Sponsored by
APIMart
tencent / HunyuanImage-3.0-Instruct
Model's Last Updated: February 03 2026
image-to-image
Introduction of HunyuanImage-3.0-Instruct
Model Details of HunyuanImage-3.0-Instruct
๐ Join our WeChat and Discord | ๐ป Official website(ๅฎ็ฝ) Try our model!
๐ฅ๐ฅ๐ฅ News
- September 28, 2025 : ๐ HunyuanImage-3.0 Technical Report Released - Comprehensive technical documentation now available
- September 28, 2025 : ๐ HunyuanImage-3.0 Open Source Release - Inference code and model weights publicly available
๐งฉ Community Contributions
If you develop/use HunyuanImage-3.0 in your projects, welcome to let us know.
๐ Open-source Plan
-
HunyuanImage-3.0 (Image Generation Model)
- Inference
- HunyuanImage-3.0 Checkpoints
- HunyuanImage-3.0-Instruct Checkpoints (with reasoning)
- VLLM Support
- Distilled Checkpoints
- Image-to-Image Generation
- Multi-turn Interaction
๐๏ธ Contents
- ๐ฅ๐ฅ๐ฅ News
- ๐งฉ Community Contributions
- ๐ Open-source Plan
- ๐ Introduction
- โจ Key Features
- ๐ ๏ธ Dependencies and Installation
- ๐ Usage
- ๐งฑ Models Cards
- ๐ Prompt Guide
- ๐ Evaluation
- ๐ Citation
- ๐ Acknowledgements
- ๐๐ Github Star History
๐ Introduction
HunyuanImage-3.0 is a groundbreaking native multimodal model that unifies multimodal understanding and generation within an autoregressive framework. Our text-to-image module achieves performance comparable to or surpassing leading closed-source models.
โจ Key Features
-
๐ง Unified Multimodal Architecture: Moving beyond the prevalent DiT-based architectures, HunyuanImage-3.0 employs a unified autoregressive framework. This design enables a more direct and integrated modeling of text and image modalities, leading to surprisingly effective and contextually rich image generation.
-
๐ The Largest Image Generation MoE Model: This is the largest open-source image generation Mixture of Experts (MoE) model to date. It features 64 experts and a total of 80 billion parameters, with 13 billion activated per token, significantly enhancing its capacity and performance.
-
๐จ Superior Image Generation Performance: Through rigorous dataset curation and advanced reinforcement learning post-training, we've achieved an optimal balance between semantic accuracy and visual excellence. The model demonstrates exceptional prompt adherence while delivering photorealistic imagery with stunning aesthetic quality and fine-grained details.
-
๐ญ Intelligent World-Knowledge Reasoning: The unified multimodal architecture endows HunyuanImage-3.0 with powerful reasoning capabilities. It leverages its extensive world knowledge to intelligently interpret user intent, automatically elaborating on sparse prompts with contextually appropriate details to produce superior, more complete visual outputs.
๐ ๏ธ Dependencies and Installation
๐ป System Requirements
- ๐ฅ๏ธ Operating System: Linux
- ๐ฎ GPU: NVIDIA GPU with CUDA support
- ๐พ Disk Space: 170GB for model weights
- ๐ง GPU Memory: โฅ3ร80GB (4ร80GB recommended for better performance)
๐ฆ Environment Setup
- ๐ Python: 3.12+ (recommended and tested)
- ๐ฅ PyTorch: 2.7.1
- โก CUDA: 12.8
๐ฅ Install Dependencies
# 1. First install PyTorch (CUDA 12.8 Version)
pip install torch==2.7.1 torchvision==0.22.1 torchaudio==2.7.1 --index-url https://download.pytorch.org/whl/cu128
# 2. Then install other dependencies
pip install -r requirements.txt
Performance Optimizations
For up to 3x faster inference , install these optimizations:
# FlashAttention for faster attention computation
pip install flash-attn==2.8.3 --no-build-isolation
# FlashInfer for optimized moe inference. v0.3.1 is tested.
pip install flashinfer-python
๐ก Installation Tips: It is critical that the CUDA version used by PyTorch matches the system's CUDA version. FlashInfer relies on this compatibility when compiling kernels at runtime. Pytorch 2.7.1+cu128 is tested. GCC version >=9 is recommended for compiling FlashAttention and FlashInfer.
โก Performance Tips: These optimizations can significantly speed up your inference!
๐ก Notation: When FlashInfer is enabled, the first inference may be slower (about 10 minutes) due to kernel compilation. Subsequent inferences on the same machine will be much faster.
๐ Usage
๐ฅ Quick Start with Transformers
1๏ธโฃ Download model weights
# Download from HuggingFace and rename the directory.
# Notice that the directory name should not contain dots, which may cause issues when loading using Transformers.
hf download tencent/HunyuanImage-3.0 --local-dir ./HunyuanImage-3
2๏ธโฃ Run with Transformers
from transformers import AutoModelForCausalLM
# Load the model
model_id = "./HunyuanImage-3"
# Currently we can not load the model using HF model_id `tencent/HunyuanImage-3.0` directly
# due to the dot in the name.
kwargs = dict(
attn_implementation="sdpa", # Use "flash_attention_2" if FlashAttention is installed
trust_remote_code=True,
torch_dtype="auto",
device_map="auto",
moe_impl="eager", # Use "flashinfer" if FlashInfer is installed
)
model = AutoModelForCausalLM.from_pretrained(model_id, **kwargs)
model.load_tokenizer(model_id)
# generate the image
prompt = "A brown and white dog is running on the grass"
image = model.generate_image(prompt=prompt, stream=True)
image.save("image.png")
๐ Local Installation & Usage
1๏ธโฃ Clone the Repository
git clone https://github.com/Tencent-Hunyuan/HunyuanImage-3.0.git
cd HunyuanImage-3.0/
2๏ธโฃ Download Model Weights
# Download from HuggingFace
hf download tencent/HunyuanImage-3.0 --local-dir ./HunyuanImage-3
3๏ธโฃ Run the Demo
python3 run_image_gen.py --model-id ./HunyuanImage-3 --verbose 1 --prompt "A brown and white dog is running on the grass"
4๏ธโฃ Command Line Arguments
| Arguments | Description | Default |
|---|---|---|
--prompt
|
Input prompt | (Required) |
--model-id
|
Model path | (Required) |
--attn-impl
|
Attention implementation. Either
sdpa
or
flash_attention_2
.
|
sdpa
|
--moe-impl
|
MoE implementation. Either
eager
or
flashinfer
|
eager
|
--seed
|
Random seed for image generation |
None
|
--diff-infer-steps
|
Diffusion infer steps |
50
|
--image-size
|
Image resolution. Can be
auto
, like
1280x768
or
16:9
|
auto
|
--save
|
Image save path. |
image.png
|
--verbose
|
Verbose level. 0: No log; 1: log inference information. |
0
|
๐จ Interactive Gradio Demo
Launch an interactive web interface for easy text-to-image generation.
1๏ธโฃ Install Gradio
pip install gradio>=4.21.0
2๏ธโฃ Configure Environment
# Set your model path
export MODEL_ID="path/to/your/model"
# Optional: Configure GPU usage (default: 0,1,2,3)
export GPUS="0,1,2,3"
# Optional: Configure host and port (default: 0.0.0.0:443)
export HOST="0.0.0.0"
export PORT="443"
3๏ธโฃ Launch the Web Interface
Basic Launch:
sh run_app.sh
With Performance Optimizations:
# Use both optimizations for maximum performance
sh run_app.sh --moe-impl flashinfer --attn-impl flash_attention_2
4๏ธโฃ Access the Interface
๐ Web Interface: Open your browser and navigate to
http://localhost:443(or your configured port)
๐งฑ Models Cards
| Model | Params | Download | Recommended VRAM | Supported |
|---|---|---|---|---|
| HunyuanImage-3.0 | 80B total (13B active) | HuggingFace | โฅ 3 ร 80 GB | โ Text-to-Image |
| HunyuanImage-3.0-Instruct | 80B total (13B active) | HuggingFace | โฅ 3 ร 80 GB |
โ
Text-to-Image
โ Prompt Self-Rewrite โ CoT Think |
Notes:
- Install performance extras (FlashAttention, FlashInfer) for faster inference.
- MultiโGPU inference is recommended for the Base model.
๐ Prompt Guide
Manually Writing Prompts.
The Pretrain Checkpoint does not automatically rewrite or enhance input prompts, Instruct Checkpoint can rewrite or enhance input prompts with thinking . For optimal results currently, we recommend community partners consulting our official guide on how to write effective prompts.
Reference: HunyuanImage 3.0 Prompt Handbook
System Prompt For Automatic Rewriting the Prompt.
We've included two system prompts in the PE folder of this repository that leverage DeepSeek to automatically enhance user inputs:
- system_prompt_universal : This system prompt converts photographic style, artistic prompts into a detailed one.
- system_prompt_text_rendering : This system prompt converts UI/Poster/Text Rending prompts to a deailed on that suits the model.
Note that these system prompts are in Chinese because Deepseek works better with Chinese system prompts. If you want to use it for English oriented model, you may translate it into English or refer to the comments in the PE file as a guide.
We also create a Yuanqi workflow to implent the universal one, you can directly try it.
Advanced Tips
-
Content Priority : Focus on describing the main subject and action first, followed by details about the environment and style. A more general description framework is: Main subject and scene + Image quality and style + Composition and perspective + Lighting and atmosphere + Technical parameters . Keywords can be added both before and after this structure.
-
Image resolution : Our model not only supports multiple resolutions but also offers both automatic and specified resolution options. In auto mode, the model automatically predicts the image resolution based on the input prompt. In specified mode (like traditional DiT), the model outputs an image resolution that strictly aligns with the user's chosen resolution.
More Cases
Our model can follow complex instructions to generate highโquality, creative images.
Our model can effectively process very long text inputs, enabling users to precisely control the finer details of generated images. Extended prompts allow for intricate elements to be accurately captured, making it ideal for complex projects requiring precision and creativity.
Show promptA cinematic medium shot captures a single Asian woman seated on a chair within a dimly lit room, creating an intimate and theatrical atmosphere. The composition is focused on the subject, rendered with rich colors and intricate textures that evoke a nostalgic and moody feeling.\n\nThe primary subject is a young Asian woman with a thoughtful and expressive countenance, her gaze directed slightly away from the camera. She is seated in a relaxed yet elegant posture on an ornate, vintage armchair. The chair is upholstered in a deep red velvet, its fabric showing detailed, intricate textures and slight signs of wear. She wears a simple, elegant dress in a dark teal hue, the material catching the light in a way that reveals its fine-woven texture. Her skin has a soft, matte quality, and the light delicately models the contours of her face and arms.\n\nThe surrounding room is characterized by its vintage decor, which contributes to the historic and evocative mood. In the immediate background, partially blurred due to a shallow depth of field consistent with a f/2.8 aperture, the wall is covered with wallpaper featuring a subtle, damask pattern. The overall color palette is a carefully balanced interplay of deep teal and rich red hues, creating a visually compelling and cohesive environment. The entire scene is detailed, from the fibers of the upholstery to the subtle patterns on the wall.\n\nThe lighting is highly dramatic and artistic, defined by high contrast and pronounced shadow play. A single key light source, positioned off-camera, projects gobo lighting patterns onto the scene, casting intricate shapes of light and shadow across the woman and the back wall. These dramatic shadows create a strong sense of depth and a theatrical quality. While some shadows are deep and defined, others remain soft, gently wrapping around the subject and preventing the loss of detail in darker areas. The soft focus on the background enhances the intimate feeling, drawing all attention to the expressive subject. The overall image presents a cinematic, photorealistic photography style. |
Show promptA cinematic, photorealistic medium shot captures a high-contrast urban street corner, defined by the sharp intersection of light and shadow. The primary subject is the exterior corner of a building, rendered in a low-saturation, realistic style.\n\nThe building wall, which occupies the majority of the frame, is painted a warm orange with a finely detailed, rough stucco texture. Horizontal white stripes run across its surface. The base of the building is constructed from large, rough-hewn stone blocks, showing visible particles and texture. On the left, illuminated side of the building, there is a single window with closed, dark-colored shutters. Adjacent to the window, a simple black pendant lamp hangs from a thin, taut rope, casting a distinct, sharp-edged shadow onto the sunlit orange wall. The composition is split diagonally, with the right side of the building enveloped in a deep brown shadow. At the bottom of the frame, a smooth concrete sidewalk is visible, upon which the dynamic silhouette of a person is captured mid-stride, walking from right to left.\n\nIn the shallow background, the faint, out-of-focus outlines of another building and the bare, skeletal branches of trees are softly visible, contributing to the quiet urban atmosphere and adding a sense of depth to the scene. These elements are rendered with minimal detail to keep the focus on the foreground architecture.\n\nThe scene is illuminated by strong, natural sunlight originating from the upper left, creating a dramatic chiaroscuro effect. This hard light source casts deep, well-defined shadows, producing a sharp contrast between the brightly lit warm orange surfaces and the deep brown shadow areas. The lighting highlights the fine details in the wall texture and stone particles, emphasizing the photorealistic quality. The overall presentation reflects a high-quality photorealistic photography style, infused with a cinematic film noir aesthetic. |
Show promptไธๅน ๆๅ ท่ง่งๅผ ๅ็ๆๅฟๅฐ้ข้ฃๆ ผไบบๅ็นๅใ็ป้ขไธปไฝๆฏไธไธช่บซ็ๅค้ฃๆฑๆ็ไบบ็ฉ๏ผๆๅพ้็จไบไป่ฉ้จไปฅไธ็่ถ ็บง่ฟ่ท็ฆป็นๅ๏ผไบบ็ฉๅ ๆฎไบ็ป้ข็็ปๅคง้จๅ๏ผๅฝขๆไบๅผบ็็่ง่งๅฒๅปๅใ\n\n็ป้ขไธญ็ไบบ็ฉไปฅไธ็งๆ ตๆ็ๅงฟๆๅบ็ฐ๏ผๅพฎๅพฎๅพๆ็ๅคด้จ๏ผ่ฃธ้ฒ็ไธไพง่ฉ่็บฟๆกๆต็ ใๅฅนๆญฃ็จไธ็งๅฆฉๅช่็ดๆฅ็็ผ็ฅๅ่ง็้ๅคด๏ผๅ็ผๅพฎๅผ ๏ผ็ผ็ฅๆทฑ้๏ผไผ ้ๅบไธ็ง็ฅ็ง่ๅพไบบ็ๆฐ่ดจใไบบ็ฉ็้ข้จ็นๅพ็ฒพ่ด๏ผ็ฎ่ค่ดจๆ็ป่ ป๏ผๅจ็นๅฎ็ๅ ็บฟไธ๏ผ้ข้จ่ฝฎๅปๆธ ๆฐๅๆ๏ผๅฑ็ฐๅบไธ็งๅคๅ ธไธ็ฐไปฃ่ๅ็ๆถๅฐ็พๆใ\n\nๆดไธช็ป้ข็่ๆฏ่ขซ่ฎพๅฎไธบไธ็ง็ฎ็บฆ่้ซ็บง็็บฏ็บข่ฒใ่ฟ็ง็บข่ฒ่ฒ่ฐๆทฑๆฒ๏ผๅ็ฐๅบๅๅ ่ดจๆ๏ผๆข็บฏ็ฒนๅๆ ไปปไฝๆ่ดจ๏ผไธบๆดไธชๆ้ป็ฅ็ง็ๆฐๅดๅฅ ๅฎไบๆฒ็จณ่ๅฏๆๅผ ๅ็ๅบ่ฐใ่ฟไธช็บฏ่ฒ็่ๆฏๆๆๅฐ็ชๅบไบๅๆฏไธญ็ไบบ็ฉไธปไฝ๏ผไฝฟๅพๆๆ่ง่ง็ฆ็น้ฝ้ไธญๅจๅ ถ่บซไธใ\n\nๅ ็บฟๅๆฐๅด็่ฅ้ ๆฏ่ฟๅน ๆๅฟ้ฃๆตทๆฅ็ๅ ณ้ฎใไธๆๆๆฉ่ฒ็ๆๅๅ ็บฟไฝไธบไธปๅ ๆบ๏ผไปไบบ็ฉ็ไธไพงๆไธๆนๆๅฐไธๆฅ๏ผ็ฒพๅๅฐๅพๅๅบไบบ็ฉ็่ธ้ขใ้ผปๆขๅ่ฉ่็่ฝฎๅป๏ผๅจ็ฎ่คไธๅฝขๆๅพฎๅฆ็ๅ ๅฝฑ่ฟๆธกใๅๆถ๏ผไบบ็ฉ็ๅจ่บซ่ฆ็ป็ไธๅฑๆๆทกไธไฝ้ฅฑๅๅบฆ็้ถ็ฝ่ฒ่พๅ ๏ผๅฆๅๆธ ๅท็ๆๅ ๏ผๅฝขๆไธ้ๆฆ่ง็่ฝฎๅปๅ ใ่ฟ้้ถ่พไธบไบบ็ฉๅขๆทปไบๅ ๅ็็ฆป็ๅนฝ็ตๆ๏ผๅผบๅไบๆดไฝๆ้ป้ฃๆ ผ็็ฅ็งๆฐ่ดจใๅ ๅฝฑ็ๅผบ็ๅฏนๆฏไธ่ฒๅฝฉ็็ฌ็นๆญ้ ๏ผๅ ฑๅๅก้ ไบ่ฟๅผ ๅ ๆปกๆ ไบๆ็็นๅ็ป้ขใๆดไฝๅพๅๅ็ฐๅบไธ็ง่ๅไบๅคๅ ธๅ ็ด ็็ฐไปฃๆถๅฐๆๅฝฑ้ฃๆ ผใ |
Show promptไธๅน ้็จๆ็ฎไฟฏ่ง่ง่ง็ๆฒน็ปไฝๅ๏ผ็ป้ขไธปไฝ็ฑไธ้ๅฑ ไธญๆๅ็็บข่ฒ็ฌ่งฆๆๆใ\n\n่ฟ้้็ฎ็็บข่ฒ็ฌ่งฆ่ฟ็จไบๅๆถๆๆณ๏ผ้ขๆๅ ๅ ๅฝขๆไบๅผบ็็็ฉ็ๅๅบฆๅไธ็ปด็ซไฝๆใๅฎไป็ป้ข็ๅทฆไธ่ง้่ฟๅปถไผธ่ณๅณไธ่ง้่ฟ๏ผๆๆไธไธชๅจๆ็ๅฏน่ง็บฟใ้ขๆ่กจ้ขๅฏไปฅๆธ ๆฐๅฐ็ๅฐ็ปๅๅฎๆฆๅ็ฌๅทๆๆณ็ไธ็็่ฟน๏ผ่พน็ผๅค็้ขๆๅฑ็ธๅฏน่พ่๏ผ่ไธญๅคฎ้จๅๅ้ซ้ซ้่ตท๏ผๅฝขๆไบไธ่งๅ็่ตทไผใ\n\nๅจ่ฟ้็ซไฝ็็บข่ฒ้ขๆไนไธ๏ผๅทงๅฆๅฐๆๅปบไบไธๅค็ฒพ่ด็ๅพฎ็ผฉๆฏ่งใๆฏ่ง็ๆ ธๅฟๆฏไธ็ๆจกๆ็บขๆตทๆปฉ็ๅบๅ๏ผ็ฑ็ป่ ป็ๆทฑ็บข่ฒ้ขๆ็น็ผ่ๆ๏ผไธไธๆนๅบๅบ็้ฒ็บข่ฒๅฝขๆไธฐๅฏ็ๅฑๆฌกๅฏนๆฏใ็ดง้ป็โ็บขๆตทๆปฉโ็ๆฏไธๅฐ็ๆนๆณ๏ผ็ฑไธๅฑๅนณๆปไธๅธฆๆๅ ๆณฝ็่่ฒไธ็ฝ่ฒๆททๅ้ขๆๆๆ๏ผ่ดจๆๅฆๅๅนณ้ๆ ๆณข็ๆฐด้ขใๆนๆณ่พน็ผ๏ผไธๅฐๆฎ่ฆ่ไธ็๏ผ็ฑๅ ๆ น็บค็ปๆบๆ็ใ็จๆทก้ป่ฒๅๆฃ่ฒ้ขๆๅพๅๅบ็็บฟๆกๆฅ่กจ็ฐใไธๅชๅฐๅทง็็ฝ้นญ็ซไบ่ฆ่ๆ๏ผๅ ถๅฝขๆ็ฑไธๅฐๅ็บฏ็ฝ่ฒ็ๅๆถ้ขๆๅก้ ๏ผไป ็จไธๆน็ฒพ็ผ็้ป่ฒ้ขๆ็นๅบๅ ถๅฐๅ๏ผๅงฟๆไผ้ ๅฎ้ใ\n\nๆดไธชๆๅพ็่ๆฏๆฏๅคง้ข็งฏ็็็ฝ๏ผๅ็ฐไธบไธๅผ ๅธฆๆ็ปๅพฎๅนๅธ็บน็็็ฝ่ฒ็บธ่ดจๅบๅบ๏ผ่ฟ็งๆ็ฎๅค็ๆๅคงๅฐ็ชๅบไบไธญๅคฎ็็บข่ฒ็ฌ่งฆๅๅ ถไธ็ๅพฎ็ผฉๆฏ่งใ\n\nๅ ็บฟไป็ป้ขไธไพงๆๅๅฐ็ งๅฐไธๆฅ๏ผๅจๅๆถ็้ขๆๅ ๅ ๅคๆไธๆทกๆทก็ใ่ฝฎๅปๅๆ็้ดๅฝฑ๏ผ่ฟไธๆญฅๅขๅผบไบ็ป้ข็ไธ็ปด็ซไฝๆๅๆฒน็ป่ดจๆใๆดๅน ็ป้ขๅ็ฐๅบไธ็ง็ปๅไบๅๆถๆๆณ็็ฐไปฃๆ็ฎไธปไนๆฒน็ป้ฃๆ ผใ |
Show promptๆดไฝ็ป้ข้็จไธไธชไบไนไบ็ๅๅฎซๆ ผๅธๅฑ๏ผไปฅไบงๅๅฏ่งๅ็้ฃๆ ผ๏ผๅฑ็คบไบไธๅชๅ ๅญๅจๅ็งไธๅๆ่ดจไธ็ๆธฒๆๆๆใๆฏไธชๅฎซๆ ผๅ ้ฝๆไธๅชๅงฟๆๅฎๅ จ็ธๅ็ๅ ๅญๆจกๅ๏ผๅฎๅๅๅงฟ๏ผๅ่ณ็ซ็ซ๏ผ้ขๆๅๆนใๆๆๅฎซๆ ผ็่ๆฏๅๆฏ็ปไธ็ไธญๆงๆทฑ็ฐ่ฒ๏ผ่ฟ็ง็ฎ็บฆ่ๆฏๆจๅจๆๅคง้ๅบฆๅฐ็ชๅบๆฏ็งๆ่ดจ็็ฌ็น่ดจๆใ\n\nๅทฆไธ่ง็ๅฎซๆ ผไธญ๏ผๅ ๅญๆจกๅ็ฑๅๅ ็ฝ่ฒ็ณ่ๆ่ดจๆๆใๅ ถ่กจ้ขๅนณๆปใๅๅไธๆ ๅๅฐ๏ผๅจๆจกๅ็่ณๆตๆ น้จใๅ่ขไบคๆฅๅค็ญๅน้ทๅบๅๅ็ฐๅบๆๅ็็ฏๅขๅ ้ฎ่ฝ้ดๅฝฑ๏ผ่ฟ็งๅพฎๅฆ็้ดๅฝฑๅๅๅธๆพไบๅ ถ็บฏ็ฒน็ๅ ไฝๅฝขๆ๏ผๆดไฝๆ่งๅไธไธช็จไบ็พๆฏ็ ็ฉถ็ๅบ็กๆจกๅใ\n\nๅณไธ่ง็ๅฎซๆ ผไธญ๏ผๅ ๅญๆจกๅ็ฑๆถ่นๅ้็ๆ ็็ต็ป็ๅถๆใๅฎๅฑ็ฐไบ้ผ็็็ฉ็ๆๅฐๆๆ๏ผ้่ฟๅ ถ้ๆ็่บซไฝ็ๅฐ็่ๆฏๅ็ฐๅบ่ฝปๅพฎ็ๆญๆฒใๆธ ๆฐ็้้ข้ซๅ ๆฒฟ็ๅ ถ่บซไฝ็ๆฒ็บฟ่ฝฎๅปๆตๅจ๏ผ่กจ้ขไธ่ฟ่ฝ็ๅฐๅพฎๅผฑ่ๆธ ๆฐ็็ฏๅขๅๅฐ๏ผ่ตไบๅ ถไธ็ง็ฒพ่ด่ๆ็ข็่ดจๆใ\n\nๅทฆไธ่ง็ๅฎซๆ ผไธญ๏ผๅ ๅญๆจกๅๅ็ฐไธบๅธฆๆๆไธ็บน็็้้ๅฑๆ่ดจใ้ๅฑ่กจ้ขๅ ทๆๆๆพ็ๅๅๅผๆงๅๅฐๆๆ๏ผๅ็ฐๅบๅทๅณป็็ฐ่ฐ้ๅฑๅ ๆณฝใ้ๅฉๆไบฎ็้ซๅ ๅๆทฑ้็้ดๅฝฑๅฝขๆไบๅผบ็ๅฏนๆฏ๏ผ็ฒพ็กฎๅฐๅฎไนไบๅ ถๅๅบ็ไธ็ปดๅฝขๆ๏ผๅฑ็ฐไบๅทฅไธ่ฎพ่ฎก่ฌ็็พๆใ\n\nๅณไธ่ง็ๅฎซๆ ผไธญ๏ผๅ ๅญๆจกๅ่ฆ็็ไธๅฑๆ่ฝฏๆตๅฏ็็ฐ่ฒๆฏ็ปใๆ นๆ นๅๆ็็ปๆฏๆธ ๆฐๅฏ่ง๏ผๅ้ ๅบไธ็งๆธฉๆใๅฏ่งฆๆธ็่ดจๅฐใๅ ็บฟ็ งๅฐๅจ็ปๆฏ็ๆซๆขข๏ผๅฝขๆๆๅ็ๅ ๆๆๆ๏ผ่ๆฏ็ปๅ ้จ็้ดๅฝฑๅๆพๅพๆทฑ้่ๆ่ฝฏ๏ผๅฑ็ฐไบ้ซๅบฆๅๅฎ็ๆฏๅๆธฒๆๆๆใ\n\nๆดไธชๅๅฎซๆ ผ็ฑๆฅ่ชๅคไธชๆนๅ็ใๆๅๅๅ็ๅฝฑๆฃ็ฏๅ ็ งไบฎ๏ผ็กฎไฟไบๆฏ็งๆ่ดจ็็ป่ๅ็นๆง้ฝๅพๅฐๆธ ๆฐ็ๅฑ็ฐ๏ผๆฒกๆไปปไฝๅบ็ผ็้ดๅฝฑๆ่ฟๆ็้ซๅ ใ่ฟๅผ ๅพๅไปฅไธ็ง้ซๅบฆๅๅฎ็3Dๆธฒๆ้ฃๆ ผๅ็ฐ๏ผๅฎ็พๅฐ่ฏ ้ไบไบงๅๅฏ่งๅ็็ฒพ้ซ |
Show prompt็ฑไธไธชไธค่กไธคๅ็็ฝๆ ผๆๆ๏ผๅ ฑๅ ๅซๅไธช็ฌ็ซ็ๅบๆฏ๏ผๆฏไธชๅบๆฏ้ฝไปฅไธๅ็่บๆฏ้ฃๆ ผๆ็ปไบไธไธชๅฐ็ทๅญฉ๏ผๅฐๆ๏ผไธๅคฉไธญ็ไธๅๆดปๅจใ\n\nๅทฆไธ่ง็็ฌฌไธไธชๅบๆฏ๏ผไปฅ่ถ ๅๅฎๆๅฝฑ้ฃๆ ผๅ็ฐใ็ป้ขไธปไฝๆฏไธไธชๅคง็บฆ8ๅฒ็ไธไบๅฐ็ทๅญฉ๏ผไป็ฉฟ็ๆดๆด็ๅฐๅญฆๅถๆโโไธไปถ็ฝ่ฒ็ญ่ข่กฌ่กซๅ่่ฒ็ญ่ฃค๏ผ่ๅญไธ็ณป็็บข้ขๅทพใไป่็ไธไธช่่ฒ็ๅ่ฉไนฆๅ ๏ผๆญฃ่ตฐๅจๅปไธๅญฆ็่ทฏไธใไปไฝไบ็ป้ข็ๅๆฏๅๅณไพง๏ผ้ขๅธฆๅพฎ็ฌ๏ผๆญฅไผ่ฝปๅฟซใๅบๆฏ่ฎพๅฎๅจๆธ ๆจ๏ผๆๅ็้ณๅ ไปๅทฆไธๆน็ งๅฐไธๆฅ๏ผๅจไบบ่ก้ไธๆไธๆธ ๆฐ่ๆๅ็ๅฝฑๅญใ่ๆฏๆฏ็ปฟๆ ๆ่ซ็่ก้ๅๆจก็ณๅฏ่ง็ๅญฆๆ ก้่บๅคง้จ๏ผ่ฅ้ ๅบๅฎ้็ๆฉๆจๆฐๅดใ่ฟๅผ ๅพ็็็ป่่กจ็ฐๆไธบไธฐๅฏ๏ผๅฏไปฅๆธ ๆฐๅฐ็ๅฐ็ทๅญฉๅคดๅ็ๅ ๆณฝใ่กฃๆ็่คถ็ฑ็บน็ไปฅๅไนฆๅ ็ๅธๅธๆ่ดจ๏ผๅฎๅ จๅฑ็ฐไบไธไธๆๅฝฑ็่ดจๆใ\n\nๅณไธ่ง็็ฌฌไบไธชๅบๆฏ๏ผ้็จๆฅๅผ่ต็็ๅจๆผซ้ฃๆ ผ็ปๅถใ็ป้ขไธญ๏ผๅฐ็ทๅญฉๅๅจๅฎถไธญ็ๆจ่ดจ้คๆกๆๅๅ้ฅญใไป็ๅฝข่ฑก่ขซๅจๆผซๅ๏ผๆฅๆๅคง่ๆไบฎ็็ผ็ๅ็ฎๆด็ไบๅฎ็บฟๆกใไป่บซ็ฉฟไธไปถ็ฎๅ็้ป่ฒTๆค๏ผๆญฃ็จ็ญทๅญๅคน่ตท็ข้็็ฑณ้ฅญใๆกไธๆๆพ็ไธ็ขๆฑคๅไธค็ๅฎถๅธธ่ใ่ๆฏๆฏไธไธชๆธฉ้ฆจ็ๅฎคๅ ็ฏๅข๏ผไธๆๆไบฎ็็ชๆท้่ฟๆญฃๅ็้ณๅ ๏ผ็ชๅคๆฏ่ๅคฉ็ฝไบใๆดไธช็ป้ข่ฒๅฝฉ้ฒ่ณใ้ฅฑๅๅบฆ้ซ๏ผ่ง่ฒ่ฝฎๅป็บฟๆธ ๆฐๆ็กฎ๏ผ้ดๅฝฑ้จๅ้็จๅนณๆถ็่ฒๅๅค็๏ผๆฏๅ ธๅ็่ต็็ๅจๆผซ้ฃๆ ผใ\n\nๅทฆไธ่ง็็ฌฌไธไธชๅบๆฏ๏ผไปฅ็ป่ ป็้ ็ฌ็ด ๆ้ฃๆ ผๅ็ฐใ็ป้ขๆ็ปไบไธๅๅจๆๅบไธ่ธข่ถณ็็ๅฐ็ทๅญฉใๆดไธชๅพๅ็ฑไธๅ็ฐๅบฆ็็ณๅขจ่ฒ่ฐๆๆ๏ผๆฒกๆๅ ถไป้ข่ฒใๅฐ็ทๅญฉ่บซ็ฉฟ่ฟๅจ็ญ่ขๅ็ญ่ฃค๏ผ่บซไฝๅๅๅพๅงฟๆ๏ผๅณ่ๆญฃ่ฆ่ธขๅไธไธช่ถณ็๏ผๅจไฝๅ ๆปกๅจๆใ่ๆฏๆฏ็ฉบๆท็ๆๅบๅ่ฟๅค็็้จ๏ผ็จ็ฎ็ป็็บฟๆกๅๆ็บฟๅพๅใ่บๆฏๅฎถ้่ฟไบคๅๆ็บฟๅๆถๆนๆๅทงๆฅ่กจ็ฐๅ ๅฝฑๅไฝ็งฏๆ๏ผ่ถณ็ไธ็้ดๅฝฑใไบบ็ฉ่บซไธ็่่็บฟๆกไปฅๅๅฐ้ข็ฒ็ณ็่ดจๆ้ฝ้่ฟ้ ็ฌ็็ฌ่งฆๅพๅฐไบๅ ๅ็ๅฑ็ฐใ่ฟๅผ ้ ็ฌ็ป็ชๅบไบ็ด ๆ็ๅ ๅฝฑๅ ณ็ณปๅ็บฟๆก็พๆใ\n\nๅณไธ่ง็็ฌฌๅไธชๅบๆฏ๏ผไปฅๆๆฃฎ็นยทๆขต้ซ็ๅๅฐ่ฑกๆดพๆฒน็ป้ฃๆ ผ่ฟ่ก่ฏ ้ใ็ป้ขๆ็ปไบๅคๆๆถๅ๏ผๅฐ็ทๅญฉ็ฌ่ชๅจๆฒณ่พน้้ฑผ็ๆฏ่ฑกใไปๅๅจไธๅๅฒฉ็ณไธ๏ผๆๆไธๆ น็ฎๆ็้้ฑผ็ซฟ๏ผ่บซๅฝฑๅจๆทฑ่่ฒ็ๅคๅนไธๆพๅพๅพๆธบๅฐใๆดไธช็ป้ข็่ง่ง็ฆ็นๆฏๅคฉ็ฉบๅๆฐด้ข๏ผๅคฉ็ฉบๅธๆปกไบๆ่ฝฌใๅทๆฒ็ๆไบ๏ผๆๆๅๆไบฎ่ขซๆ็ปๆๅทจๅคงใๅๅ ็ๅ ๅข๏ผไฝฟ็จไบๅๆถ็ๆฒน็ป้ขๆ๏ผImpasto๏ผ๏ผ็ฌ่งฆ็ฒ็ท่ๅ ๆปก่ฝ้ใๆทฑ่ใไบฎ้ปๅ็ฝ่ฒ็้ขๆๅจ็ปๅธไธ็ธไบไบค็ป๏ผๅฝขๆๅผบ็็่ง่งๅฒๅปๅใๆฐด้ขๅๆ ็ๅคฉ็ฉบไธญๆญๆฒ็ๅ ๅฝฑ๏ผๆดไธชๅบๆฏๅ ๆปกไบๆขต้ซไฝๅไธญ็นๆ็ๅผบ็ๆ ๆๅๅจ่กไธๅฎ็็พๆใ่ฟๅน ็ปไฝๆฏๅฏนๆขต้ซ้ฃๆ ผ็ๆทฑๅบฆ่ดๆฌใ |
Show promptไปฅๅนณ่ง่ง่ง๏ผๅ็ฐไบไธๅน ๅ ณไบๅฆไฝ็จ็ด ๆๆๆณ็ปๅถ้นฆ้น็ไนๅฎซๆ ผๆๅญฆๅพใๆดไฝๆๅพ่งๆด๏ผไนไธชๅคงๅฐไธ่ด็ๆนๅฝข็ปๆกไปฅไธ่กไธๅ็ๅฝขๅผๅๅๅๅธๅจๆต ็ฐ่ฒ่ๆฏไธ๏ผๆธ ๆฐๅฐๅฑ็คบไบไปๅบๆฌๅฝข็ถๅฐๆ็ปๆๅ็ๅ จ่ฟ็จใ\n\n็ฌฌไธ่กไปๅทฆ่ณๅณๅฑ็คบไบ็ป็ป็ๅๅงๆญฅ้ชคใๅทฆไธ่ง็็ฌฌไธไธช็ปๆกไธญ๏ผ็จ็ฎๆด็้ ็ฌ็บฟๆกๅพๅๅบ้นฆ้น็ๅบๆฌๅ ไฝๅฝขๆ๏ผไธไธชๅๅฝขไปฃ่กจๅคด้จ๏ผไธไธช็จๅคง็ๆคญๅๅฝขไปฃ่กจ่บซไฝใๅณไธ่งๆไธไธชๅฐๅท็ๆ ่กฌ็บฟๅญไฝๆฐๅญโ1โใไธญ้ด็็ฌฌไบไธช็ปๆกไธญ๏ผๅจๅบ็กๅฝขๆไธๆทปๅ ไบไธ่งๅฝข็้ธๅ่ฝฎๅปๅไธๆก้ฟ้ฟ็ๅผง็บฟไฝไธบๅฐพๅทด็้ๅฝข๏ผๅคด้จๅ่บซไฝ็่ฟๆฅๅค็บฟๆกๅๅพๆดๅ ๆต็ ๏ผๅณไธ่งๆ ๆๆฐๅญโ2โใๅณไพง็็ฌฌไธไธช็ปๆกไธญ๏ผ่ฟไธๆญฅ็ฒพ็กฎไบ้นฆ้น็ๆดไฝ่ฝฎๅป๏ผๅพๅๅบๅคด้จ้กถ็ซฏ็็พฝๅ ๅๆธ ๆฐ็็ผ้จๅๅฝข่ฝฎๅป๏ผๅณไธ่งๆ ๆๆฐๅญโ3โใ\n\n็ฌฌไบ่กไธๆณจไบ็ปๆไธ็ป่็ๆทปๅ ๏ผๆ็ปไบ็ป็ป็ไธญๆ้ถๆฎตใๅทฆไพง็็ฌฌๅไธช็ปๆก้๏ผ้นฆ้น็่บซไฝไธๆทปๅ ไบ็ฟ ่็ๅบๆฌๅฝข็ถ๏ผๅๆถๅจ่บซไฝไธๆน็ปๅบไบไธๆ นไฝไธบๆ ๆจ็ๆจชๅๆ ๆ๏ผ้นฆ้น็็ชๅญๅๆญฅๆญๅจๆ ๆไธ๏ผๅณไธ่งๆ ๆๆฐๅญโ4โใไธญ้ด็็ฌฌไบไธช็ปๆกไธญ๏ผๅผๅง็ปๅ็ฟ ่ๅๅฐพ้จ็็พฝๆฏๅ็ป๏ผ็จ็ญไฟ็็บฟๆก่กจ็ฐๅบๅฑๆฌกๆ๏ผๅนถๆธ ๆฐๅฐ็ปๅบ็ชๅญ็ดงๆกๆ ๆ็็ป่๏ผๅณไธ่งๆ ๆๆฐๅญโ5โใๅณไพง็็ฌฌๅ ญไธช็ปๆก้๏ผๅผๅงไธบ้นฆ้นๆทปๅ ๅๆญฅ็้ดๅฝฑ๏ผไฝฟ็จไบคๅๆ็บฟ็็ด ๆๆๆณๅจ่ น้จใ็ฟ ่ไธๆนๅ้ข้จๅถ้ ๅบไฝ็งฏๆ๏ผๅณไธ่งๆ ๆๆฐๅญโ6โใ\n\n็ฌฌไธ่กๅๅฑ็คบไบๆ็ป็ๆถฆ่ฒไธๅฎๆ้ถๆฎตใๅทฆไธ่ง็็ฌฌไธไธช็ปๆกไธญ๏ผ็ด ๆ็ๆ็บฟๆดๅ ๅฏ้๏ผ้ดๅฝฑๅฑๆฌกๆดๅ ไธฐๅฏ๏ผ็พฝๆฏ็็บน็็ป่่ขซไป็ปๅป็ปๅบๆฅ๏ผ็ผ็ ไนๆทปๅ ไบ้ซๅ ็น็ผ๏ผๆพๅพ็ฏ็ฏๆ็ฅ๏ผๅณไธ่งๆ ๆๆฐๅญโ7โใไธญ้ด็็ฌฌๅ ซไธช็ปๆก้๏ผๆ็ป็้็น่ฝฌ็งปๅฐๆ ๆจไธ๏ผๅขๅ ไบๆ ๆ็็บน็ๅ่็ค็ป่๏ผๅๆถๆดไฝ่ฐๆดไบ้นฆ้น่บซไธ็ๅ ๅฝฑๅ ณ็ณป๏ผไฝฟ็ซไฝๆๆดไธบ็ชๅบ๏ผๅณไธ่งๆ ๆๆฐๅญโ8โใๅณไธ่ง็็ฌฌไนไธช็ปๆกๆฏๆ็ปๅฎๆๅพ๏ผๆๆ็บฟๆก้ฝ็ป่ฟไบ็ฒพ็ผ๏ผๅ ๅฝฑๅฏนๆฏๅผบ็๏ผ้นฆ้น็็พฝๆฏ่ดจๆใๆจ่ดจๆ ๆจ็็ฒ็ณๆ้ฝ่กจ็ฐๅพๆทๆผๅฐฝ่ด๏ผๅ็ฐๅบไธๅน ๅฎๆดไธ็ป่ไธฐๅฏ็็ด ๆไฝๅ๏ผๅณไธ่งๆ ๆๆฐๅญโ9โใ\n\nๆดไธช็ป้ข็ๅ ็บฟๅๅ่ๆไบฎ๏ผๆฒกๆไปปไฝ็นๅฎ็ๅ ๆบๆนๅ๏ผ็กฎไฟไบๆฏไธชๆๅญฆๆญฅ้ชค็่ง่งๆธ ๆฐๅบฆใๆดไฝๅ็ฐๅบไธ็งๆธ ๆฐใๆๆก็็ๆฐๅญๆ็ปๆ็จ้ฃๆ ผใ |
Show promptไธๅผ ็ฐไปฃๅนณ้ข่ฎพ่ฎก้ฃๆ ผ็ๆตทๆฅๅ ๆฎไบๆดไธช็ป้ข๏ผๆๅพ็ฎๆดไธไธญๅฟ็ชๅบใ\n\nๆตทๆฅ็ไธปไฝๆฏไฝไบ็ป้ขๆญฃไธญๅคฎ็ไธๅช่ พ่ฎฏQQไผ้น ใ่ฟๅชไผ้น ้็จไบๅๆถฆๅฏ็ฑ็3Dๅก้ๆธฒๆ้ฃๆ ผ๏ผ่บซไฝไธป่ฆไธบ้ฅฑๆปก็้ป่ฒ๏ผ่ น้จไธบ็บฏ็ฝ่ฒใๅฎ็็ผ็ๅคง่ๅ๏ผ็ผ็ฅๅฅฝๅฅๅฐ็ด่งๅๆนใ้ป่ฒ็ๅดๅทดๅฐๅทง่็ซไฝ๏ผๅ่ๅๆ ทไธบ้ฒๆ็้ป่ฒ๏ผ็จณ็จณๅฐ็ซ็ซ็ใไธๆกๆ ๅฟๆง็็บข่ฒๅดๅทพๆด้ฝๅฐ็ณปๅจๅฎ็่ๅญไธ๏ผๅดๅทพ็ๆ่ดจๅธฆๆ่ฝปๅพฎ็ๅธๆ่ดจๆ๏ผๆซ็ซฏ่ช็ถไธๅใไผ้น ็ๆดไฝ้ ๅๅนฒๅๅฉ่ฝ๏ผ่พน็ผๅ ๆป๏ผๅ็ฐๅบไธ็ง็ฒพ่ด็ๆฐๅญๆ็ป่ดจๆใ\n\nๆตทๆฅ็่ๆฏๆฏไธ็งไปไธๅฐไธ็ฑๆต ่่ฒๅนณๆป่ฟๆธกๅฐ็ฝ่ฒ็ๆๅๆธๅ๏ผ่ฅ้ ๅบไธ็งๅผ้ใๆไบฎ็็ฉบ้ดๆใๅจไผ้น ็่บซๅ๏ผๆฃๅธ็ไธไบๆทกๆทก็ใๆจก็ณ็ๅๅฝขๅ ๆๅๅ ้ๆๅ็ๆฝ่ฑกๅ ๆ๏ผไธบ่ฟไธช็ฎ็บฆ็ๅนณ้ข่ฎพ่ฎกๆตทๆฅๅขๆทปไบๅพฎๅฆ็ๆทฑๅบฆๅ็งๆๆใ\n\n็ป้ข็ๅบ้จๅบๅๆฏๆๅญ้จๅ๏ผๆ็ๅฑ ไธญๅฏน้ฝใไธๅ้จๅๆฏไธ่ก็จๅคง็้ป่ฒ้ปไฝๅญ๏ผๅ ๅฎนไธบโHunyuan Image 3.0โใ็ดง้ๅ ถไธ็ๆฏไธ่กๅญๅท็ฅๅฐ็ๆทฑ็ฐ่ฒ้ปไฝๅญ๏ผๅ ๅฎนไธบโๅ็ๅคๆจกๆๅคงๆจกๅโใไธค่กๆๅญๆธ ๆฐๆ่ฏป๏ผไธๆดไฝ็็ฐไปฃๅนณ้ข่ฎพ่ฎก้ฃๆ ผไฟๆไธ่ดใ\n\nๆดไฝๅ ็บฟๆไบฎใๅๅ๏ผๆฒกๆๆๆพ็้ดๅฝฑ๏ผ็ชๅบไบไผ้น ๅๆๅญไฟกๆฏ๏ผ็ฌฆๅ็ฐไปฃ่ฎพ่ฎกๆตทๆฅ็่ง่ง่ฆๆฑใ่ฟๅผ ๅพๅๅ็ฐไบ็ฐไปฃใ็ฎๆด็ๅนณ้ข่ฎพ่ฎกๆตทๆฅ้ฃๆ ผใ |
๐ Evaluation
-
๐ค
SSAE (Machine Evaluation)
SSAE (Structured Semantic Alignment Evaluation) is an intelligent evaluation metric for image-text alignment based on advanced multimodal large language models (MLLMs). We extracted 3500 key points across 12 categories, then used multimodal large language models to automatically evaluate and score by comparing the generated images with these key points based on the visual content of the images. Mean Image Accuracy represents the image-wise average score across all key points, while Global Accuracy directly calculates the average score across all key points.
- ๐ฅ GSB (Human Evaluation)
We adopted the GSB (Good/Same/Bad) evaluation method commonly used to assess the relative performance between two models from an overall image perception perspective. In total, we utilized 1,000 text prompts, generating an equal number of image samples for all compared models in a single run. For a fair comparison, we conducted inference only once for each prompt, avoiding any cherry-picking of results. When comparing with the baseline methods, we maintained the default settings for all selected models. The evaluation was performed by more than 100 professional evaluators.
๐ Citation
If you find HunyuanImage-3.0 useful in your research, please cite our work:
@misc{HunyuanImage-3.0,
title={HunyuanImage 3.0: Technical Report},
author={Tencent Hunyuan Team},
year={2025},
howpublished={\url{https://github.com/Tencent-Hunyuan/HunyuanImage-3.0}},
}
๐ Acknowledgements
We extend our heartfelt gratitude to the following open-source projects and communities for their invaluable contributions:
- ๐ค Transformers - State-of-the-art NLP library
- ๐จ Diffusers - Diffusion models library
- ๐ HuggingFace - AI model hub and community
- โก FlashAttention - Memory-efficient attention
- ๐ FlashInfer - Optimized inference engine
Runs of tencent HunyuanImage-3.0-Instruct on huggingface.co
17.6K
Total runs
0
24-hour runs
1.1K
3-day runs
102
7-day runs
-156
30-day runs
More Information About HunyuanImage-3.0-Instruct huggingface.co Model
Url of HunyuanImage-3.0-Instruct
HunyuanImage-3.0-Instruct huggingface.co Url
Provider of HunyuanImage-3.0-Instruct huggingface.co
Other API from tencent
Total runs:
331.5K
Run Growth:
94.3K
Growth Rate:
28.45%
Total runs:
319.1K
Run Growth:
289.1K
Growth Rate:
90.62%
Total runs:
117.0K
Run Growth:
23.0K
Growth Rate:
19.65%
Total runs:
90.7K
Run Growth:
-582.4K
Growth Rate:
-642.43%
Total runs:
67.6K
Run Growth:
22.7K
Growth Rate:
33.61%
Total runs:
56.9K
Run Growth:
-323
Growth Rate:
-0.57%
Total runs:
51.4K
Run Growth:
37.1K
Growth Rate:
72.13%
Total runs:
43.2K
Run Growth:
42.8K
Growth Rate:
99.15%
Total runs:
35.8K
Run Growth:
8.6K
Growth Rate:
23.97%
Total runs:
24.5K
Run Growth:
14.7K
Growth Rate:
59.79%
Total runs:
19.3K
Run Growth:
12.1K
Growth Rate:
63.02%
Total runs:
18.5K
Run Growth:
14.5K
Growth Rate:
78.37%
Total runs:
16.4K
Run Growth:
7.6K
Growth Rate:
46.27%
Total runs:
15.9K
Run Growth:
-3.1K
Growth Rate:
-19.78%
Total runs:
11.8K
Run Growth:
4.2K
Growth Rate:
35.38%
Total runs:
10.9K
Run Growth:
-12.0K
Growth Rate:
-109.36%
Total runs:
6.1K
Run Growth:
6.1K
Growth Rate:
100.00%
Total runs:
6.0K
Run Growth:
3.4K
Growth Rate:
56.59%
Total runs:
4.1K
Run Growth:
-736
Growth Rate:
-17.90%
Total runs:
3.9K
Run Growth:
3.7K
Growth Rate:
96.40%
Total runs:
3.8K
Run Growth:
1.3K
Growth Rate:
33.52%
Total runs:
3.4K
Run Growth:
-5.4K
Growth Rate:
-157.29%
Total runs:
3.2K
Run Growth:
2.7K
Growth Rate:
84.26%
Total runs:
3.0K
Run Growth:
-152
Growth Rate:
-5.06%
Total runs:
2.6K
Run Growth:
-2.4K
Growth Rate:
-91.58%
Total runs:
2.5K
Run Growth:
-781
Growth Rate:
-31.40%
Total runs:
2.4K
Run Growth:
-1.6K
Growth Rate:
-69.61%
Total runs:
1.8K
Run Growth:
327
Growth Rate:
17.71%
Total runs:
1.7K
Run Growth:
-873
Growth Rate:
-51.17%
Total runs:
1.6K
Run Growth:
20
Growth Rate:
1.24%
Total runs:
1.5K
Run Growth:
-204
Growth Rate:
-13.56%
Total runs:
1.4K
Run Growth:
1.2K
Growth Rate:
82.02%
Total runs:
1.4K
Run Growth:
954
Growth Rate:
70.10%
Total runs:
1.2K
Run Growth:
-680
Growth Rate:
-55.42%
Total runs:
1.2K
Run Growth:
-897
Growth Rate:
-76.80%
Total runs:
1.1K
Run Growth:
732
Growth Rate:
64.89%
Total runs:
984
Run Growth:
487
Growth Rate:
49.49%
Total runs:
730
Run Growth:
567
Growth Rate:
77.67%
Total runs:
719
Run Growth:
264
Growth Rate:
36.72%
Total runs:
696
Run Growth:
352
Growth Rate:
50.57%
Total runs:
693
Run Growth:
-114
Growth Rate:
-16.45%
Total runs:
600
Run Growth:
196
Growth Rate:
32.67%
Total runs:
587
Run Growth:
372
Growth Rate:
63.37%
Total runs:
541
Run Growth:
182
Growth Rate:
33.64%
Total runs:
526
Run Growth:
-104
Growth Rate:
-19.77%
Total runs:
503
Run Growth:
-1.6K
Growth Rate:
-324.06%
Total runs:
480
Run Growth:
79
Growth Rate:
16.46%
Total runs:
456
Run Growth:
149
Growth Rate:
32.68%
Total runs:
443
Run Growth:
194
Growth Rate:
43.79%
Total runs:
426
Run Growth:
275
Growth Rate:
64.55%
Total runs:
418
Run Growth:
418
Growth Rate:
100.00%
Total runs:
399
Run Growth:
234
Growth Rate:
58.65%
Total runs:
352
Run Growth:
62
Growth Rate:
17.61%
Total runs:
322
Run Growth:
238
Growth Rate:
73.91%
Total runs:
317
Run Growth:
-81
Growth Rate:
-25.55%
Total runs:
308
Run Growth:
126
Growth Rate:
40.91%
Total runs:
297
Run Growth:
-416
Growth Rate:
-140.07%
Total runs:
292
Run Growth:
181
Growth Rate:
61.99%
Total runs:
290
Run Growth:
-86
Growth Rate:
-29.66%
Total runs:
288
Run Growth:
145
Growth Rate:
50.35%
Total runs:
280
Run Growth:
-137
Growth Rate:
-48.93%
Total runs:
277
Run Growth:
-69
Growth Rate:
-24.91%
Total runs:
273
Run Growth:
94
Growth Rate:
34.43%
Total runs:
269
Run Growth:
-264
Growth Rate:
-98.14%
Total runs:
260
Run Growth:
27
Growth Rate:
10.38%
Total runs:
240
Run Growth:
97
Growth Rate:
40.42%
Total runs:
235
Run Growth:
103
Growth Rate:
43.83%
Total runs:
227
Run Growth:
42
Growth Rate:
18.50%
Total runs:
224
Run Growth:
100
Growth Rate:
44.64%