Tencent image model
Hunyuan Image 2.1 on RenderFlow AI is the hosted Tencent model: 3 credits per image, width and height from 256 to 1536 pixels, and JPEG, PNG, or WebP output.
Your generated image will appear here.
Enter a prompt and click 'Generate Image' — or start from an example:
Examples
These six images are Hunyuan Image 2.1 outputs on RenderFlow AI. Open one to read the prompt, then change size, format, or seed in the canvas. They are not Hunyuan Image 3 results.
Poster / illustration
Flat illustration poster
Prompt: Flat vector-style travel poster of a coastal lighthouse on striped cliffs, a tiny sailboat on a patterned teal sea, big round sun in a coral sky, seagulls as simple curved marks, bold geometric shapes with a subtle paper texture, mid-century travel poster aesthetic, clean edges, limited palette of coral, teal, cream, and navy. No text.
Product mockup
Product visual on a budget
Prompt: Clean product photograph of a matte ceramic pour-over coffee dripper in terracotta, sitting on a walnut table with a linen cloth, a few roasted coffee beans scattered nearby, soft morning side light, gentle shadow, warm minimal lifestyle aesthetic, square composition for an online shop listing, realistic textures.
Social media graphic
Social graphic with short text
Prompt: Cheerful social media graphic for a fictional neighborhood farmers market: illustrated piles of tomatoes, peaches, and sunflowers forming a loose border around a cream center, with the words "SATURDAY MARKET" in large friendly hand-lettered capitals in the middle and "EVERY WEEK · 8 TO 1" in smaller type below. Warm harvest palette, folk-art flat illustration style, text crisp and correctly spelled.
Character / anime illustration
Anime-style character scene
Prompt: Anime-style illustration of a girl with a short silver bob and a oversized teal raincoat standing under a clear umbrella at a rainy train crossing at dusk, glowing vending machine light nearby, puddles reflecting neon signs, cinematic Makoto-Shinkai-inspired lighting with lush clouds after rain, detailed background art, gentle melancholic mood.
Packaging design concept
Bilingual tea packaging concept
Prompt: Elegant packaging design mockup for a white tea brand: a tall cylindrical paper canister in soft ivory with a minimal ink-wash mountain illustration wrapping the lower half, the English words "WHITE PEONY TEA" in a refined serif on the front and the Chinese characters "白牡丹" in elegant calligraphy beneath them, a thin gold band at the lid. Soft studio light, seamless pale background, premium minimal East-Asian design, all characters correctly rendered.
Interior / lifestyle concept
Cozy interior scene
Prompt: Warm illustration of a tiny bakery kitchen in the early morning: wooden shelves stacked with mixing bowls, a window with soft blue dawn light, croissants proofing on a tray, flour dust in the air, a cat asleep on a stool, storybook gouache style with soft edges and a honey-and-cream palette, inviting and detailed.
Hunyuan Image 2.1 on RenderFlow AI is the hosted text-to-image model. The catalog price is 3 credits per image. Width runs from 256 to 1536 pixels and height runs from 256 to 1536, both defaulting to 1024. Output can be jpeg, png, webp. The seed defaults to -1.
Tencent publishes HunyuanImage-2.1 as open weights. The public model card describes a 2K pipeline, Chinese and English prompts, and optional prompt enhancement and refinement. This canvas does not expose 2048-pixel output, a refiner switch, or a prompt-rewriter switch. Stay inside the size range on the page and inspect the file, especially if you expected the 2K result described for the full pipeline.
Set each side from 256 to 1536 pixels. The default is 1024 by 1024. Use a smaller side only when the placement is small, and look at the file before you crop it further. This page cannot set 2048.
Choose WebP for a web handoff, PNG when you want a lossless file, or JPEG when a photo workflow expects it. JPEG is the canvas default.
State the subject, the setting, and the style in English or Chinese. A usable pattern is: "Flat travel poster of a coral lighthouse on teal cliffs, tiny sailboat, no text." Keep requested lettering short.
The seed defaults to -1, which starts a new result. Set a fixed seed, change one phrase, and generate again. Return the seed to -1 when you want a fresh image.
If the approved idea must exceed 1536 pixels, rerun the prompt on Imagen 4 or another model whose canvas lists the size you need. Do not upscale this page's ceiling in the prompt and expect 2K.
These rows are the live Hunyuan Image 2.1 controls on RenderFlow AI, checked with the model catalog.
| Price | 3 credits per image. |
|---|---|
| Width | 256 to 1536 pixels, default 1024 |
| Height | 256 to 1536 pixels, default 1024 |
| Output | jpeg, png, webp, default jpeg |
| Seed | Default -1. Maximum 2147483647. |
| Not on this page | No 2048-pixel size, no refiner switch, and no prompt-enhancer switch. |
Tencent's published HunyuanImage-2.1 card describes a 2K pipeline. RenderFlow AI hosts the smaller size range above.
Yes. Tencent published the HunyuanImage-2.1 weights. RenderFlow AI hosts generation for that model name at 3 credits per image. The hosted canvas is not the full 2K pipeline: it has no 2048-pixel size, no refiner switch, and no prompt-enhancer switch.
Width and height each run from 256 to 1536 pixels and default to 1024. Output is JPEG, PNG, or WebP, defaulting to JPEG. The seed defaults to -1 and can be set up to 2147483647. The settings table on this page repeats the live canvas values.
Use Hunyuan Image 2.1 for a general scene, an illustration, or a file-format choice inside its size cap. Use Qwen Image when the job is a poster, a menu, or other text-heavy layout. Both are separate RenderFlow AI pages, so compare the live credit price on each canvas.
Anything that needs a side longer than 1536 pixels, a guaranteed 2K file, or a long block of in-image text. Small sizes are available, but the public model card says sub-2K output can artifact on the full pipeline, so check edges and faces before you ship a 512-pixel draft.
Yes. The published HunyuanImage-2.1 model documents Chinese and English prompts. Write in whichever language the brief uses, and proofread any characters that must appear inside the image.
Open the canvas, set a size inside 256 to 1536 pixels, and check the 3-credit price before you run the prompt.
Open in AI Image GeneratorQwen Image Generator
Create images with strong text rendering and layout control.
Hunyuan Image 3
Generate complex scenes with Hunyuan Image 3 on RenderFlow AI.
Google Imagen 4
Generate photorealistic images with Google Imagen 4.
Flux Pro
Generate professional images with Flux 1.1 Pro.
Imagen 4 Ultra
Use Google Imagen 4 Ultra for premium photorealistic AI image generation.
Flux Kontext Pro
Edit images with context-aware FLUX prompt controls.