Trending Buzz About

q-future/one-align

Model

The model that corresponds to Q-Align (ICML2024).

46

54 commits

1 linked in READMEs

updated May 14, 2024

README

The model that corresponds to Q-Align (ICML2024).

Quick Start with AutoModel

For this image, start an AutoModel scorer with transformers==4.36.1:

import requests
import torch
from transformers import AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained("q-future/one-align", trust_remote_code=True, attn_implementation="eager", 
                                             torch_dtype=torch.float16, device_map="auto")

from PIL import Image
url = "https://raw.githubusercontent.com/Q-Future/Q-Align/main/fig/singapore_flyer.jpg"
image = Image.open(requests.get(url,stream=True).raw)
model.score([image], task_="quality", input_="image")
# task_ : quality | aesthetics; # input_: image | video

Result should be 1.911 (in range [1,5], higher is better).

From paper: arxiv.org/abs/2312.17090.

Syllabus

IQA Results (Spearman/Pearson/Kendall)

Datasets	KonIQ (NR-IQA, seen)	SPAQ (NR-IQA, Seen)	KADID (FR-IQA, Seen)	LIVE-C (NR-IQA, Unseen)	LIVE (FR-IQA, Unseen)	CSIQ (FR-IQA, Unseen)	AGIQA (AIGC, Unseen)
Previous SOTA	0.916/0.928 (MUSIQ, ICCV2021)	0.922/0.919 (LIQE, CVPR2023)	0.934/0.937 (CONTRIQUE, TIP2022)	NA	NA	NA	NA
Q-Align (IQA)	0.937/0.945/0.785	0.931/0.933/0.763	0.934/0.934/0.777	0.887/0.896/0.706	0.874/0.840/0.682	0.845/0.876/0.654	0.731/0.791/0.529
Q-Align (IQA+VQA)	0.944/0.949/0.797	0.931/0.934/0.764	0.952/0.953/0.809	0.892/0.899/0.715	0.874/0.846/0.684	0.852/0.876/0.663	0.739/0.782/0.526
OneAlign (IQA+IAA+VQA)	0.941/0.950/0.791	0.932/0.935/0.766	0.941/0.942/0.791	0.881/0.894/0.699	0.887/0.856/0.699	0.881/0.906/0.699	0.801/0.838/0.602

IAA Results (Spearman/Pearson)

Dataset	AVA_test
VILA (CVPR, 2023)	0.774/0.774
LIQE (CVPR, 2023)	0.776/0.763
Aesthetic Predictor (retrained on AVA_train)	0.721/0.723
Q-Align (IAA)	0.822/0.817
OneAlign (IQA+IAA+VQA)	0.823/0.819

VQA Results (Spearman/Pearson)

Datasets	LSVQ_test	LSVQ_1080p	KoNViD-1k	MaxWell_test
SimpleVQA (ACMMM, 2022)	0.867/0.861	0.764/0.803	0.840/0.834	0.720/0.715
FAST-VQA (ECCV 2022)	0.876/0.877	0.779/0.814	0.859/0.855	0.721/0.724
Q-Align (VQA)	0.883/0.882	0.797/0.830	0.865/0.877	0.780/0.782
Q-Align (IQA+VQA)	0.885/0.883	0.802/0.829	0.867/0.880	0.781/0.787
OneAlign (IQA+IAA+VQA)	0.886/0.886	0.803/0.837	0.876/0.888	0.781/0.786

custom_code

feature-extraction

mplug_owl2

pytorch

transformers

zero-shot-image-classification

Similar repos

Q-Future/Q-Align

③[ICML2024] [IQA, IAA, VQA] All-in-one Foundation Model for visual scoring. Can efficiently…

627

chaofengc/Awesome-Image-Quality-Assessment

A comprehensive collection of IQA papers

1,542

TianheWu/VisualQuality-R1

[NeurIPS 2025 Spotlight] VisualQuality-R1 is the first open-sourced NR-IQA model can accurately…

201

CodeGoat24/UnifiedReward-qwen-3b

UnifiedReward-qwen-3B

1

chancharikmitra/t2v_metrics

Evaluating text-to-image/video/3D models with VQAScore

4

osunlp/UGround-V1-2B

UGround-V1-2B （Qwen2-VL-Based)

11

TianheWu/VisualQuality-R1-7B

VisualQuality-R1-7B

15

osunlp/UGround-V1-7B

UGround-V1-7B （Qwen2-VL-Based)

21

Linked in READMEs

AMAP-ML/VMBench

[ICCV 25] VMBench: A Benchmark for Perception-Aligned Video Motion Generation

76

q-future/one-align

Model

The model that corresponds to Q-Align (ICML2024).

46

54 commits

1 linked in READMEs

updated May 14, 2024

README

The model that corresponds to Q-Align (ICML2024).

Quick Start with AutoModel

For this image, start an AutoModel scorer with transformers==4.36.1:

import requests
import torch
from transformers import AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained("q-future/one-align", trust_remote_code=True, attn_implementation="eager", 
                                             torch_dtype=torch.float16, device_map="auto")

from PIL import Image
url = "https://raw.githubusercontent.com/Q-Future/Q-Align/main/fig/singapore_flyer.jpg"
image = Image.open(requests.get(url,stream=True).raw)
model.score([image], task_="quality", input_="image")
# task_ : quality | aesthetics; # input_: image | video

Result should be 1.911 (in range [1,5], higher is better).

From paper: arxiv.org/abs/2312.17090.

Syllabus

IQA Results (Spearman/Pearson/Kendall)

Datasets	KonIQ (NR-IQA, seen)	SPAQ (NR-IQA, Seen)	KADID (FR-IQA, Seen)	LIVE-C (NR-IQA, Unseen)	LIVE (FR-IQA, Unseen)	CSIQ (FR-IQA, Unseen)	AGIQA (AIGC, Unseen)
Previous SOTA	0.916/0.928 (MUSIQ, ICCV2021)	0.922/0.919 (LIQE, CVPR2023)	0.934/0.937 (CONTRIQUE, TIP2022)	NA	NA	NA	NA
Q-Align (IQA)	0.937/0.945/0.785	0.931/0.933/0.763	0.934/0.934/0.777	0.887/0.896/0.706	0.874/0.840/0.682	0.845/0.876/0.654	0.731/0.791/0.529
Q-Align (IQA+VQA)	0.944/0.949/0.797	0.931/0.934/0.764	0.952/0.953/0.809	0.892/0.899/0.715	0.874/0.846/0.684	0.852/0.876/0.663	0.739/0.782/0.526
OneAlign (IQA+IAA+VQA)	0.941/0.950/0.791	0.932/0.935/0.766	0.941/0.942/0.791	0.881/0.894/0.699	0.887/0.856/0.699	0.881/0.906/0.699	0.801/0.838/0.602

IAA Results (Spearman/Pearson)

Dataset	AVA_test
VILA (CVPR, 2023)	0.774/0.774
LIQE (CVPR, 2023)	0.776/0.763
Aesthetic Predictor (retrained on AVA_train)	0.721/0.723
Q-Align (IAA)	0.822/0.817
OneAlign (IQA+IAA+VQA)	0.823/0.819

VQA Results (Spearman/Pearson)

Datasets	LSVQ_test	LSVQ_1080p	KoNViD-1k	MaxWell_test
SimpleVQA (ACMMM, 2022)	0.867/0.861	0.764/0.803	0.840/0.834	0.720/0.715
FAST-VQA (ECCV 2022)	0.876/0.877	0.779/0.814	0.859/0.855	0.721/0.724
Q-Align (VQA)	0.883/0.882	0.797/0.830	0.865/0.877	0.780/0.782
Q-Align (IQA+VQA)	0.885/0.883	0.802/0.829	0.867/0.880	0.781/0.787
OneAlign (IQA+IAA+VQA)	0.886/0.886	0.803/0.837	0.876/0.888	0.781/0.786

custom_code

feature-extraction

mplug_owl2

pytorch

transformers

zero-shot-image-classification

Similar repos

Q-Future/Q-Align

③[ICML2024] [IQA, IAA, VQA] All-in-one Foundation Model for visual scoring. Can efficiently…

627

chaofengc/Awesome-Image-Quality-Assessment

A comprehensive collection of IQA papers

1,542

TianheWu/VisualQuality-R1

[NeurIPS 2025 Spotlight] VisualQuality-R1 is the first open-sourced NR-IQA model can accurately…

201

CodeGoat24/UnifiedReward-qwen-3b

UnifiedReward-qwen-3B

1

chancharikmitra/t2v_metrics

Evaluating text-to-image/video/3D models with VQAScore

4

osunlp/UGround-V1-2B

UGround-V1-2B （Qwen2-VL-Based)

11

TianheWu/VisualQuality-R1-7B

VisualQuality-R1-7B

15

osunlp/UGround-V1-7B

UGround-V1-7B （Qwen2-VL-Based)

21

Linked in READMEs

AMAP-ML/VMBench

[ICCV 25] VMBench: A Benchmark for Perception-Aligned Video Motion Generation

76