MirageLSD v2 (right). It’s early and far from perfect but watch what stays consistent as the video continues. 🧵 Prompts below (GPT-5.2).

Sharon Lee

30,737 次观看 • 9 个月前

Would you like to have full control over character movement and camera shots? 📽️ That’s exactly what you can achieve with Kinetix Upload a first frame and an acting video (or use one from their gallery), choose the camera movement, and within minutes you’ll see that character perform your moves. It’s the closest thing to being inside an avatar 🤯 Now imagine the potential for ads, music videos, and even movies. Here’s how it works. It’s really easy 👇
0:31

Would you like to have full control over character movement and camera shots? 📽️ That’s exactly what you can achieve with Kinetix Upload a first frame and an acting video (or use one from their gallery), choose the camera movement, and within minutes you’ll see that character perform your moves. It’s the closest thing to being inside an avatar 🤯 Now imagine the potential for ads, music videos, and even movies. Here’s how it works. It’s really easy 👇

OscarAI

27,034 次观看 • 9 个月前

this guy built an AI video pipeline that turns one prompt into a finished short. he barely opens editing software. give Claude a simple idea. in the demo: a puppy rescue story. Claude runs the entire production from there: → generates the images with Nano Banana 2 → turns them into motion with Kinovi / Seedance 2.0 → stitches the clips together with FFmpeg → uploads the finished video no manually generating every frame. no dragging clips around a timeline for an hour. no stitching together the edit by hand. here’s the actual shift, and it’s bigger than “AI made a video”: Claude isn’t just one tool in the chain anymore. it’s coordinating the whole chain deciding what goes where, which tool handles which step, and executing it end to end. idea → images → video clips → edit → final render. one prompt in, finished short out. most people are still using AI one tool at a time generate an image here, cut it there, stitch it somewhere else, doing the coordination themselves. the bigger unlock isn’t a better individual tool. it’s connecting the tools so nothing needs a human in between steps. give it an idea. let the system make the video.
1:02

this guy built an AI video pipeline that turns one prompt into a finished short. he barely opens editing software. give Claude a simple idea. in the demo: a puppy rescue story. Claude runs the entire production from there: → generates the images with Nano Banana 2 → turns them into motion with Kinovi / Seedance 2.0 → stitches the clips together with FFmpeg → uploads the finished video no manually generating every frame. no dragging clips around a timeline for an hour. no stitching together the edit by hand. here’s the actual shift, and it’s bigger than “AI made a video”: Claude isn’t just one tool in the chain anymore. it’s coordinating the whole chain deciding what goes where, which tool handles which step, and executing it end to end. idea → images → video clips → edit → final render. one prompt in, finished short out. most people are still using AI one tool at a time generate an image here, cut it there, stitch it somewhere else, doing the coordination themselves. the bigger unlock isn’t a better individual tool. it’s connecting the tools so nothing needs a human in between steps. give it an idea. let the system make the video.

RUX

11,269 次观看 • 1 个月前

Everybody speak about consistent character for video generation as Minimax, Kling etc... But nothing looking super stable. And so I trained for the first time a LoRA model on Hunyuan video model (open source) on a real person. It take approximatly 15h of training on a A100 GPU with 50 videos. the result is pretty good !! With more training it will allow to have even better result. The result was generated inside ComfyUI. All this video have been generated in AI. Check at , we are doing cool stuff :)
0:21

Everybody speak about consistent character for video generation as Minimax, Kling etc... But nothing looking super stable. And so I trained for the first time a LoRA model on Hunyuan video model (open source) on a real person. It take approximatly 15h of training on a A100 GPU with 50 videos. the result is pretty good !! With more training it will allow to have even better result. The result was generated inside ComfyUI. All this video have been generated in AI. Check at , we are doing cool stuff :)

Lovis Odin

93,560 次观看 • 1 年前

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:
6:05

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 次观看 • 2 年前

THIS $1,300 CARD HAS THE SAME 32GB OF VRAM AS A $2,000+ RTX 5090 - FOR LOCAL AI, THAT'S THE SPEC THAT DECIDES EVERYTHING. that clip is the gigabyte radeon ai pro r9700 ai top, 32gb of vram, built for local ai. the pitch is simple: the same memory capacity as an rtx 5090, for roughly a third of what a 5090 actually sells for. here's why that matters, and where it doesn't. for ai, vram is the gate. a model either fits in memory or it doesn't. 32gb loads models a 16gb card can't touch, full stop. so for running local llms and image models, this card does the one thing that counts, cheap. honest line: this is not a 5090 for gaming. the 5090 is far faster at raster and ray tracing. they only match on how much vram they carry. if you want frames, buy the 5090. if you want to fit big models locally, you just found the same 32gb for a third of the money. no $2,000+ price tag, no cloud gpu rental, no model too big for 16gb. the uncomfortable part isn't that amd is cheaper. it's that for local ai you were about to overpay for gaming power you'd never use. follow RetroChainer for more on paying for the spec that matters, and bookmark this before your next gpu.
1:52

THIS $1,300 CARD HAS THE SAME 32GB OF VRAM AS A $2,000+ RTX 5090 - FOR LOCAL AI, THAT'S THE SPEC THAT DECIDES EVERYTHING. that clip is the gigabyte radeon ai pro r9700 ai top, 32gb of vram, built for local ai. the pitch is simple: the same memory capacity as an rtx 5090, for roughly a third of what a 5090 actually sells for. here's why that matters, and where it doesn't. for ai, vram is the gate. a model either fits in memory or it doesn't. 32gb loads models a 16gb card can't touch, full stop. so for running local llms and image models, this card does the one thing that counts, cheap. honest line: this is not a 5090 for gaming. the 5090 is far faster at raster and ray tracing. they only match on how much vram they carry. if you want frames, buy the 5090. if you want to fit big models locally, you just found the same 32gb for a third of the money. no $2,000+ price tag, no cloud gpu rental, no model too big for 16gb. the uncomfortable part isn't that amd is cheaper. it's that for local ai you were about to overpay for gaming power you'd never use. follow RetroChainer for more on paying for the spec that matters, and bookmark this before your next gpu.

RetroChainer

38,844 次观看 • 1 个月前

I got this custom scorpion rigged, animated and running in my game in one full day with AI. GPT-6 built the entire rig. My part was preparing the model and motion references, then giving feedback. After trying a few approaches, I found a workflow that worked: 1. Give it a model that makes sense. I generated the model with Tripo P2.0, then cleaned it up myself. Low-poly, optimized, split into logical parts. I think that preparation mattered a lot. GPT-6 works on the mesh through code. A manageable vertex count and sensible parts give it a clearer starting point for bone placement and skinning. 2. Show it the movement you want. I took a reference image of the character and used Seedance to generate side-view animation videos. I decided which animations the game needed and selected the takes with the movements I liked. Then I gave GPT-6 the model, the videos and that animation list. There was no existing rig to start from. 3. Compare the animation frame by frame. This was the idea I wanted to test: ask GPT-6 to compare its Blender animation against the reference video frame by frame, from the same view. That gave it concrete poses and timing to work toward. I could point to where the feet should be planted or when the tail should strike. 4. Expect to give feedback. A generated run can look like hopping. An attack can start with a jump you never wanted. Choosing the references matters, and a side view still leaves depth and hidden legs to figure out. It took several iterations. I explained what looked wrong and how I wanted it to move, and GPT-6 kept refining the animation. Once the walk worked, I also had it create left and right strafe animations procedurally from that walk. Those didn't need their own reference videos. By the end of the day, the creature was in Unity. I've recorded the full workflow, including the Blender setup and feedback process:
0:59

I got this custom scorpion rigged, animated and running in my game in one full day with AI. GPT-6 built the entire rig. My part was preparing the model and motion references, then giving feedback. After trying a few approaches, I found a workflow that worked: 1. Give it a model that makes sense. I generated the model with Tripo P2.0, then cleaned it up myself. Low-poly, optimized, split into logical parts. I think that preparation mattered a lot. GPT-6 works on the mesh through code. A manageable vertex count and sensible parts give it a clearer starting point for bone placement and skinning. 2. Show it the movement you want. I took a reference image of the character and used Seedance to generate side-view animation videos. I decided which animations the game needed and selected the takes with the movements I liked. Then I gave GPT-6 the model, the videos and that animation list. There was no existing rig to start from. 3. Compare the animation frame by frame. This was the idea I wanted to test: ask GPT-6 to compare its Blender animation against the reference video frame by frame, from the same view. That gave it concrete poses and timing to work toward. I could point to where the feet should be planted or when the tail should strike. 4. Expect to give feedback. A generated run can look like hopping. An attack can start with a jump you never wanted. Choosing the references matters, and a side view still leaves depth and hidden legs to figure out. It took several iterations. I explained what looked wrong and how I wanted it to move, and GPT-6 kept refining the animation. Once the walk worked, I also had it create left and right strafe animations procedurally from that walk. Those didn't need their own reference videos. By the end of the day, the creature was in Unity. I've recorded the full workflow, including the Blender setup and feedback process:

Stefan 3D AI

12,563 次观看 • 6 天前

I texted someone inside a simulation. She had to go upstairs and find her phone before she could text me back. The video model didn’t decide what happened. This is Argos, my stateful simulation engine, rendered through H3 using Fal Director. Thanks to fal for the generous credits helping me bring it to life. Underneath the video is a persistent world: characters, objects, locations, and systems. The characters have their own cognition, memories, and goals. They choose actions; the simulation determines what actually happens. Her phone has a location. Messages have delivery and read states. Typing a reply takes time. If I move the phone before she gets there, it’s gone—even if she remembers leaving it there. Argos turns those changing world states into instructions for H3 to depict. You can also see her character thought stream. The video currently trails the simulation a little; I’m working on aligning the two. Next: connect this to SMS, so you can text someone inside the world and receive their reply. Or whisper an impulse into her thoughts and see whether she follows it. The bigger ambition is a world that keeps growing while its characters inhabit it—with agents writing and maintaining the simulation’s systems. I’ll be building more of this in public. Not just a video that looks like a world. A world that keeps existing underneath the video.
1:42

I texted someone inside a simulation. She had to go upstairs and find her phone before she could text me back. The video model didn’t decide what happened. This is Argos, my stateful simulation engine, rendered through H3 using Fal Director. Thanks to fal for the generous credits helping me bring it to life. Underneath the video is a persistent world: characters, objects, locations, and systems. The characters have their own cognition, memories, and goals. They choose actions; the simulation determines what actually happens. Her phone has a location. Messages have delivery and read states. Typing a reply takes time. If I move the phone before she gets there, it’s gone—even if she remembers leaving it there. Argos turns those changing world states into instructions for H3 to depict. You can also see her character thought stream. The video currently trails the simulation a little; I’m working on aligning the two. Next: connect this to SMS, so you can text someone inside the world and receive their reply. Or whisper an impulse into her thoughts and see whether she follows it. The bigger ambition is a world that keeps growing while its characters inhabit it—with agents writing and maintaining the simulation’s systems. I’ll be building more of this in public. Not just a video that looks like a world. A world that keeps existing underneath the video.

Parzival - ∞/89

489,635 次观看 • 16 天前

This is probably the most complex workflow I’ve ever built, only with open-source tools. It took my 4 days. It takes four inputs: author, title, and style; and generates a full visual animated story in one click in ComfyUI . I worked on it for four days. There are still some bugs, but here’s the first preview. Here’s a quick breakdown: - The four inputs are sent to LLMs with precise instructions to generate: first, prompts for images and image modifications; second, prompts for animations; third, prompts for generating music. - All voices are generated from the text and timed precisely, as they determine the length of each animation segment. - The first image and video are generated to serve as the title, but also as the guide for all other images created for the video. - Titles and subtitles are also added automatically in Comfy. - I also developed a lot of custom nodes for minor frame calculations, mostly to match audio and video. - The full system is a large loop that, for each line of text, generates an image and then a video from that image. The loop was the hardest part to build in this workflow, so it can process either a 20-second video or a 2-minute video with the same input. - There are multiple combinations of LLMs that try to understand the text in the best way to provide the best prompts for images and video. - The final video is assembled entirely within ComfyUI. - The music is generated based on the LLM output and matches the exact timing of the full animation. - Done! For reference, this workflow uses a lot of models and only works on an RTX 6000 Pro with plenty of RAM. My goal is not to replace humans, as I’ll try to explain later, this workflow is highly controlled and can be adapted or reworked at any point by real artists! My aim was to create a tool that can animate text in one go, allowing the AI some freedom while keeping a strict flow. I don’t know yet how I’ll share this workflow with people, I still need to polish it properly, but maybe through Patreon. Anyway, I hope you enjoy my research, and let’s always keep pushing further! :)
0:55

This is probably the most complex workflow I’ve ever built, only with open-source tools. It took my 4 days. It takes four inputs: author, title, and style; and generates a full visual animated story in one click in ComfyUI . I worked on it for four days. There are still some bugs, but here’s the first preview. Here’s a quick breakdown: - The four inputs are sent to LLMs with precise instructions to generate: first, prompts for images and image modifications; second, prompts for animations; third, prompts for generating music. - All voices are generated from the text and timed precisely, as they determine the length of each animation segment. - The first image and video are generated to serve as the title, but also as the guide for all other images created for the video. - Titles and subtitles are also added automatically in Comfy. - I also developed a lot of custom nodes for minor frame calculations, mostly to match audio and video. - The full system is a large loop that, for each line of text, generates an image and then a video from that image. The loop was the hardest part to build in this workflow, so it can process either a 20-second video or a 2-minute video with the same input. - There are multiple combinations of LLMs that try to understand the text in the best way to provide the best prompts for images and video. - The final video is assembled entirely within ComfyUI. - The music is generated based on the LLM output and matches the exact timing of the full animation. - Done! For reference, this workflow uses a lot of models and only works on an RTX 6000 Pro with plenty of RAM. My goal is not to replace humans, as I’ll try to explain later, this workflow is highly controlled and can be adapted or reworked at any point by real artists! My aim was to create a tool that can animate text in one go, allowing the AI some freedom while keeping a strict flow. I don’t know yet how I’ll share this workflow with people, I still need to polish it properly, but maybe through Patreon. Anyway, I hope you enjoy my research, and let’s always keep pushing further! :)

Lovis Odin

58,841 次观看 • 1 年前