Loading video...

Video Failed to Load

Go Home

🚨 BREAKING: Open-source just outperformed closed-source in AI video generation. I tested four video models using the same prompt focused on facial expressions, cinematic control, and more. Here are the results 👇 #1 Laughing heartily expression, F1 driver enjoying victory moment

heyshrutimishra's profile picture

Shruti

163,076 subscribers

62,293 views • 10 months ago •via X (Twitter)

Science & TechnologyNews & PoliticsArts
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

I tested Kling 2.6 Motion Control head-to-head against other video models. Same prompt. Same reference. Kling outperformed across the board. Here’s why: 👇
0:10

I tested Kling 2.6 Motion Control head-to-head against other video models. Same prompt. Same reference. Kling outperformed across the board. Here’s why: 👇

Rishabh

131,196 views • 6 months ago

OPEN SOURCE IS REALLY WINNING THIS TIME ran the same prompt on Claude Design and Kimi K2.6 here're the outputs and Kimi on the right is 7x cheaper and 100% open source... see prompt in the comments👇
0:18

OPEN SOURCE IS REALLY WINNING THIS TIME ran the same prompt on Claude Design and Kimi K2.6 here're the outputs and Kimi on the right is 7x cheaper and 100% open source... see prompt in the comments👇

Hasan

101,616 views • 1 month ago

Our video editing model Lucy-Edit just got way better. 2× faster, half the price (and open source). More control, faster performance, and seamless results.
0:11

Our video editing model Lucy-Edit just got way better. 2× faster, half the price (and open source). More control, faster performance, and seamless results.

Decart

814,369 views • 7 months ago

I've nearly ditched closed source models for image generation (in creative workflows). For most tasks, the cost/speed ratio doesn't justify closed models anymore. Open models have caught up on quality and I can try 15 new images in 1-2 sec. Iteration speed matters. Sharing the few models I currently use ⬇️
0:16

I've nearly ditched closed source models for image generation (in creative workflows). For most tasks, the cost/speed ratio doesn't justify closed models anymore. Open models have caught up on quality and I can try 15 new images in 1-2 sec. Iteration speed matters. Sharing the few models I currently use ⬇️

Victor M

39,333 views • 5 months ago

OpenAI's open-source models are not Horizon Alpha or Beta I ran the same prompts again, and the results from OSS-120 were significantly worse than those produced by the Horizon models
0:10

OpenAI's open-source models are not Horizon Alpha or Beta I ran the same prompts again, and the results from OSS-120 were significantly worse than those produced by the Horizon models

AiBattle

73,582 views • 10 months ago

This is NOT a real person. 🤯 I just tested Seedance 1.5 Pro on Higgsfield AI. It creates visuals and sound at the same time, with spot-on lip sync, natural ambient audio and cinematic cuts, all from a single prompt. Here are few more examples 👇🏻
0:12

This is NOT a real person. 🤯 I just tested Seedance 1.5 Pro on Higgsfield AI. It creates visuals and sound at the same time, with spot-on lip sync, natural ambient audio and cinematic cuts, all from a single prompt. Here are few more examples 👇🏻

Heisenberg

21,677 views • 6 months ago

🚨 SkyReels just launched! The world’s first open-source video generation platform supporting unlimited duration 🔥 All-in-one creator toolkit: - Consistent high-quality video (LoRA ready) - Fast gen, amazing output. - Amazing facial expressions . Plus text-to-film agent handles everything: script, character, storyboards, full AV gen, auto-edit . it's Wild! Step by step tutorial 👇
0:12

🚨 SkyReels just launched! The world’s first open-source video generation platform supporting unlimited duration 🔥 All-in-one creator toolkit: - Consistent high-quality video (LoRA ready) - Fast gen, amazing output. - Amazing facial expressions . Plus text-to-film agent handles everything: script, character, storyboards, full AV gen, auto-edit . it's Wild! Step by step tutorial 👇

AshutoshShrivastava

81,012 views • 1 year ago

And here comes the objective control footage. The video shows a precise hit on the local TCC office in Druzhkovka using a Geran UAV. Right on target! Source:
0:16

And here comes the objective control footage. The video shows a precise hit on the local TCC office in Druzhkovka using a Geran UAV. Right on target! Source:

MD

12,413 views • 11 months ago

🚨BREAKING: This open-source AI turns flat images into 3D models instantly. Hunyuan 3D-2.1 just dropped. Here’s what’s inside (with real outputs): 👇
0:14

🚨BREAKING: This open-source AI turns flat images into 3D models instantly. Hunyuan 3D-2.1 just dropped. Here’s what’s inside (with real outputs): 👇

Saadat Najafova

290,024 views • 11 months ago

🔥 BREAKING: Open source just leveled up AI agents Eigent gives you a fully local, customizable AI workforce....built to run on your laptop. → No vendor lock-in → No cloud dependency → 100% open source Just fast, private, parallel agents you control (Here's how):👇
0:15

🔥 BREAKING: Open source just leveled up AI agents Eigent gives you a fully local, customizable AI workforce....built to run on your laptop. → No vendor lock-in → No cloud dependency → 100% open source Just fast, private, parallel agents you control (Here's how):👇

Shruti

63,497 views • 11 months ago

You can now clone any website just by writing a prompt. Just paste the website URL and Al agents will instantly create a working clone you can build on top of. 100% open source with major AI models👇
0:17

You can now clone any website just by writing a prompt. Just paste the website URL and Al agents will instantly create a working clone you can build on top of. 100% open source with major AI models👇

Alvaro Cintas

66,979 views • 10 months ago

Comparing AI Video Models: Creepy found footage Pika 2.0 Kling AI 1.5 OpenAI Sora Google Veo-2 Runway Gen-3 Hunyuan Video Hailuo MiniMax Luma Dream Machine I ran the same prompt in each model 3-4x and chose the best results:
0:10

Comparing AI Video Models: Creepy found footage Pika 2.0 Kling AI 1.5 OpenAI Sora Google Veo-2 Runway Gen-3 Hunyuan Video Hailuo MiniMax Luma Dream Machine I ran the same prompt in each model 3-4x and chose the best results:

Heather Cooper

71,788 views • 1 year ago

open source AI is out of control.. someone generated this with some crazy unfiltered prompts using higgsfield wan.. this is dark side of AI here are the prompts:
0:12

open source AI is out of control.. someone generated this with some crazy unfiltered prompts using higgsfield wan.. this is dark side of AI here are the prompts:

el.cine

24,432 views • 9 months ago

We are excited to launch our two models Pharia-1-LLM-7B-control and Pharia-1-LLM-7B-control-aligned. Both models and the code used to train them are now publicly available and open-sourced for non-commercial research and educational use. Read our model blog post here: Learn more about our open-source codebase Scaling: #writtenbyalephalpha
0:13

We are excited to launch our two models Pharia-1-LLM-7B-control and Pharia-1-LLM-7B-control-aligned. Both models and the code used to train them are now publicly available and open-sourced for non-commercial research and educational use. Read our model blog post here: Learn more about our open-source codebase Scaling: #writtenbyalephalpha

Aleph Alpha

44,326 views • 1 year ago

Google Veo3 → I2V Prompting Guide. Playing with "human expression" Tips: + Guide the performance + Control facial expressions/gestures + It can handle finer details. + Don't overcomplicate the prompt BASE PROMPT STRUCTURE: [scene description], [expression/gesture description] (More exploration in thread 🧵) #google #veo3 #promptshare
0:16

Google Veo3 → I2V Prompting Guide. Playing with "human expression" Tips: + Guide the performance + Control facial expressions/gestures + It can handle finer details. + Don't overcomplicate the prompt BASE PROMPT STRUCTURE: [scene description], [expression/gesture description] (More exploration in thread 🧵) #google #veo3 #promptshare

Rory Flynn

160,500 views • 1 year ago

We are building “Open Source Nano Banana for Video” - here is open source demo v0.1 We are open sourcing Lucy Edit, the first foundation model for text-guided video editing! Get the model on Hugging Face 🤗, API on @FAL, and nodes on ComfyUI 🧵
0:17

We are building “Open Source Nano Banana for Video” - here is open source demo v0.1 We are open sourcing Lucy Edit, the first foundation model for text-guided video editing! Get the model on Hugging Face 🤗, API on @FAL, and nodes on ComfyUI 🧵

Decart

413,726 views • 9 months ago

The evolution of AI design in 2025 I tested the same prompt on 10 groundbreaking models of the year. We've come so far. Which one's your favourite?
0:19

The evolution of AI design in 2025 I tested the same prompt on 10 groundbreaking models of the year. We've come so far. Which one's your favourite?

Mattia

21,401 views • 6 months ago

it's over.. this AI agent can build AI apps now I just used Emergent AI to build an AI studio w/o censorship, it can generate and edit images using text and.. you can add any open source models to the studio more examples:
0:17

it's over.. this AI agent can build AI apps now I just used Emergent AI to build an AI studio w/o censorship, it can generate and edit images using text and.. you can add any open source models to the studio more examples:

el.cine

280,948 views • 1 year ago

LTX Studio just dropped the next stage of AI video evolution: LTXV 13B Distilled → Blazing-fast rendering → Consumer GPU-ready → Open source → Multiscale, cinematic, smooth Comparison against other top AI video modles included... 🧵
0:11

LTX Studio just dropped the next stage of AI video evolution: LTXV 13B Distilled → Blazing-fast rendering → Consumer GPU-ready → Open source → Multiscale, cinematic, smooth Comparison against other top AI video modles included... 🧵

Heather Cooper

32,098 views • 1 year ago

🚨 Omg.. the $1M AI War just began. Genspark launched a $1 MILLION Side-by-Side AI Showdown, challenging any AI, including ChatGPT. I tested many of them on the same tasks… but In every test, Genspark’s results came out on top. Check the head-to-head below: 👇
0:14

🚨 Omg.. the $1M AI War just began. Genspark launched a $1 MILLION Side-by-Side AI Showdown, challenging any AI, including ChatGPT. I tested many of them on the same tasks… but In every test, Genspark’s results came out on top. Check the head-to-head below: 👇

ZOYA ✪

105,301 views • 11 months ago