Tencent ยท Open-sourced September 28, 2025

Hunyuan Image 3 AI Image Generator

Tencent's 80 billion parameter mixture-of-experts image model, the largest open-source text-to-image model at release, with readable text baked into the picture. 1 credit per image, five aspect ratios, no watermark, on every Aura AI plan.

1
Credit per Image
5
Aspect Ratios
80B
Parameters (MoE)
Open
Weights Upstream

Hunyuan Image 3 on Aura AI

MakerTencent
ModesText to image
VariantsHunyuan Image V3
OutputStill image, no watermark
Aspect ratios16:9, 9:16, 1:1, 4:3, 3:4
EditingNo edit variant
Credits1 per image
PlanStarter, Pro, Premium

What is Hunyuan Image 3?

Hunyuan Image 3, officially HunyuanImage 3.0, is the text-to-image model that Tencent's Hunyuan team open-sourced on September 28, 2025. It is a mixture-of-experts model with 80 billion total parameters, of which about 13 billion are active for each token, routed across 64 experts. At release it was the largest open-source image generation model available, and within days it climbed to the top of the LMArena text-to-image leaderboard, ahead of several closed models. The weights ship under the Tencent Hunyuan Community License, which permits commercial use with some regional and scale restrictions.

What sets it apart technically is the architecture. Instead of a standard diffusion transformer, Tencent combined a mixture-of-experts language backbone with a "Transfusion" style image head, so text understanding and pixel generation live in one unified autoregressive framework. The practical result is a model that follows long, detailed prompts of a thousand characters or more, reasons about what the scene should contain, and renders Chinese and English text inside the picture with unusual accuracy, from poster headlines to product labels and small annotations.

On Aura AI, Hunyuan Image 3 runs in text-to-image mode for a flat 1 credit per image, in five aspect ratios from 16:9 widescreen to 9:16 vertical, on every plan. It is one of the cheapest models in the studio, which makes it a natural first pass before you spend more credits on Qwen Image 3, FLUX 2 or Nano Banana. All output is delivered without watermark and can be sent straight to the image editor or to image-to-video.

Hunyuan Image 3 Capabilities

Six things Tencent's largest open image model does well

80B Mixture of Experts

64 experts and 80 billion total parameters, with about 13 billion active per token. The model has the knowledge of a very large network while spending compute only on the experts a given prompt needs.

Readable Text in Images

Titles, slogans, logos, signage and small labels come out legible in both Chinese and English. This was a headline feature of the release and it holds up on posters, packaging mockups and infographics.

Unified Multimodal Architecture

Text understanding and image generation share one autoregressive backbone. The model interprets the prompt the way a language model would, then generates pixels, which improves adherence on complex scenes.

Long, Detailed Prompts

Tencent reports semantic understanding of prompts beyond 1,000 characters. You can describe several subjects, their positions, the lighting and the text you want on screen, and the model keeps track of all of it.

Open Weights

The full checkpoint is public under the Tencent Hunyuan Community License, and the model reached first place on LMArena's text-to-image leaderboard in October 2025. On Aura AI you skip the 80B download and run it hosted.

1 Credit per Image

The lowest price tier in the Aura AI image catalog, shared with FLUX 2 Turbo, Krea 2 Turbo and Gemini 3.1 Flash. Iterate on composition at low cost, then move to a 2 or 3 credit model only if you need an editor.

How to Use Hunyuan Image 3 on Aura AI

Four steps from prompt to a downloadable image

  1. Open the Text to Image tool and sign in with your Aura AI account. Hunyuan Image 3 is available on every plan.
  2. Pick Hunyuan Image V3 in the model selector and choose one of the five aspect ratios (16:9, 9:16, 1:1, 4:3, 3:4). The cost shows as 1 credit before you generate.
  3. Write a detailed prompt. Hunyuan Image 3 rewards specificity: name the subject, the setting, the lighting, the camera and, if you want text, put the exact words in quotes and say where they go.
  4. Generate, preview and download the image without watermark. To retouch it, send the result to the image editor and pick an edit model such as Qwen Image 3 Edit or FLUX 2 Edit.

Hunyuan Image 3 Pricing in Credits

A single flat cost, the same in every aspect ratio

Variant Mode Credits per image Best for
Hunyuan Image V3Text to image1 creditText-heavy posters, dense multi-subject scenes, cheap first drafts
Hunyuan Image 3 is available on every plan: Starter ($14/mo), Pro ($59/mo) and Premium ($99/mo). Each plan includes a monthly credit allowance, and only successful generations are charged. There is no edit variant, so image editing uses another model from the same credit pool.

Hunyuan Image 3 vs Qwen Image 3 vs FLUX 2 vs Nano Banana

How Tencent's open model compares to its closest rivals on Aura AI

Feature Hunyuan Image 3 Qwen Image 3 FLUX 2 Nano Banana
Maker Tencent Alibaba Black Forest Labs Google
Text-to-image credits 1 2 2 (Turbo 1, Max 3) 3 (Pro or 2)
Edit variant on Aura AI No 2 credits 2 credits 2 or 3 credits
Open weights Community License No (3.0 released without weights) Dev checkpoint only No
Text rendering Chinese and English, strong Strong, 12 languages upstream Good Good
Architecture 80B MoE, unified autoregressive Not disclosed for 3.0 Diffusion transformer Gemini-based
Aspect ratios on Aura AI 5 5 5 5
Plan All plans All plans All plans All plans

What to Make with Hunyuan Image 3

Where a 1 credit model with real text rendering pays off

Posters and Flyers with Text

Event posters, sale banners and social announcements where the headline has to be spelled correctly. Put the exact copy in quotes and specify position and typeface style.

Example Prompt: "Concert poster, bold sans-serif headline 'MIDNIGHT SESSIONS' at the top, subline 'Sat 14 Nov, Warehouse 9', dark blue background with neon pink light streaks, 3:4"

Packaging and Label Mockups

Product boxes, bottles and bags with brand names and ingredient text rendered legibly. Useful for pitch decks and early e-commerce concepts before a designer touches them.

Example Prompt: "Matte black coffee bag on a wooden counter, label reads 'KURO ROAST, Single Origin Ethiopia, 250g', minimal gold typography, soft window light, 1:1"

Infographics and Diagrams

Simple explanatory graphics with labelled parts, numbered steps and short captions. The unified architecture keeps the labels attached to the right elements.

Example Prompt: "Flat infographic of a bicycle with four labelled callouts: 'Frame', 'Chain', 'Brake', 'Saddle', pastel colors, white background, clean vector style, 16:9"

Bulk Concept Exploration

At 1 credit per image you can run ten variations of a scene for the price of a few premium generations. Explore compositions here, then refine the winner in a model with an editor.

Example Prompt: "Cozy bookshop interior at dusk, tall shelves, warm lamps, a cat asleep on the counter, rain on the window, cinematic depth of field, 4:3"

Hunyuan Image 3 FAQ

Common questions about Hunyuan Image 3 on Aura AI

What is Hunyuan Image 3? +
Hunyuan Image 3 (HunyuanImage 3.0) is Tencent's text-to-image model, open-sourced on September 28, 2025. It is a mixture-of-experts model with 80 billion total parameters, 13 billion of which are active per token, spread across 64 experts. It was the largest open-source image generation model at release and is known for rendering readable Chinese and English text inside images. On Aura AI it runs in text-to-image mode for 1 credit per picture.
How many credits does Hunyuan Image 3 cost on Aura AI? +
Hunyuan Image 3 costs a flat 1 credit per image on Aura AI, in any of the five aspect ratios (16:9, 9:16, 1:1, 4:3, 3:4). There is no resolution multiplier and no surcharge for long prompts. Only successful generations are charged.
Which plan do I need to use Hunyuan Image 3? +
Hunyuan Image 3 is available on every Aura AI plan: Starter ($14/mo), Pro ($59/mo) and Premium ($99/mo). Each plan includes a monthly credit allowance that you can spend on Hunyuan Image 3 or on any other image and video model in the studio. It works on web, iOS, Android and Windows.
Can Hunyuan Image 3 edit existing images on Aura AI? +
No. On Aura AI, Hunyuan Image 3 is a text-to-image model only, with no edit variant. Tencent later published an Instruct version upstream that adds image-to-image editing and multi-image fusion, but that variant is not exposed on Aura AI. For editing, use Qwen Image 3 Edit (2 credits), FLUX 2 Edit (2 credits) or Nano Banana Edit (2 credits) in the image editor.
How does Hunyuan Image 3 compare to Qwen Image 3 and FLUX 2? +
Hunyuan Image 3 is the cheapest of the three on Aura AI at 1 credit per image, against 2 credits for Qwen Image 3 and 2 credits for FLUX 2. Hunyuan Image 3 and FLUX 2 Dev both ship open weights, while Qwen-Image-3.0 was released without weights. Qwen Image 3 and FLUX 2 both have edit variants on Aura AI, Hunyuan Image 3 does not. Pick Hunyuan Image 3 for budget text-heavy posters and dense scenes, Qwen Image 3 for very long layout prompts, FLUX 2 for photoreal work with a matching editor.

Generate Hunyuan Image 3 Pictures Online

Tencent's 80B open image model, 1 credit per image, five aspect ratios, no watermark. Available on every plan, worldwide.