正在加载视频...

视频加载失败

返回首页

🚨 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 次观看 • 11 个月前 •via X (Twitter)

科学技术新闻政治艺术
LIVE

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

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 次观看 • 6 个月前

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 次观看 • 1 个月前

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 次观看 • 7 个月前

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 次观看 • 5 个月前

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 次观看 • 11 个月前

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 次观看 • 6 个月前

🚨 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 次观看 • 1 年前

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 次观看 • 11 个月前

🚨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 次观看 • 11 个月前

🔥 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 次观看 • 11 个月前

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 次观看 • 9 个月前

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 次观看 • 1 年前

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 次观看 • 10 个月前

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 次观看 • 1 年前

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 次观看 • 1 年前

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 次观看 • 9 个月前

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 次观看 • 6 个月前

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 次观看 • 1 年前

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 次观看 • 1 年前

🚨 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 次观看 • 11 个月前