Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

Seedream v4.5 is HERE! ByteDance’s new-generation image creation model that combines image generation + image editing in one unified architecture. Cleaner text, sharper details, smarter edits, all in a single model. Pair it with ImagineArt’s 71% OFF Cyber Monday deal + give access to 40 creators on your plan.... show more

ImagineArt

22,853 subscribers

535,008 просмотров • 9 месяцев назад •via X (Twitter)

Искусство Здоровье и велнес Наука и технологии

Anya Rossi• Live Now

Private livecam show

Комментарии: 40

Фото профиля ImagineArt

ImagineArt9 месяцев назад

Try Seedream v4.5 now 🚀

Фото профиля BMX

BMX9 месяцев назад

Yes Seedream v4.5 is fire, thanks Imagine Art.

Фото профиля ImagineArt

ImagineArt9 месяцев назад

@babymemexx Can't wait to see what else you create

Фото профиля Mrspickles

Mrspickles9 месяцев назад

So now it generates AND edits? Great, just waiting for the model that does my emails AND excuses me from meetings 😎💻

Фото профиля ImagineArt

ImagineArt9 месяцев назад

✍️ Writing that down Maybe we'll add it in our upcoming model 👀

Фото профиля TechyTricksAI

TechyTricksAI9 месяцев назад

ImagineArt Seedream

Фото профиля Angry Tom

Angry Tom9 месяцев назад

huge!

Фото профиля Nimentrix

Nimentrix9 месяцев назад

ImagineArt Seedream 4.5 I was waiting for... 😍

Фото профиля ImagineArt

ImagineArt9 месяцев назад

The wait is over now!

Фото профиля Altamash007🧡

Altamash007🧡9 месяцев назад

Seedream 4.5 looks like a major upgrade cleaner text sharper details and smarter edits in one unified model Excited to explore how this new architecture improves image generation and editing on ImagineArt

Фото профиля ImagineArt

ImagineArt9 месяцев назад

Can’t wait to see it in action—bring on your best creations and tag us!

Фото профиля Altamash007🧡

Altamash007🧡9 месяцев назад

Thanks so much I'm really excited to create with ImagineArt If my Creator Program application gets approved I’ll be able to produce consistent high-quality cinematic content using Seedream and Kling the kind of storytelling no one has seen before Really hoping to join the program soon so I can start delivering my best work and tag ImagineArt with every release!

Фото профиля Alejandro Martinez | IA

Alejandro Martinez | IA9 месяцев назад

ImagineArt Seedream

Фото профиля ImagineArt

ImagineArt9 месяцев назад

Your credits are waiting for you 🫡

Фото профиля Heisenberg

Heisenberg9 месяцев назад

ImagineArt Seedream

Фото профиля Hakan Çeliker

Hakan Çeliker9 месяцев назад

ImagineArt Seedream looks very very insane

Фото профиля ImagineArt

ImagineArt9 месяцев назад

Your credits are in your DMs 🚀

Фото профиля Lost 🎯

Lost 🎯9 месяцев назад

Have to check that 👀

Фото профиля ImagineArt

ImagineArt9 месяцев назад

Head on over to :)

Фото профиля DrSadek 🪶

DrSadek 🪶9 месяцев назад

Niiiiiiiiiiiiiiiiiiiiiiiiiice

Фото профиля Kashif Nadeem

Kashif Nadeem9 месяцев назад

Seedream v4.5 is here ByteDance’s latest model combines image generation and editing cleaner text, sharper details, smarter edits, all in one

Фото профиля Vipin Gautam (Viipin I Gautam)

Vipin Gautam (Viipin I Gautam)9 месяцев назад

ImagineArt Seedream

Фото профиля Dmitry

Dmitry9 месяцев назад

ImagineArt Seedream

Фото профиля Weinberg

Weinberg9 месяцев назад

ImagineArt Seedream

Фото профиля 𝕄𝕒𝕪𝕒𝕟𝕜 🎧

𝕄𝕒𝕪𝕒𝕟𝕜 🎧9 месяцев назад

ImagineArt Seedream

Фото профиля AI Girl

AI Girl9 месяцев назад

ImagineArt seedream

Фото профиля Pablo Evans

Pablo Evans9 месяцев назад

ImagineArt Seedream

Фото профиля Naggibator Tazov

Naggibator Tazov9 месяцев назад

ImagineArt Seedream

Фото профиля D-Coder

D-Coder9 месяцев назад

ImagineArt Seedream

Фото профиля ADRIAN | PROFESOR IA

ADRIAN | PROFESOR IA9 месяцев назад

ImagineArt Seedream

Фото профиля AI Builder

AI Builder9 месяцев назад

ImagineArt seedream

Фото профиля Tamsome

Tamsome9 месяцев назад

ImagineArt Seedream

Фото профиля Antonio Costa | IA

Antonio Costa | IA9 месяцев назад

ImagineArt Seedream

Фото профиля Kevin Faircloth

Kevin Faircloth9 месяцев назад

Hey @jimcramer it’s Wednesday and yet another choking point for OAI has dropped. Market share say what!

Фото профиля Nao

Nao9 месяцев назад

ImagineArt Seedream

Фото профиля Promethean

Promethean9 месяцев назад

ImagineArt Seedream

Фото профиля 👁️עין_תחת_עין👁️

👁️עין_תחת_עין👁️9 месяцев назад

ImagineArt Seedream

Фото профиля Matheus | IA

Matheus | IA9 месяцев назад

ImagineArt Seedream

Фото профиля Dipti Sharma

Dipti Sharma9 месяцев назад

ImagineArt Seedream

Фото профиля Arsalan

Arsalan9 месяцев назад

ImagineArt Seedream

Похожие видео

We have updated image generation models with Nano Banana, Qwen-image, and Seedream 4.0, now enabling direct image-to-video creation. Up to 4k images generation. Stremline your workflow! -> Retweet to get 300 credits in DMs (72H ONLY)

We have updated image generation models with Nano Banana, Qwen-image, and Seedream 4.0, now enabling direct image-to-video creation. Up to 4k images generation. Stremline your workflow! -> Retweet to get 300 credits in DMs (72H ONLY)

PixVerse

76,804 просмотров • 11 месяцев назад

Dreamina AI has officially launched Seedream 3.0 – its cutting-edge new model. The wait is over！ This is the latest breakthrough in AI image generation. With Seedream 3.0, Dreamina AI delivers: 🎬 Cinematic-quality visuals 🖼️ 2K resolution output 💎 Ultra-realistic textures & materials 🔠 Precise, clean typography 📝 Accurate English text generation ability This isn’t just text-to-image — it’s next-level visual storytelling. 🚀 Try it here: Let your vision flow. ✨ #dreaminaai #seedream #TextToImage #AIArt #GenerativeAI #AImodels

Dreamina AI has officially launched Seedream 3.0 – its cutting-edge new model. The wait is over！ This is the latest breakthrough in AI image generation. With Seedream 3.0, Dreamina AI delivers: 🎬 Cinematic-quality visuals 🖼️ 2K resolution output 💎 Ultra-realistic textures & materials 🔠 Precise, clean typography 📝 Accurate English text generation ability This isn’t just text-to-image — it’s next-level visual storytelling. 🚀 Try it here: Let your vision flow. ✨ #dreaminaai #seedream #TextToImage #AIArt #GenerativeAI #AImodels

Dreamina AI

41,293 просмотров • 1 год назад

The first truly open-source audio-video model. LTX-2 is a DiT-based foundation model with all core video generation capabilities in one unified model. Designed to run locally on consumer GPUs. - text-to-video - image-to-video - and video-to-video modes 100% open-source.

The first truly open-source audio-video model. LTX-2 is a DiT-based foundation model with all core video generation capabilities in one unified model. Designed to run locally on consumer GPUs. - text-to-video - image-to-video - and video-to-video modes 100% open-source.

Akshay 🚀

66,197 просмотров • 8 месяцев назад

Nano Banana Pro is LIVE in Hedra DAY 0! This is the most advanced model for creators. Clear text generation. Multi-image blending. Natural-language lighting. 100% Character consistency. We're giving you 2,500 credits to try it. 12 HOURS ONLY: Follow + RT + reply "Nano Banana Pro" for 2,500 credits in DM.

Nano Banana Pro is LIVE in Hedra DAY 0! This is the most advanced model for creators. Clear text generation. Multi-image blending. Natural-language lighting. 100% Character consistency. We're giving you 2,500 credits to try it. 12 HOURS ONLY: Follow + RT + reply "Nano Banana Pro" for 2,500 credits in DM.

Hedra

400,539 просмотров • 10 месяцев назад

Introducing SDXL Turbo: A real-time text-to-image generation model. SDXL Turbo achieves state-of-the-art performance with a new distillation technology, enabling single-step image generation with unprecedented quality, reducing the required step count from 50 to just one. The code, research paper, and weights for non-commercial use are now available on our website. You can test SDXL Turbo on Stability AI’s image editing platform Clipdrop, with a beta demonstration of the real-time text-to-image generation capabilities. Learn more:

Introducing SDXL Turbo: A real-time text-to-image generation model. SDXL Turbo achieves state-of-the-art performance with a new distillation technology, enabling single-step image generation with unprecedented quality, reducing the required step count from 50 to just one. The code, research paper, and weights for non-commercial use are now available on our website. You can test SDXL Turbo on Stability AI’s image editing platform Clipdrop, with a beta demonstration of the real-time text-to-image generation capabilities. Learn more:

Stability AI

976,940 просмотров • 2 лет назад

Introducing Omni, one unified model can support any-to-any multimodal modeling, including multimodal understanding, image/video generation and editing, world modeling and 3D reconstruction. All in one that adopts standard mixture-of-experts arch with only 3B activations.

Introducing Omni, one unified model can support any-to-any multimodal modeling, including multimodal understanding, image/video generation and editing, world modeling and 3D reconstruction. All in one that adopts standard mixture-of-experts arch with only 3B activations.

Ceyuan Yang

32,674 просмотров • 5 месяцев назад

Pollo Chat is LIVE NOW! Create instantly from ANY page. One unified chat window for all your Image & Video generation needs. 24H Only :Follow + RT + Reply "PolloChat" = 222 FREE Credits ! To prevent bot farming, we only issue credits to X accounts with a profile photo.

Pollo AI

125,489 просмотров • 8 месяцев назад

Now enjoy PIXVERSE v5.5 - the video generation engine built for creators who move fast. Text → video. Image → video. All in stunning, high-quality motion with native audio baked in. Retweet + reply + like + follow and 500 credits will be given to 5 people from comments!

Now enjoy PIXVERSE v5.5 - the video generation engine built for creators who move fast. Text → video. Image → video. All in stunning, high-quality motion with native audio baked in. Retweet + reply + like + follow and 500 credits will be given to 5 people from comments!

ImagineArt

423,753 просмотров • 9 месяцев назад

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

89,392 просмотров • 1 год назад

INTRODUCING: Seedream 5.0 Lite — the next generation of AI image creation is here. 🚀✨ Describe the vibe, reference a sketch, throw in a few images and a wild brief — Seedream 5.0 Lite figures out the rest. Built to understand structure, layout, and complex design intent, it delivers predictable, high-fidelity results you can actually rely on. The power to create with precision and control is now in your hands. 🎨 🔗 Try Seedream 5.0 Lite via ModelArk API today: 📖 Read more about Seedream 5.0 Lite: #Seedream #BytePlus #ByteDance #GenerativeAI

INTRODUCING: Seedream 5.0 Lite — the next generation of AI image creation is here. 🚀✨ Describe the vibe, reference a sketch, throw in a few images and a wild brief — Seedream 5.0 Lite figures out the rest. Built to understand structure, layout, and complex design intent, it delivers predictable, high-fidelity results you can actually rely on. The power to create with precision and control is now in your hands. 🎨 🔗 Try Seedream 5.0 Lite via ModelArk API today: 📖 Read more about Seedream 5.0 Lite: #Seedream #BytePlus #ByteDance #GenerativeAI

BytePlus

76,855 просмотров • 7 месяцев назад

Qwen‑Image‑2.0 continues to push what’s possible in next‑gen image generation. From pro typography rendering and stronger semantic adherence to improved text rendering and a lighter model architecture, it keeps delivering creative power with ease ✨ Check out the demos to discover more!

Qwen‑Image‑2.0 continues to push what’s possible in next‑gen image generation. From pro typography rendering and stronger semantic adherence to improved text rendering and a lighter model architecture, it keeps delivering creative power with ease ✨ Check out the demos to discover more!

Alibaba Group

3,302,434 просмотров • 6 месяцев назад

TurboEdit Instant text-based image editing discuss: We address the challenges of precise image inversion and disentangled image editing in the context of few-step diffusion models. We introduce an encoder based iterative inversion technique. The inversion network is conditioned on the input image and the reconstructed image from the previous step, allowing for correction of the next reconstruction towards the input image. We demonstrate that disentangled controls can be easily achieved in the few-step diffusion model by conditioning on an (automatically generated) detailed text prompt. To manipulate the inverted image, we freeze the noise maps and modify one attribute in the text prompt (either manually or via instruction based editing driven by an LLM), resulting in the generation of a new image similar to the input image with only one attribute changed. It can further control the editing strength and accept instructive text prompt. Our approach facilitates realistic text-guided image edits in real-time, requiring only 8 number of functional evaluations (NFEs) in inversion (one-time cost) and 4 NFEs per edit. Our method is not only fast, but also significantly outperforms state-of-the-art multi-step diffusion editing techniques.

TurboEdit Instant text-based image editing discuss: We address the challenges of precise image inversion and disentangled image editing in the context of few-step diffusion models. We introduce an encoder based iterative inversion technique. The inversion network is conditioned on the input image and the reconstructed image from the previous step, allowing for correction of the next reconstruction towards the input image. We demonstrate that disentangled controls can be easily achieved in the few-step diffusion model by conditioning on an (automatically generated) detailed text prompt. To manipulate the inverted image, we freeze the noise maps and modify one attribute in the text prompt (either manually or via instruction based editing driven by an LLM), resulting in the generation of a new image similar to the input image with only one attribute changed. It can further control the editing strength and accept instructive text prompt. Our approach facilitates realistic text-guided image edits in real-time, requiring only 8 number of functional evaluations (NFEs) in inversion (one-time cost) and 4 NFEs per edit. Our method is not only fast, but also significantly outperforms state-of-the-art multi-step diffusion editing techniques.

AK

16,062 просмотров • 2 лет назад

🚨🍌Big Reveal: who was "Nano Banana?" The anonymous model, “nano-banana,” that caught the world's attention with its ability to follow complex instructions, preserve character identity, and maintain contextual details was: Gemini-2.5-Flash-Image-Preview by Google DeepMind 🍌✨ - Now ranked #1 on the Image Edit Arena - Also ranked #1 for Text-to-Image In two weeks, “nano-banana” has driven over 5 million votes to the Image Edit Arena. With 2.5M+ votes for this model, it is the highest number of votes any model has received, with the largest Elo score lead (171) in Arena history. Congrats to the Google DeepMind team on this incredible milestone in image edit and generation. 👏

🚨🍌Big Reveal: who was "Nano Banana?" The anonymous model, “nano-banana,” that caught the world's attention with its ability to follow complex instructions, preserve character identity, and maintain contextual details was: Gemini-2.5-Flash-Image-Preview by Google DeepMind 🍌✨ - Now ranked #1 on the Image Edit Arena - Also ranked #1 for Text-to-Image In two weeks, “nano-banana” has driven over 5 million votes to the Image Edit Arena. With 2.5M+ votes for this model, it is the highest number of votes any model has received, with the largest Elo score lead (171) in Arena history. Congrats to the Google DeepMind team on this incredible milestone in image edit and generation. 👏

Arena.ai

106,535 просмотров • 1 год назад

We’re excited to announce the release and open-source of HunyuanImage 3.0 — the largest and most powerful open-source text-to-image model to date, with over 80 billion total parameters, of which 13 billion are activated per token during inference.The effect is completely comparable to the industry’s flagship closed-source model.🚀🚀🚀 HunyuanImage 3.0 originates from our internally developed native multimodal large language model, with fine-tuning and post-training focused on text-to-image generation. This unique foundation gives the model a powerful set of capabilities: ✅Reason with world knowledge ✅Understand complex, thousand-word prompts ✅Generate precise text within images Different from traditional DiT architecture image generation models, HunyuanImage 3.0’s MoE architecture uses a Transfusion-based approach to deeply couple Diffusion and LLM training for a single, powerful system. Built on Hunyuan-A13B, HunyuanImage 3.0 was trained on a massive dataset: 5 billion image-text pairs, video frames, interleaved image-text data, and 6 trillion tokens of text corpora. This hybrid training across multimodal generation, understanding, and LLM capabilities allows the model to seamlessly integrate multiple tasks. Whether you're an illustrator, designer, or creator, this is built to slash your workflow from hours to minutes. HunyuanImage 3.0 can generate intricate text, detailed comics, expressive emojis, and lively, engaging illustrations for educational content. The current release focuses solely on text-to-image generation and future updates will include image-to-image, image editing, multi-turn interaction, and more. 👉🏻Try it now: 🔗GitHub: 🤗Hugging Face:

We’re excited to announce the release and open-source of HunyuanImage 3.0 — the largest and most powerful open-source text-to-image model to date, with over 80 billion total parameters, of which 13 billion are activated per token during inference.The effect is completely comparable to the industry’s flagship closed-source model.🚀🚀🚀 HunyuanImage 3.0 originates from our internally developed native multimodal large language model, with fine-tuning and post-training focused on text-to-image generation. This unique foundation gives the model a powerful set of capabilities: ✅Reason with world knowledge ✅Understand complex, thousand-word prompts ✅Generate precise text within images Different from traditional DiT architecture image generation models, HunyuanImage 3.0’s MoE architecture uses a Transfusion-based approach to deeply couple Diffusion and LLM training for a single, powerful system. Built on Hunyuan-A13B, HunyuanImage 3.0 was trained on a massive dataset: 5 billion image-text pairs, video frames, interleaved image-text data, and 6 trillion tokens of text corpora. This hybrid training across multimodal generation, understanding, and LLM capabilities allows the model to seamlessly integrate multiple tasks. Whether you're an illustrator, designer, or creator, this is built to slash your workflow from hours to minutes. HunyuanImage 3.0 can generate intricate text, detailed comics, expressive emojis, and lively, engaging illustrations for educational content. The current release focuses solely on text-to-image generation and future updates will include image-to-image, image editing, multi-turn interaction, and more. 👉🏻Try it now: 🔗GitHub: 🤗Hugging Face:

Tencent Hy

413,096 просмотров • 1 год назад

UI design is underrated for AI. Sometimes they go hand in hand with new model capabilities in delightful ways. Here's a very clever demo: you can use rich text (bold, font style, color) to assign different types of weights to each token, making image generation controllable in a highly intuitive & flexible fashion. Paper: Expressive Text-to-Image Generation with Rich Text HuggingFace demo: Authors: Songwei Ge, Taesung Park, Jun-Yan Zhu, Jia-Bin Huang

UI design is underrated for AI. Sometimes they go hand in hand with new model capabilities in delightful ways. Here's a very clever demo: you can use rich text (bold, font style, color) to assign different types of weights to each token, making image generation controllable in a highly intuitive & flexible fashion. Paper: Expressive Text-to-Image Generation with Rich Text HuggingFace demo: Authors: Songwei Ge, Taesung Park, Jun-Yan Zhu, Jia-Bin Huang

Jim Fan

146,921 просмотров • 3 лет назад

FLUX 3 Video is live in ComfyUI via Partner Nodes Black Forest Labs FLUX 3 Model highlights: → 20s in a single generation → native audio, not dubbed on after → text-to-video, image-to-video, keyframes, continuation → multi-scene and multi-angle in one prompt → multilingual dialogue with lipsync that holds → typography that sits in the scene → chain clips agentically for longer stories One model across video, audio, image, and action. Click the link below to download the workflows and learn more with blog

FLUX 3 Video is live in ComfyUI via Partner Nodes Black Forest Labs FLUX 3 Model highlights: → 20s in a single generation → native audio, not dubbed on after → text-to-video, image-to-video, keyframes, continuation → multi-scene and multi-angle in one prompt → multilingual dialogue with lipsync that holds → typography that sits in the scene → chain clips agentically for longer stories One model across video, audio, image, and action. Click the link below to download the workflows and learn more with blog

ComfyUI

25,715 просмотров • 1 месяц назад

Big News! Meta just released Segment Anything, a new AI model that can "cut out" any object, in any image/video, with a single click. The model is designed and trained to be promptable, so it can transfer zero-shot to new image distributions and tasks.

Big News! Meta just released Segment Anything, a new AI model that can "cut out" any object, in any image/video, with a single click. The model is designed and trained to be promptable, so it can transfer zero-shot to new image distributions and tasks.

Lior Alexander

290,330 просмотров • 3 лет назад

UNLIMITED Kling O1 Video & Video Edit is LIVE! 💥 70% OFF. Exclusively on Higgsfield. Day 0 access by default. First EVER unified video model - generate, edit, restyle & extend in one engine. Up to 7 image refs, 2K resolution, 3-10s clips. For 12 hours: retweet & reply & follow & like for FREE 276 credits

UNLIMITED Kling O1 Video & Video Edit is LIVE! 💥 70% OFF. Exclusively on Higgsfield. Day 0 access by default. First EVER unified video model - generate, edit, restyle & extend in one engine. Up to 7 image refs, 2K resolution, 3-10s clips. For 12 hours: retweet & reply & follow & like for FREE 276 credits

Higgsfield AI 🧩

804,379 просмотров • 9 месяцев назад