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.

FLUX.2 is here - our most capable image generation & editing model to date. Multi-reference. 4MP. Production-ready. Open weights. Into the new.

Black Forest Labs

56,118 subscribers

485,193 views • 11 months ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

33 Comments

Black Forest Labs11 months ago

Read more here

Thomas Wolf11 months ago

Congrats folks! Nano-banana-like quality for a fraction of the price. Super impressive

merve11 months ago

find out how you can infer & train with diffusers here 🧨

Jaid11 months ago

You mean the best consistency available in any Flux model or the best consistency available in any model globally?

Mr Ash11 months ago

Nano Banana Pro you have competition from FLUX 2

apolinario (poli)11 months ago

Try it out on the @huggingface Spaces demo

Girl Lich 🏳️‍⚧️⚢💀11 months ago

Imagine releasing a model in late 2025 who fails the scorpion centaur test

Vincent Adultman11 months ago

Very very very bold claim in a world where Nano Banana Pro exists

Fernandes11 months ago

Is a goooood model

AustrianMyers11 months ago

Bei open weights hattet ihr mich.

Seth Saler11 months ago

My god. Has anyone checked on @patience_cave?

Lincoln 🇿🇦11 months ago

@altryne

Dreaming Tulpa 🥓👑11 months ago

congratulations on shipping 🔥

Emily11 months ago

Congratulations 🎉 🫶🫶🫶

Alex Barashkov11 months ago

Impressive work! Great job to the team!

Simon11 months ago

@ivanfioravanti Something of interest. The 32B dev model is open weights!

Simon11 months ago

@ComfyUI Will this get a standard template? ;-) (Non API - local gold)

Stephen11 months ago

🌲🌲

Sebastian Sch11 months ago

🤘🏻🤘🏻🤘🏻

mirror11 months ago

is it faster and have low vram usage than qwen?

VOID9 months ago

A tough challenger for @NanoBanana , the tests are really amazing!! Google needs to buckle up!

David Moosmann11 months ago

No Flux 2 Schnell? Urgh

sickbrain211 months ago

Cool!

AICU - つくる人をつくる11 months ago

Congrats! Here is Japanese review using ComfyUI!

Heather Cooper11 months ago

yesss

Todd Grilliot11 months ago

Amazing news. Most likely I'll start using this in my app ❤️

blankbrain11 months ago

not good enough . Cant even do , the fully filled whine glass

Afro Chuck11 months ago

@openingai_com Wow this is very impressive, how much more can we improve these things?

AmirMušić11 months ago

Now we talking 👀

zdhpeter11 months ago

nice work

Mathias_M11 months ago

Thx! Fantastic flexible model.

TrevorPillows11 months ago

Damn, while we’re chasing moon memes, you just dropped a 4MP beast. When’s the free demo, fam?

Antrunt11 months ago

4MP is a complete joke, 1440px lol

Related Videos

FLUX 3 Image Klein by Black Forest Labs is now natively supported in ComfyUI. 5.6B parameters, with open weights for both the base and distilled versions. → Native 4K generation → Bounding boxes for layout control → Multi-reference generation → Pixel perfect editing → Text rendering and editing Click the link in the comments to download the weights and learn more ⬇️

FLUX 3 Image Klein by Black Forest Labs is now natively supported in ComfyUI. 5.6B parameters, with open weights for both the base and distilled versions. → Native 4K generation → Bounding boxes for layout control → Multi-reference generation → Pixel perfect editing → Text rendering and editing Click the link in the comments to download the weights and learn more ⬇️

ComfyUI

19,554 views • 12 days ago

gpt-image-2 is here, available today in the API and Codex. The most capable image generation model yet, built for production-grade workflows with stronger text rendering, layout, editing, resolution, and multilingual rendering.

gpt-image-2 is here, available today in the API and Codex. The most capable image generation model yet, built for production-grade workflows with stronger text rendering, layout, editing, resolution, and multilingual rendering.

OpenAI Developers

182,216 views • 6 months ago

Flux.2 Max is out NOW 💥 UNLIMITED for 1 month for Premium+ and Pro users The highest-quality and most consistent FLUX.2 model Built for maximum prompt adherence, multi-reference consistency, and production-ready editing at blazing speed Available for all users

Flux.2 Max is out NOW 💥 UNLIMITED for 1 month for Premium+ and Pro users The highest-quality and most consistent FLUX.2 model Built for maximum prompt adherence, multi-reference consistency, and production-ready editing at blazing speed Available for all users

Magnific

24,333 views • 10 months ago

Introducing Nano Banana Pro (Gemini 3 Pro Image), our new state-of-the-art image generation and editing model from Google DeepMind. It improves on the original model while adding new advanced capabilities, enhanced world knowledge and text rendering, allowing you to create and edit studio-quality, production-ready visuals.

Introducing Nano Banana Pro (Gemini 3 Pro Image), our new state-of-the-art image generation and editing model from Google DeepMind. It improves on the original model while adding new advanced capabilities, enhanced world knowledge and text rendering, allowing you to create and edit studio-quality, production-ready visuals.

Google

1,899,020 views • 11 months ago

Qwen-Image-2.1 is now supported in ComfyUI! Open weights. One 7B checkpoint that generates and edits. → Image generation at native 2K → Instruction editing from up to 10 reference images in a single pass → RGBA output, alpha included

Qwen-Image-2.1 is now supported in ComfyUI! Open weights. One 7B checkpoint that generates and edits. → Image generation at native 2K → Instruction editing from up to 10 reference images in a single pass → RGBA output, alpha included

ComfyUI

197,543 views • 1 month ago

FLUX.2 Is Live - FREE for 1 WEEK on ImagineArt Unlimited generations. Zero limits. 4MP output, HEX color precision, deep consistency via multi-reference, and creative control with JSON prompting. RT + Comment “ImagineArt x FLUX.2” to get an exclusive prompt guide in DMs.

FLUX.2 Is Live - FREE for 1 WEEK on ImagineArt Unlimited generations. Zero limits. 4MP output, HEX color precision, deep consistency via multi-reference, and creative control with JSON prompting. RT + Comment “ImagineArt x FLUX.2” to get an exclusive prompt guide in DMs.

ImagineArt

937,016 views • 11 months ago

Krea 2 Open-Source is now available on fal The most aesthetic open-source image model, released with open weights Turbo delivers fast, polished text-to-image at low step counts RAW serves as the malleable base checkpoint for LoRA training

Krea 2 Open-Source is now available on fal The most aesthetic open-source image model, released with open weights Turbo delivers fast, polished text-to-image at low step counts RAW serves as the malleable base checkpoint for LoRA training

fal

48,244 views • 4 months ago

New open source image model called Mage-Flow by Microsoft. > Supports image generation and editing. > Lightweight 4B model with 4-step turbo variants. > Free and open-source, MIT license.

New open source image model called Mage-Flow by Microsoft. > Supports image generation and editing. > Lightweight 4B model with 4-step turbo variants. > Free and open-source, MIT license.

AI Search

14,705 views • 3 months ago

FLUX.3 Image Klein 6B just dropped on Hugging Face 🔥 Base and distilled (16 steps), multi-reference editing, JSON bounding-box layouts play with it 👇

FLUX.3 Image Klein 6B just dropped on Hugging Face 🔥 Base and distilled (16 steps), multi-reference editing, JSON bounding-box layouts play with it 👇

Hugging Apps

15,594 views • 12 days ago

Q2 Reference-to-Video Pro is available now! Reference Anything. Create Everything. 🎉The world’s first video model where anything can be a reference Fully upgraded reference editing: multi-reference support with 2 videos + 4 images 6 video reference types: character, scene, effects, expressions, actions, and textures Flexible video editing: add, remove, modify Built for real production workflows: fast edits and revisions for film, short drama, and animation 🎁New User Bonus Code：YESVIDU

Q2 Reference-to-Video Pro is available now! Reference Anything. Create Everything. 🎉The world’s first video model where anything can be a reference Fully upgraded reference editing: multi-reference support with 2 videos + 4 images 6 video reference types: character, scene, effects, expressions, actions, and textures Flexible video editing: add, remove, modify Built for real production workflows: fast edits and revisions for film, short drama, and animation 🎁New User Bonus Code：YESVIDU

Vidu AI

73,220 views • 9 months ago

Bria Fibo 2.0 from BRIA AI is live on fal. The #1 open-weight image editing model on Artificial Analysis, with text-to-image generation and targeted editing. Trained only on licensed data, with clear commercial rights. - Image editing with up to four input images - Background swaps, product restaging and lighting changes - Text-to-image generation for reasoning-heavy prompts

Bria Fibo 2.0 from BRIA AI is live on fal. The #1 open-weight image editing model on Artificial Analysis, with text-to-image generation and targeted editing. Trained only on licensed data, with clear commercial rights. - Image editing with up to four input images - Background swaps, product restaging and lighting changes - Text-to-image generation for reasoning-heavy prompts

fal

15,730 views • 7 days ago

Introducing LTX-2.3 Our most production-ready model yet. The fastest 4K video generation in the world with built-in native dialogue. Here’s what’s new 🧵 1/9

Introducing LTX-2.3 Our most production-ready model yet. The fastest 4K video generation in the world with built-in native dialogue. Here’s what’s new 🧵 1/9

LTX Studio

678,210 views • 7 months ago

FLUX 3 Video is #2 in the world. To celebrate, FLUX 3 Video is free to use in our playground until Sunday 16th, 11:59pm PT (link in the thread). This is just the beginning of what’s coming. Up next: 4K, video editing, and multiple images & videos as reference input.

FLUX 3 Video is #2 in the world. To celebrate, FLUX 3 Video is free to use in our playground until Sunday 16th, 11:59pm PT (link in the thread). This is just the beginning of what’s coming. Up next: 4K, video editing, and multiple images & videos as reference input.

Black Forest Labs

408,740 views • 2 months ago

🚨FLUX.1 Kontext [dev], the open image editing model, is now available at fal with training capabilities! ✨4x faster inference (2s vs 7s) 💰 Ultra-affordable at $0.025/megapixel 🔧 Full LoRA training support 🖌️Game-changing image editing capabilities

🚨FLUX.1 Kontext [dev], the open image editing model, is now available at fal with training capabilities! ✨4x faster inference (2s vs 7s) 💰 Ultra-affordable at $0.025/megapixel 🔧 Full LoRA training support 🖌️Game-changing image editing capabilities

fal

161,022 views • 1 year ago

We've officially released and open-sourced HunyuanImage 2.1, our latest text-to-image model. The new model delivers on our commitment to balancing performance and quality. With native 2K image generation, HunyuanImage 2.1 is an advanced open-source text-to-image model.🎨 ✨ New in 2.1: 🔹Advanced Semantics: Supports ultra-long and complex prompts of up to 1000 tokens, and precisely controls the generation of multiple subjects in a single image. 🔹Precise Chinese and English Text Rendering with seamless image–text integration: The model naturally integrates text into images, making it suitable for a wide range of applications such as product covers, illustrations, and poster design to meet the needs of various fields. 🔹Rich Styles and High Aesthetic: Capable of generating images in various styles—including photorealistic portraits, comics, and vinyl figures—it delivers outstanding visual appeal and artistic quality. 🔹High-Quality Generation: Efficiently produces ultra-high-definition (2K) images in the same time other models take to generate a 1K image. HunyuanImage 2.1 uses two text encoders: a multimodal large language model (MLLM) to improve the model's image and text alignment capabilities, and a multi-language character-aware encoder to improve text rendering capabilities. The model is a single- and double-stream diffusion transformer with 17B parameters. We've also open-sourced the weights of the the accelerated version with meanflow which reduces inference steps from 100 to just 8, and PromptEnhancer, the first industrial-grade rewriting model that enhances your prompts for more nuanced and expressive image generation. Now, creators turn complex ideas—like posters with slogans or multi-panel comics—into visuals faster than ever. We’re just getting started. Stay tuned for our native multimodal image generation model coming soon. 🌐Website: 🔗Github: 🤗Hugging Face: ✨Hugging Face Demo:

We've officially released and open-sourced HunyuanImage 2.1, our latest text-to-image model. The new model delivers on our commitment to balancing performance and quality. With native 2K image generation, HunyuanImage 2.1 is an advanced open-source text-to-image model.🎨 ✨ New in 2.1: 🔹Advanced Semantics: Supports ultra-long and complex prompts of up to 1000 tokens, and precisely controls the generation of multiple subjects in a single image. 🔹Precise Chinese and English Text Rendering with seamless image–text integration: The model naturally integrates text into images, making it suitable for a wide range of applications such as product covers, illustrations, and poster design to meet the needs of various fields. 🔹Rich Styles and High Aesthetic: Capable of generating images in various styles—including photorealistic portraits, comics, and vinyl figures—it delivers outstanding visual appeal and artistic quality. 🔹High-Quality Generation: Efficiently produces ultra-high-definition (2K) images in the same time other models take to generate a 1K image. HunyuanImage 2.1 uses two text encoders: a multimodal large language model (MLLM) to improve the model's image and text alignment capabilities, and a multi-language character-aware encoder to improve text rendering capabilities. The model is a single- and double-stream diffusion transformer with 17B parameters. We've also open-sourced the weights of the the accelerated version with meanflow which reduces inference steps from 100 to just 8, and PromptEnhancer, the first industrial-grade rewriting model that enhances your prompts for more nuanced and expressive image generation. Now, creators turn complex ideas—like posters with slogans or multi-panel comics—into visuals faster than ever. We’re just getting started. Stay tuned for our native multimodal image generation model coming soon. 🌐Website: 🔗Github: 🤗Hugging Face: ✨Hugging Face Demo:

Tencent Hy

89,430 views • 1 year ago

New text and image to video generation AI model Open-Sora-Plan-v1.3.0

New text and image to video generation AI model Open-Sora-Plan-v1.3.0

AK

51,843 views • 2 years ago

Qwen Image 2.1 is here! 🖼️ A 7B params native image generation and editing model, with up to 10 image references The model comes with it's own prompt enhancement LLMs, integrated with diffusers 🧨 and ComfyUI ▶️ on Spaces

Qwen Image 2.1 is here! 🖼️ A 7B params native image generation and editing model, with up to 10 image references The model comes with it's own prompt enhancement LLMs, integrated with diffusers 🧨 and ComfyUI ▶️ on Spaces

Hugging Apps

92,135 views • 1 month ago

FLUX.2 is LIVE on Higgsfield. Our 65% Black Friday lineup expands with the best open-source image model. Fully unrestricted, uncensored & FREE. ALL image models UNLIMITED for 1 year! Two days left to lock this in 🔥 For 9 hours: comment&retweet&like for 240 FREE credits

FLUX.2 is LIVE on Higgsfield. Our 65% Black Friday lineup expands with the best open-source image model. Fully unrestricted, uncensored & FREE. ALL image models UNLIMITED for 1 year! Two days left to lock this in 🔥 For 9 hours: comment&retweet&like for 240 FREE credits

Higgsfield AI 🧩

1,097,050 views • 11 months ago