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.

bytedance just released BAGEL! an open-source multimodal alternative to gpt-4o and gemini flash it supports: > image reasoning > image editing > video generation > style transfer (ghiblify anyone?) > 3d rotation > outpainting > navigation

Dreaming Tulpa 🥓👑

54,801 subscribers

258,018 views • 1 year ago •via X (Twitter)

Arts Gaming Science & Technology

Anya Rossi• Live Now

Private livecam show

11 Comments

Dreaming Tulpa 🥓👑1 year ago

project page: code: model: demo:

HUDI1 year ago

facebook has +2,8 billion active users, 1/3 of world population 📣👇

Mattias Johansson1 year ago

What does “3d rotation” mean ?

Emily1 year ago

The quality is terrible 😭😭😭

のうッ1 year ago

It's pretty good for a 7B multimodal model. 😲

SIKORA1 year ago

The logo looks like the font went missing lol

Cris Lenta1 year ago

Only 7B params? Too good to be true?

❝Rijn Hartman❞1 year ago

seems to be available on replicate too:

Futuro Martinez1 year ago

Modelos abiertos como BAGEL nos abren nuevas vías para crear y colaborar en manufactura y media. Este tipo de avances impulsan nuestra capacidad de innovar y transformar sectores clave.

revolver ocelot1 year ago

It's closer to whisk

Markus Malmros1 year ago

Sounds great, but is it actually any good?

Related Videos

Bytedance drops an open-source Gemini Omni!!! Bernini is a new AI video generation + editing framework. > Edit videos with text prompts > Image/video references > Code available

Bytedance drops an open-source Gemini Omni!!! Bernini is a new AI video generation + editing framework. > Edit videos with text prompts > Image/video references > Code available

⚡AI Search⚡

43,804 views • 1 month ago

"AI telephone" starts with an image -> GPT describes the image -> DALL-E makes an image from that description -> GPT describes the image -> DALL-E makes an image from that description, etc.... Experiment from my artist residency at OpenAI

"AI telephone" starts with an image -> GPT describes the image -> DALL-E makes an image from that description -> GPT describes the image -> DALL-E makes an image from that description, etc.... Experiment from my artist residency at OpenAI

Alexander Reben

39,228 views • 2 years ago

Playing with open-ended AI Agent behavior. Here's an AI Agent (claude code) making a self-portrait. It "evolves" the image by: writing code that generates image -> view image -> modify image -> view -> modify -> repeat.

Playing with open-ended AI Agent behavior. Here's an AI Agent (claude code) making a self-portrait. It "evolves" the image by: writing code that generates image -> view image -> modify image -> view -> modify -> repeat.

Max | Emergent Garden

22,851 views • 11 months ago

yet ANOTHER release from ByteDance just landed on the hub ✨HuMo✨ > video generation w/ multi-modal conditioning: audio, text & image > supports consistent subject preservation, synchronized audio-driven motion > based on Wan 2.1 & Whisper Large v3

yet ANOTHER release from ByteDance just landed on the hub ✨HuMo✨ > video generation w/ multi-modal conditioning: audio, text & image > supports consistent subject preservation, synchronized audio-driven motion > based on Wan 2.1 & Whisper Large v3

Linoy Tsaban🎗️

17,573 views • 10 months ago

first update of since the launch > presets now match your image sizes > move and scale on canvas > color or image as background > per-image durations > sound over the video

first update of since the launch > presets now match your image sizes > move and scale on canvas > color or image as background > per-image durations > sound over the video

Drice

16,307 views • 1 month ago

Higgsfield Mod for Minecraft is live. > prompt any building or city, even the Statue of Liberty > create paintings with text-to-image > snap a view and restyle it with image-to-image > make videos from a prompt with text-to-video. > animate in-game photos with image-to-video

Higgsfield Mod for Minecraft is live. > prompt any building or city, even the Statue of Liberty > create paintings with text-to-image > snap a view and restyle it with image-to-image > make videos from a prompt with text-to-video. > animate in-game photos with image-to-video

Higgsfield AI 🧩

457,102 views • 1 month ago

Just launched a free Midjourney Style Reference explorer tool with Kive > over 12k style codes and growing > search by vibe, color, theme & more > discover similar styles for any image > 3 curated boards (photos, illustrations, 3D) Link to join below

Just launched a free Midjourney Style Reference explorer tool with Kive > over 12k style codes and growing > search by vibe, color, theme & more > discover similar styles for any image > 3 curated boards (photos, illustrations, 3D) Link to join below

Nick St. Pierre

90,541 views • 1 year ago

Canva unveils MRT. Turns AI images into editable layers. > 20B diffusion model > Text-to-layers, image-to-layers, layers-to-layers > Trained on 10M+ designs > 8-step generation, 10-100x faster than Qwen-Image-Layered

Canva unveils MRT. Turns AI images into editable layers. > 20B diffusion model > Text-to-layers, image-to-layers, layers-to-layers > Trained on 10M+ designs > 8-step generation, 10-100x faster than Qwen-Image-Layered

⚡AI Search⚡

15,000 views • 1 month ago

We might have a new top open-source music generator. > Unified acoustic-token pipeline > Full-song generation > Text + lyric control for style, mood, vocals

We might have a new top open-source music generator. > Unified acoustic-token pipeline > Full-song generation > Text + lyric control for style, mood, vocals

⚡AI Search⚡

13,849 views • 2 months ago

Introducing OpenChatKit 🚀 - The first open-source alternative to ChatGPT! A team of ex-OpenAI fellows at Together have released a 20B chat-GPT model, fine-tuned for chat using EleutherAI's GPT-NeoX-20B, with over 43 million instructions under the Apache-2.0 license. >>>

Introducing OpenChatKit 🚀 - The first open-source alternative to ChatGPT! A team of ex-OpenAI fellows at Together have released a 20B chat-GPT model, fine-tuned for chat using EleutherAI's GPT-NeoX-20B, with over 43 million instructions under the Apache-2.0 license. >>>

Itamar Golan 🤓

555,498 views • 3 years ago

> bored at home > open higgsfield > you can start making an AI film > no setup, no studio > turn an idea into something real > submit it to their original series > win $ 150k in an AI contest > book a flight and disappear > live your best life for a while

> bored at home > open higgsfield > you can start making an AI film > no setup, no studio > turn an idea into something real > submit it to their original series > win $ 150k in an AI contest > book a flight and disappear > live your best life for a while

CG

80,396 views • 4 months ago

Claude + Higgsfield MCP = Unlimited DTC Ads #1 Playbook in 2026. > Open Claude > Drop your site and product image > Pick a format. Get a ready-to-run creative > 40 styles old tools couldn't handle autonomously > No broken text. Runs at scale.

Claude + Higgsfield MCP = Unlimited DTC Ads #1 Playbook in 2026. > Open Claude > Drop your site and product image > Pick a format. Get a ready-to-run creative > 40 styles old tools couldn't handle autonomously > No broken text. Runs at scale.

Higgsfield AI 🧩

163,955 views • 2 months ago

Excited to release: AgentUI > a fresh chat interface - natively multi-agent > agents coordinate via reports and figures > plug+play any open/closed model as sub-agent > agents specialise in code, web search, multimodal... Try it here:

Excited to release: AgentUI > a fresh chat interface - natively multi-agent > agents coordinate via reports and figures > plug+play any open/closed model as sub-agent > agents specialise in code, web search, multimodal... Try it here:

Leandro von Werra

41,065 views • 4 months ago

update on my recent workflow on Freepik Spaces > Midjourney 2D concepts > Nano Banana style transfer and editing > Nano Banana triptych or grid-based cinematic shots > Kling animation I really like this new workflow, it gives me much more control over my creations

update on my recent workflow on Freepik Spaces > Midjourney 2D concepts > Nano Banana style transfer and editing > Nano Banana triptych or grid-based cinematic shots > Kling animation I really like this new workflow, it gives me much more control over my creations

INK

39,143 views • 6 months ago

holy moly 🔥 Pusa 1.0 is a new image-to-video finetune based on Wan2.1-T2V-14B that surpasses Wan-I2V-14B and is: > 200x cheaper to train (only cost $500 🤯) > 5x faster inference > supports start-end frames, video extension and video completion

holy moly 🔥 Pusa 1.0 is a new image-to-video finetune based on Wan2.1-T2V-14B that surpasses Wan-I2V-14B and is: > 200x cheaper to train (only cost $500 🤯) > 5x faster inference > supports start-end frames, video extension and video completion

Dreaming Tulpa 🥓👑

15,688 views • 11 months ago

Open Fiesta BIGGEST Update V1.2 45+ Models Free to use (NO API KEY) 85+ Total Models >Free GPT-5, Claude 4, Grok 3 (No API key Needed) >UNLIMITED Image Gen >UNLIMITED Audio Gen (Until I go Bankrupt😭) Link in Comments

Open Fiesta BIGGEST Update V1.2 45+ Models Free to use (NO API KEY) 85+ Total Models >Free GPT-5, Claude 4, Grok 3 (No API key Needed) >UNLIMITED Image Gen >UNLIMITED Audio Gen (Until I go Bankrupt😭) Link in Comments

Humi

89,077 views • 10 months ago

i compared the top open-source OCR solutions and found which one works the best. featuring: > DeepSeek OCR > Datalab Chandra > Qwen3-VL > Dots OCR > Granite Docling also created an app that lets you run all of these OCR models in one place. 100% open-source.

i compared the top open-source OCR solutions and found which one works the best. featuring: > DeepSeek OCR > Datalab Chandra > Qwen3-VL > Dots OCR > Granite Docling also created an app that lets you run all of these OCR models in one place. 100% open-source.

Akshay 🚀

45,427 views • 6 months ago

🚨 Gemini 3.0 Flash > one shotted this trip on globe planner > super fast and to the point > i think this will be beast in gemini cli for faster and to the point coding

🚨 Gemini 3.0 Flash > one shotted this trip on globe planner > super fast and to the point > i think this will be beast in gemini cli for faster and to the point coding

Chetaslua

36,421 views • 9 months ago

only video you need to see what OpenAI released today at DevDay 2025! > apps sdk → build native apps inside ChatGPT > agentkit → openai’s version of n8n > chatkit, evals > more powerful codex > new models in the API → sora 2, gpt-5-pro

only video you need to see what OpenAI released today at DevDay 2025! > apps sdk → build native apps inside ChatGPT > agentkit → openai’s version of n8n > chatkit, evals > more powerful codex > new models in the API → sora 2, gpt-5-pro

Tushar Mehta

13,757 views • 9 months ago