HunyuanImage-2.1
Tencent Hunyuan · tencent/HunyuanImage-2.1
Weights license: Publisher terms: Tencent Hunyuan Community License Agreement · code and components may use other terms
Quality
No comparable score
Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. Leaderboard (link only)
Reported by the publisher
- Mean Image Accuracy
- 0.889
- Global Accuracy
- 0.883
- Primary Subject · Noun
- 0.934
- Primary Subject · Key Attributes
- 0.934
- Primary Subject · Other Attributes
- 0.836
- Primary Subject · Action
- 0.834
- Secondary Subject · Noun
- 0.963
- Secondary Subject · Attributes
- 0.887
Every reported result
Values as printed on the card, with the publisher's own settings (card section: 📈 Comparisons › SSAE Evaluation); column “HunyuanImage 2.1”. Not comparable across publishers and not used in any ranking. Model card
Runs on
Enough memory 22
A publisher documents a path within this memory, on this platform (CUDA or Apple MPS). Conditional paths need offload or quantization.
Show all 22
One memory tier short 16
The same machines with the next memory size up would have enough.
Show all 16
Hardware profiles grouped by the publisher's documented minimum memory path and platform. Not a measured run.
Consider HunyuanImage-2.1 from Tencent Hunyuan for the text-to-image task (17B parameters).
The catalog lists the publisher's documented memory path under Runs on and has not reviewed other configurations. Actual memory depends on precision, resolution, duration and offload; consult the official source.
Measured speed
No published measurement for this checkpoint
Generation time per image is shown only when a source publishes it with hardware, build and setup. It is never estimated.
How to run
Publisher-documented memory path: Official FP8 path at 2048×2048. Actual memory depends on precision, resolution, duration and offload; consult the official source. Official hardware evidence
Documented ways to run it
Copied as printed in the linked source (read 2026-10-18); not run by this site.
git clone https://github.com/Tencent-Hunyuan/HunyuanImage-2.1.git
cd HunyuanImage-2.1import os
os.environ['PYTORCH_CUDA_ALLOC_CONF'] = 'expandable_segments:True'
import torch
from hyimage.diffusion.pipelines.hunyuanimage_pipeline import HunyuanImagePipeline
# Supported model_name: hunyuanimage-v2.1, hunyuanimage-v2.1-distilled
model_name = "hunyuanimage-v2.1"
pipe = HunyuanImagePipeline.from_pretrained(model_name=model_name, use_fp8=True)
pipe = pipe.to("cuda")
prompt = "A cute, cartoon-style anthropomorphic penguin plush toy with fluffy fur, standing in a painting studio, wearing a red knitted scarf and a red beret with the word “Tencent” on it, holding a paintbrush with a focused expression as it paints an oil painting of the Mona Lisa, rendered in a photorealistic photographic style."
image = pipe(
prompt=prompt,
# Examples of supported resolutions and aspect ratios for HunyuanImage-2.1:
# 16:9 -> width=2560, height=1536
# 4:3 -> width=2304, height=1792
# 1:1 -> width=2048, height=2048
# 3:4 -> width=1792, height=2304
# 9:16 -> width=1536, height=2560
# Please use one of the above width/height pairs for best results.
width=2048,
height=2048,
use_reprompt=False, # Enable prompt enhancement (which may result in higher GPU memory usage)
use_refiner=True, # Enable refiner model
# For the distilled model, use 8 steps for faster inference.
# For the non-distilled model, use 50 steps for better quality.
num_inference_steps=8 if "distilled" in model_name else 50,
guidance_scale=3.25 if "distilled" in model_name else 3.5,
shift=4 if "distilled" in model_name else 5,
seed=649151,
)
image.save(f"generated_image.png")Evidence level: Publisher documentation linked; no execution reproduced by this site.
Before downloading
- Check the exact checkpoint and license linked here.
- Confirm a compatible runtime and precision or quantization for your platform.
- Allow for context, batch size and any extra media components beyond the weights.
Technical details
What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.
- Checkpoint / version
- tencent/HunyuanImage-2.1
- Task and modality
- text-to-image · image
- Count and basis
- 17B · manufacturer model card
- Released
- Tencent-Hunyuan/HunyuanImage-2.1 README (GitHub), Latest Updates · read 2026-10-09source
- Published repository size
- 173 GBNot runtime memory or a minimum download.files
- Published components
- DiT · VAE · Reprompt module
- Runtime and precision
- No local execution verified.
- Commercial use
- Allowed with conditions Not licensed in the EU, UK or South Korea; over 100M monthly users needs a Tencent license · Tencent Hunyuan Community License (tencent/HunyuanImage-3.0 LICENSE) · read 2026-10-18license text
Sources
Identity and published specifications come from the checkpoint page. Benchmark scores belong to the named release and do not measure speed on your computer.
- Publisher checkpoint and model card
- Weight license and use terms
- Quality benchmark source · Artificial Analysis image · excluded (free tier is internal use only)
- Publisher hardware documentation
Catalog reviewed: 2026-09-22.






























