Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Training Wan 2.1-1.3B to use Qwen3-VL-2B text encoder. Doing 33% text only, 33% VL only, and 33% both. Just pretraining the two text input linear layers for now. It is amazing how quickly a model can adapt to a different text encoder. This is 25,750 steps, BS of 10.

Ostris

15,381 subscribers

26,778 views • 4 months ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

A quick way to improve how text behaves in your app is to use `text-wrap: balance`. It distributes text evenly across each line, avoiding orphaned words. It is only supported for a limited number lines (<6-10 depending on the browser), which means it's best used for headings or short paragraphs.

A quick way to improve how text behaves in your app is to use `text-wrap: balance`. It distributes text evenly across each line, avoiding orphaned words. It is only supported for a limited number lines (<6-10 depending on the browser), which means it's best used for headings or short paragraphs.

Jakub Krehel

58,413 views • 8 months ago

Your gaming gpu might be capable of more than you think 💀 NSFW Wan 1.3B is a community model for uncensored text-to-video generation, now available on Hugging Face. → 2.8GB model file → around 8GB VRAM for the base model → 480p video generation → runs locally through ComfyUI how to try it :) visit the Hugging Face model page download wan_1.3B_exp_e14 set up ComfyUI with the Wan 2.1 workflow load the model and test it locally model link: 18+ only. Check the model license and requirements before downloading.

Sensitive content

Your gaming gpu might be capable of more than you think 💀 NSFW Wan 1.3B is a community model for uncensored text-to-video generation, now available on Hugging Face. → 2.8GB model file → around 8GB VRAM for the base model → 480p video generation → runs locally through ComfyUI how to try it :) visit the Hugging Face model page download wan_1.3B_exp_e14 set up ComfyUI with the Wan 2.1 workflow load the model and test it locally model link: 18+ only. Check the model license and requirements before downloading.

DEATHLESS

35,659 views • 3 days ago

Just doing a first test with #runwayml new video to video. No image input yet, only text atm. But driving the animation is a good first step.

Just doing a first test with #runwayml new video to video. No image input yet, only text atm. But driving the animation is a good first step.

Jon Finger

389,298 views • 2 years ago

react-native-enriched 🤝 <EnrichedText> We just dropped a dedicated text component, making it a complete rich-text solution. Now it only takes a few lines of code to get your inputs and display text working seamlessly together using the exact same format.

react-native-enriched 🤝 <EnrichedText> We just dropped a dedicated text component, making it a complete rich-text solution. Now it only takes a few lines of code to get your inputs and display text working seamlessly together using the exact same format.

Software Mansion

19,502 views • 6 months ago

[to the tune of happy birthday] text turns into speech text turns into speech the model is launching text turns into speech

[to the tune of happy birthday] text turns into speech text turns into speech the model is launching text turns into speech

fofr

25,405 views • 6 months ago

hey babe <33 wanna see more? text me

Sensitive content

hey babe <33 wanna see more? text me

Chalina.l

78,475 views • 1 year ago

Bismillah. Image-To-Text Converter for Non-English PDFs is now available! It converts books in Arabic, Urdu, Persian, Spanish, etc. with amazing accuracy Currently this just a MVP version that extracts text but there is a lot on the roadmap iA Link below to test it out!

Bismillah. Image-To-Text Converter for Non-English PDFs is now available! It converts books in Arabic, Urdu, Persian, Spanish, etc. with amazing accuracy Currently this just a MVP version that extracts text but there is a lot on the roadmap iA Link below to test it out!

Shahrukh Raza

27,272 views • 2 years ago

STEVE-1: A Generative Model for Text-to-Behavior in Minecraft paper page: Constructing AI models that respond to text instructions is challenging, especially for sequential decision-making tasks. This work introduces an instruction-tuned Video Pretraining (VPT) model for Minecraft called STEVE-1, demonstrating that the unCLIP approach, utilized in DALL-E 2, is also effective for creating instruction-following sequential decision-making agents. STEVE-1 is trained in two steps: adapting the pretrained VPT model to follow commands in MineCLIP's latent space, then training a prior to predict latent codes from text. This allows us to finetune VPT through self-supervised behavioral cloning and hindsight relabeling, bypassing the need for costly human text annotations. By leveraging pretrained models like VPT and MineCLIP and employing best practices from text-conditioned image generation, STEVE-1 costs just $60 to train and can follow a wide range of short-horizon open-ended text and visual instructions in Minecraft. STEVE-1 sets a new bar for open-ended instruction following in Minecraft with low-level controls (mouse and keyboard) and raw pixel inputs, far outperforming previous baselines. We provide experimental evidence highlighting key factors for downstream performance, including pretraining, classifier-free guidance, and data scaling. All resources, including our model weights, training scripts, and evaluation tools are made available for further research.

STEVE-1: A Generative Model for Text-to-Behavior in Minecraft paper page: Constructing AI models that respond to text instructions is challenging, especially for sequential decision-making tasks. This work introduces an instruction-tuned Video Pretraining (VPT) model for Minecraft called STEVE-1, demonstrating that the unCLIP approach, utilized in DALL-E 2, is also effective for creating instruction-following sequential decision-making agents. STEVE-1 is trained in two steps: adapting the pretrained VPT model to follow commands in MineCLIP's latent space, then training a prior to predict latent codes from text. This allows us to finetune VPT through self-supervised behavioral cloning and hindsight relabeling, bypassing the need for costly human text annotations. By leveraging pretrained models like VPT and MineCLIP and employing best practices from text-conditioned image generation, STEVE-1 costs just $60 to train and can follow a wide range of short-horizon open-ended text and visual instructions in Minecraft. STEVE-1 sets a new bar for open-ended instruction following in Minecraft with low-level controls (mouse and keyboard) and raw pixel inputs, far outperforming previous baselines. We provide experimental evidence highlighting key factors for downstream performance, including pretraining, classifier-free guidance, and data scaling. All resources, including our model weights, training scripts, and evaluation tools are made available for further research.

AK

144,827 views • 3 years ago

This is kind of insane but making it official. You can literally text TEXTAI (839824) and AI answers your questions. Right in your texts. No bs. No app. No log in. Just text it.

This is kind of insane but making it official. You can literally text TEXTAI (839824) and AI answers your questions. Right in your texts. No bs. No app. No log in. Just text it.

Rushi Shah

14,437 views • 1 year ago

🆕 Now you can use Gemini in Google Sheets right from a cell to quickly generate, summarize, and categorize text. →

🆕 Now you can use Gemini in Google Sheets right from a cell to quickly generate, summarize, and categorize text. →

Google Workspace

250,060 views • 1 year ago

Rive text is live!! Animatable, variable, dynamic text for runtime, with full support for any language. There are a MONSTER amount of new things to play around with! 🚀 Create Text objects, styles, runs, and modifiers. 🚀 Support for any language. LTR, RTL, special characters/features, ligatures, etc. 🚀 Animate variable fonts. 🚀 Google Fonts are provided by default, but you can upload custom fonts. 🚀 Runs are a way to segment a text field into different sections. You can target runs at runtime to change their content dynamically. See documentation here: 🚀 Apply different text styles to runs. 🚀 Convert text to paths (flatten). 🚀 Text modifiers are a powerful way to add layered animation to text, while maintaining its editability! 🚀 Use transform constraints to resize graphics to text objects. Coming soon: 🚧 Ability to export fonts out of band or via CDN. They are currently packaged in the .riv file.

Rive text is live!! Animatable, variable, dynamic text for runtime, with full support for any language. There are a MONSTER amount of new things to play around with! 🚀 Create Text objects, styles, runs, and modifiers. 🚀 Support for any language. LTR, RTL, special characters/features, ligatures, etc. 🚀 Animate variable fonts. 🚀 Google Fonts are provided by default, but you can upload custom fonts. 🚀 Runs are a way to segment a text field into different sections. You can target runs at runtime to change their content dynamically. See documentation here: 🚀 Apply different text styles to runs. 🚀 Convert text to paths (flatten). 🚀 Text modifiers are a powerful way to add layered animation to text, while maintaining its editability! 🚀 Use transform constraints to resize graphics to text objects. Coming soon: 🚧 Ability to export fonts out of band or via CDN. They are currently packaged in the .riv file.

Guido Rosso

25,950 views • 3 years ago

Text-to-image diffusion transformer models learn to align text and image representations as a byproduct of their conditional denoising task. By taking the dot product between the text and image representations of a DiT model (like Flux 2), you can create rich saliency maps.

Text-to-image diffusion transformer models learn to align text and image representations as a byproduct of their conditional denoising task. By taking the dot product between the text and image representations of a DiT model (like Flux 2), you can create rich saliency maps.

Alec Helbling

94,195 views • 10 months ago

Adding this new Minimax h3 fused 4-step model to Maestro is a game changer! It supports text to video, image to video, references, and audio driven. And smooth infinite extend. example is only 4-steps; 720p at 14.4s, 2.5m to generate on 4090! or up to 8 steps for more detail!

Adding this new Minimax h3 fused 4-step model to Maestro is a game changer! It supports text to video, image to video, references, and audio driven. And smooth infinite extend. example is only 4-steps; 720p at 14.4s, 2.5m to generate on 4090! or up to 8 steps for more detail!

Blaine Brown

33,887 views • 1 month ago

Get beautiful text animations. We built a hand-crafted collection of text animations and wrapped them as a SKILL for your AI agent. Use it with Remotion, Motion, GSAP, WAAPI, or any animation library. It comes with clear animation specs - pacing, curves, transitions - so your output looks great from the first prompt. Install it with: npx skills add pixel-point/animate-text --skill animate-text Use it /animate-text apply soft-blur-in to hero section text

Get beautiful text animations. We built a hand-crafted collection of text animations and wrapped them as a SKILL for your AI agent. Use it with Remotion, Motion, GSAP, WAAPI, or any animation library. It comes with clear animation specs - pacing, curves, transitions - so your output looks great from the first prompt. Install it with: npx skills add pixel-point/animate-text --skill animate-text Use it /animate-text apply soft-blur-in to hero section text

Alex Barashkov

130,618 views • 6 months ago

The new open-weights MiniMax Design (H3) H3 is live on OpenRouter thanks to MiniMax (official)! H3 is a lightweight video model for text, image, audio, & video input, with native audio-visual output. Built for instruction-led edits, text/brand rendering, and video-2-video motion transfer.

OpenRouter

28,865 views • 3 months ago

Add text to any video. Text overlay is now live on the iOS video editor 🤍

Add text to any video. Text overlay is now live on the iOS video editor 🤍

Allegra Jacchia

97,802 views • 2 months ago

The `rebel-large` model is awesome for relation extraction 🔗 Paired with CUDA, it’s blazing fast ⚡️. With LlamaIndex 🦙 🦙, we can now build a knowledge graph over any text data super quickly! 🕸️ Full Colab notebook showing how you can use it:

The `rebel-large` model is awesome for relation extraction 🔗 Paired with CUDA, it’s blazing fast ⚡️. With LlamaIndex 🦙 🦙, we can now build a knowledge graph over any text data super quickly! 🕸️ Full Colab notebook showing how you can use it:

Jerry Liu

181,829 views • 3 years ago