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.

Today, we introduce HunyuanImage 3.0-Instruct, a native multimodal model focusing on image-editing by integrating visual understanding with precise image synthesis! 🚀 It understands input images and reasons before generating images. Built on an 80B-parameter MoE architecture (13B activated), it natively unifies deep multimodal comprehension and high-fidelity generation. 🧠 A... "Thinking" Model with Native CoT & MixGRPO: The model doesn’t just execute commands, it processes them through a Native Chain-of-Thought (CoT) schema. Enhanced by our self-developed MixGRPO algorithm, it reasons through complex instructions to achieve flawless intent alignment and human-preference consistency. 🎨 Precise Editing & Multi-Image Fusion: The model enables accurate image editing by adding, removing, or modifying elements while keeping non-target areas perfectly intact. It also excels at seamless multi-image fusion, synthesizing complex scenes by extracting and blending elements from multiple sources into a unified, consistent output. 🏆 SOTA Performance: HunyuanImage 3.0-Instruct sets a new benchmark in visual quality and alignment, delivering performance that matches leading proprietary models. We aim to enable the community to explore new ideas with a state-of-the-art foundation model, fostering a dynamic and vibrant image generation ecosystem. 🛠️🎨 💻Try it at (PC only):show more

Tencent Hy

57,573 subscribers

127,120 views • 9 months ago •via X (Twitter)

Arts Education Science & Technology

Anya Rossi• Live Now

Private livecam show

34 Comments

Antonio Bustamante9 months ago

Nice! Any plans to open-source?

Bone-Studio9 months ago

Sadly as long as you don’t change your open source license to allow EU, UK and South Korea, this pass as nothing interesting, even when the tech behind is amazing I’m sure But your license makes it useless for a pretty big part of the world. Embrace real Apache 2.0 or MIT please

Tencent AI9 months ago

HunyuanImage 3.0-Instruct's img-to-img is solid! High output consistency, realism & vibe. Much faster now.

Curious Circuit9 months ago

Please open source this

Nid All | AI art and more 🤖9 months ago

The model is super cool and hyper-consistent.

fanfan9 months ago

amazing realism

Aaliya9 months ago

This is impressive. The multi-image fusion part sounds especially powerful. Excited to try it out.

polihedge9 months ago

Whoa

Salah Alden9 months ago

Amazing

Yupp9 months ago

Big congrats! We have HunyuanImage 3 Instruct available on Yupp, ready to prompt along with hundreds of other top AIs. Looking forward to seeing how it performs on our user-preference leaderboard! 📊

NGLPRZ9 months ago

🔥🔥

Researcher9 months ago

@grok is it open source?

Sebastian Buzdugan9 months ago

80b moe for editing is super interesting

rizu9 months ago

Data farmer 2000

Chair9 months ago

what does "PC-only" mean

Kaizenus Imperium9 months ago

Does this model understand english well as madarin ?

ikan laut9 months ago

very amazing, I am very impressed with this achievement

Fahd Mirza9 months ago

💥 HunyuanImage 3.0-Instruct Just Dropped 🌀 ♠ but there's a licensing catch that's killing the hype 🚨 🔹 80B-A13B MoE architecture 🔹 Native Chain-of-Thought reasoning 🔹 Multi-image fusion + precise editing 🔹 Thinks before it generates ⚠️ Problem: Not Open-Weight 🔥 Full demo + breakdown here:

Saïd Aitmbarek9 months ago

based

Himanshu Kumar9 months ago

@TencentHunyuan, HY, the MoE architecture is an interesting choice for this multimodal model.

darthsider9 months ago

@ComfyUI when?

Michael Wirth9 months ago

Congratulations on the new model! 🚀 Are there any benchmarks out yet? 📊

Fernando Peña3 months ago

I'm upset because they cut off my access to the image editing model HY Image 3.0 Instruct ( Why did they remove access for Latin America?

ai lover fun wan9 months ago

Be like bfl, release open model with low spec like 4b and 9b.

Đặng Văn Hoàn9 months ago

Where to upload image on the site?

BlackLeftistTraitor7 months ago

YOUR MODEL SUCKS!!! It TIMESOUT like HALF THE TIME! WORTHLESS

Dishubtive9 months ago

There's a problem with the text field here for me.

Zeek9 months ago

Release in English

4chan ♱9 months ago

insane

Nicolas Craske9 months ago

🤩🙏

hayzSapiens 🎮📡8 months ago

Please work on generating better UV map for AI models

Leonard8 months ago

api?

Olgerd9 months ago

Wow! Amazing

OneNinerFive9 months ago

What can it do just as good as, if not better than, Nano Banana Pro?

Related Videos

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

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

413,296 views • 1 year ago

Introducing Wan2.6 - A native multimodal model that turns your ideas into breathtaking videos and images! · Starring: Cast characters from reference videos into new scenes. Support human or human-like figures, enabling complex multi-person and human-object interactions with appearance and voice consistency. · Intelligent Multi-shot Narrative: Turn simple prompts into auto-storyboarded, multi-shot videos. Maintain visual consistency and upgrade storytelling from single shots to rich narratives. · Native A/V Sync: Generate multi-speaker dialogue with natural lip-sync and studio-quality audio. It doesn’t just look real - it sounds real. · Cinematic Quality: 15s 1080p HD generation with comprehensive upgrades to instruction adherence, motion physics, and aesthetic control. · Advanced Image Synthesis and Editing: Deliver cinematic photorealism with precise control over lens and lighting. Support multi-image referencing for commercial-grade consistency and faithful aesthetic transfer. · Storytelling with Structure: Generate interleaved texts and images powered by real-world knowledge and reasoning capabilities, enabling hierarchical and structured visual narratives.

Introducing Wan2.6 - A native multimodal model that turns your ideas into breathtaking videos and images! · Starring: Cast characters from reference videos into new scenes. Support human or human-like figures, enabling complex multi-person and human-object interactions with appearance and voice consistency. · Intelligent Multi-shot Narrative: Turn simple prompts into auto-storyboarded, multi-shot videos. Maintain visual consistency and upgrade storytelling from single shots to rich narratives. · Native A/V Sync: Generate multi-speaker dialogue with natural lip-sync and studio-quality audio. It doesn’t just look real - it sounds real. · Cinematic Quality: 15s 1080p HD generation with comprehensive upgrades to instruction adherence, motion physics, and aesthetic control. · Advanced Image Synthesis and Editing: Deliver cinematic photorealism with precise control over lens and lighting. Support multi-image referencing for commercial-grade consistency and faithful aesthetic transfer. · Storytelling with Structure: Generate interleaved texts and images powered by real-world knowledge and reasoning capabilities, enabling hierarchical and structured visual narratives.

Wan

3,848,218 views • 10 months ago

Introducing ChatGPT Images 2.0 A state-of-the-art image model that can take on complex visual tasks and produce precise, immediately usable visuals, with sharper editing, richer layouts, and thinking-level intelligence. Video made with ChatGPT Images

Introducing ChatGPT Images 2.0 A state-of-the-art image model that can take on complex visual tasks and produce precise, immediately usable visuals, with sharper editing, richer layouts, and thinking-level intelligence. Video made with ChatGPT Images

OpenAI

12,937,383 views • 6 months ago

introducing Seedream 5.0 Pro. this new multimodal model brings advance reasoning, precise image editing, and support for up to 10 image references. try it now on Krea.

introducing Seedream 5.0 Pro. this new multimodal model brings advance reasoning, precise image editing, and support for up to 10 image references. try it now on Krea.

Krea

38,896 views • 4 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 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

93,032 views • 1 month ago

We present MMaDA, first diffusion that unifies text reasoning, multimodal understanding, and image generation through Mixed Long-CoT, and unified RL - UniGRPO. 📚 Paper: 💻 Code: 📦 Model:

We present MMaDA, first diffusion that unifies text reasoning, multimodal understanding, and image generation through Mixed Long-CoT, and unified RL - UniGRPO. 📚 Paper: 💻 Code: 📦 Model:

Ling Yang

87,734 views • 1 year ago

CosmicMan A Text-to-Image Foundation Model for Humans We present CosmicMan, a text-to-image foundation model specialized for generating high-fidelity human images. Unlike current general-purpose foundation models that are stuck in the dilemma of inferior quality and

CosmicMan A Text-to-Image Foundation Model for Humans We present CosmicMan, a text-to-image foundation model specialized for generating high-fidelity human images. Unlike current general-purpose foundation models that are stuck in the dilemma of inferior quality and

AK

46,778 views • 2 years ago

Today, we open-source P-H3-Image, an image generation and editing model built from MiniMax-H3 by MiniMax (official). A SOTA video model, turned into an efficient open image model. - 𝗛𝗼𝘄 𝗲𝗳𝗳𝗶𝗰𝗶𝗲𝗻𝘁 𝗶𝘀 𝗶𝘁? Generate or edit images 5× faster, in 8 steps instead of 50. A 4 MP image takes 2.6 s instead of 12.4 s. The model is 7× smaller than H3, so high-resolution images are a light download and run on a much smaller GPU. - 𝗛𝗼𝘄 𝗴𝗼𝗼𝗱 𝗶𝘀 𝗶𝘁? Strongest at photorealism, documentary and editorial photography, film stills, and graphic styles with short quoted text. It renders 2 to 16 MP and edits with up to 8 input images. -𝗛𝗼𝘄 𝗱𝗼𝗲𝘀 𝗶𝘁 𝘄𝗼𝗿𝗸? We reworked every component of H3: the prompt upsampler, the text encoder, the diffusion schedule, the transformer, and the decoder. Use it with Diffusers or ComfyUI. 📄 Tech Report: 🤗 Hugging Face Open Weights: 👉 ComfyUI Native Support:

Today, we open-source P-H3-Image, an image generation and editing model built from MiniMax-H3 by MiniMax (official). A SOTA video model, turned into an efficient open image model. - 𝗛𝗼𝘄 𝗲𝗳𝗳𝗶𝗰𝗶𝗲𝗻𝘁 𝗶𝘀 𝗶𝘁? Generate or edit images 5× faster, in 8 steps instead of 50. A 4 MP image takes 2.6 s instead of 12.4 s. The model is 7× smaller than H3, so high-resolution images are a light download and run on a much smaller GPU. - 𝗛𝗼𝘄 𝗴𝗼𝗼𝗱 𝗶𝘀 𝗶𝘁? Strongest at photorealism, documentary and editorial photography, film stills, and graphic styles with short quoted text. It renders 2 to 16 MP and edits with up to 8 input images. -𝗛𝗼𝘄 𝗱𝗼𝗲𝘀 𝗶𝘁 𝘄𝗼𝗿𝗸? We reworked every component of H3: the prompt upsampler, the text encoder, the diffusion schedule, the transformer, and the decoder. Use it with Diffusers or ComfyUI. 📄 Tech Report: 🤗 Hugging Face Open Weights: 👉 ComfyUI Native Support:

Pruna AI

150,517 views • 3 days ago

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 views • 2 years ago

1/4 🚀We are launching Qwen-Image-2.0, a next-generation foundational image generation model. The key highlights of Qwen-Image-2.0 include: Professional Typography Rendering: Supports 1k-token instructions for direct generation of professional infographics, including PPTs, posters, comics, and more. Stronger Semantic Adherence: Native 2K resolution support for finely detailed realistic scenes, including people, nature, and architecture. Improved Text Rendering: Integrated understanding and generation capabilities, unifying image generation and editing in a single mode Lighter Model Architecture: Smaller model size with faster inference speed.

1/4 🚀We are launching Qwen-Image-2.0, a next-generation foundational image generation model. The key highlights of Qwen-Image-2.0 include: Professional Typography Rendering: Supports 1k-token instructions for direct generation of professional infographics, including PPTs, posters, comics, and more. Stronger Semantic Adherence: Native 2K resolution support for finely detailed realistic scenes, including people, nature, and architecture. Improved Text Rendering: Integrated understanding and generation capabilities, unifying image generation and editing in a single mode Lighter Model Architecture: Smaller model size with faster inference speed.

Tongyi Lab

164,097 views • 9 months ago

You imagine it. We create it. 🎨 Introducing #PixelStudio, a first-of-its-kind image generator on #Pixel9 powered by an on-device diffusion model¹ running on Tensor G4 and our Imagen 3 text-to-image model in the cloud.

You imagine it. We create it. 🎨 Introducing #PixelStudio, a first-of-its-kind image generator on #Pixel9 powered by an on-device diffusion model¹ running on Tensor G4 and our Imagen 3 text-to-image model in the cloud.

Made by Google

28,302 views • 2 years ago

Compute is the backbone of the AI-driven future. OptimAI Compute Engine would enable scalable, high-performance workloads across image and video models, supporting: • Text-to-image generation • Image editing and inpainting • 2K / 4K / 8K super-resolution • Brand-aligned visual synthesis • OCR and image intelligence • Video generation and motion synthesis • Frame interpolation and enhancement • Multimodal model inference Distributed compute built for faster inference, shorter training cycles, and production-grade AI execution.

OptimAI Network

18,909 views • 8 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 • 18 days ago

🚀UniWorld: a unified model that skips VAEs and uses semantic features from SigLIP! Using just 1% of BAGEL’s data, it outperforms on image editing and excels in understanding & generation. 🌟Now data, model, training & evaluation script are open-source!

🚀UniWorld: a unified model that skips VAEs and uses semantic features from SigLIP! Using just 1% of BAGEL’s data, it outperforms on image editing and excels in understanding & generation. 🌟Now data, model, training & evaluation script are open-source!

Bin Lin

22,387 views • 1 year ago

Introducing ChatGPT Images, powered by our flagship new image generation model. - Stronger instruction following - Precise editing - Detail preservation - 4x faster than before Rolling out today in ChatGPT for all users, and in the API as GPT Image 1.5.

Introducing ChatGPT Images, powered by our flagship new image generation model. - Stronger instruction following - Precise editing - Detail preservation - 4x faster than before Rolling out today in ChatGPT for all users, and in the API as GPT Image 1.5.

OpenAI

3,249,001 views • 10 months ago