whatmodel.sh · find the best image models you can run

Best text-to-image models

A leaderboard of the best text-to-image models. GPT Image 2.5 Sunburst is #1 right now, followed by GPT Image 2.5 Flare and GPT Image 2. Models are ranked on human votes and image generation tests like GenEval. Filter by your computer or budget to find the best one you can use.

161 models · scores combine 41 benchmarks · updated 2026-10-11 02:20 UTChow it works · find a leaderboard · benchmark your machine

task[all tasks][text to image][image to image / editing]

Scores use reviewed text to image evaluations only. Compare scores within this task. Models without task measurements are excluded.

Filter by your hardware and budget · reset

+ more

set[all sets][LMArena text-to-image · 157][CVTG-2K word accuracy · 3]

Filter the model list while keeping task scores. Models without a shared score scale are not yet calibrated; select a set to see its own scores.

Detect your exact chip or graphics card:

curl -G whatmodel.sh/image -d max=0 --data-urlencode "mac=$(sysctl -n hw.memsize machdep.cpu.brand_string)"Mac

curl -G whatmodel.sh/image -d max=0 --data-urlencode "ram=$(awk '/MemT/{print $2}' /proc/meminfo)" --data-urlencode "nv=$(nvidia-smi --query-gpu=name,memory.total --format=csv,noheader 2>/dev/null)"Linux

curl.exe -G whatmodel.sh/image -d max=0 --data-urlencode "ram=$((gcim Win32_ComputerSystem).TotalPhysicalMemory)" --data-urlencode "nv=$(nvidia-smi --query-gpu=name,memory.total --format=csv,noheader 2>$null)"Windows

$ terminal

ram[8][16][24][32][48][64][96][128][192][256]GB

gpu[apple silicon][graphics card][none]

price[local][$0.001][$0.005][$0.02][$0.1][any]max per image

detecting your OS…

Score vs API price

     │                                                      ◆ GPT Image 2.5 Sunburst
  75 ┤ · · · · · · ··· · · · · · · · · · · · · · · · · ·◆─Muse Image · · · ◇ ◇ · ◇◇· ◇ · · ··· ·◇· · · · ·◇· ·
     │                         Recraft V4.1 Flash ◆─────∘◇    ∘    ∘     ◇ ◇ ◇◇ ∘◇  ◇ ◇◇∘   ◇          ◇
  50 ┤ · · · · · · ··●───────────────∘───────●────┘· · ··· · ◇∘·◇·◇· ·∘· · ∘ ◇ · ∘ ·◇∘ ∘◇· ·∘· ·∘· · · · · · ·
     │   ●───────────┘        ∘∘                                           ∘                      ∘
     └──────────────┬───────────────────────────────────┬───────────────────────────────────┬─────────────────
                 $0.001                               $0.01                               $0.1

#	model	task score↓	where↓	speed↓	RAM↓	get it	sources

#	model	task score↓	where↓	RAM↓	get it	sources
1	GPT Image 2.5 Sunburst OpenAI	90±2*	api $0.013/image		fal.ai ↗
2	GPT Image 2.5 Flare OpenAI	88±2*	api $0.013/image		fal.ai ↗
3	GPT Image 2 OpenAI	85±2	api $0.053/image		fal.ai ↗
4	MAI-Image-2.6 Microsoft AI	81±2*	comparison only
5	Nano Banana 2.1 Google	80±2*	api $0.034/image		ai.google.dev ↗
6	Reve 2.1 Reve	78±2*	api $0.25/image		fal.ai ↗
7	Grok Imagine Image 2.0 SpaceXAI	78±2*	api $0.040/image		docs.x.ai ↗
8	Nano Banana 2 (Gemini 3.1 Flash Image) Google	75±2	api $0.067/image		ai.google.dev ↗
9	Muse Image Meta	75±2*	api $0.010/image		dev.meta.ai ↗
10	Qwen-Image-3.0-Pro Alibaba	74±2	api $0.040/image		www.alibabacloud.com ↗
11	Seedream 5.0 Pro ByteDance Seed	74±2	api $0.050/image		deepinfra.com ↗
12	Reve 2.0 Reve	74±2*	api $0.25/image		fal.ai ↗
13	Nano Banana Pro (Gemini 3 Pro Image) Google	73±2	api $0.13/image		ai.google.dev ↗
14	MAI-Image-2.5 Microsoft AI	73±2*	comparison only
15	Nano Banana 2 Lite (Gemini 3.1 Flash-Lite Image) Google	72±2*	api $0.034/image		ai.google.dev ↗
16	GPT Image 1.5 OpenAI	70±2	api $0.034/image		developers.openai.com ↗
17	Qwen-Image 2.0 Pro Alibaba	69±4	api $0.075/image		www.alibabacloud.com ↗
18	Ideogram 4.0 Ideogram	68±2*	api $0.060/image +local	~6.1GB	www.together.ai ↗
19	Qwen-Image-2.1 Alibaba	67±2*	local	~12GB	how to run ›
20	Boogu-Image-0.1 Base Boogu project	66±5*	comparison only
21	Qwen-Image-2.0-Pro (2026-06-22) Alibaba	66±2*	api $0.075/image		www.alibabacloud.com ↗
22	Uni-1.1 Max Luma AI	66±2*	api $0.10/image		lumalabs.ai ↗
23	Uni-1.1 Luma AI	66±2*	api $0.040/image		lumalabs.ai ↗
24	MAI-Image-2 Microsoft AI	65±2*	comparison only
25	Grok Imagine Image SpaceXAI (xAI)	64±2*	api $0.020/image		docs.x.ai ↗
26	Recraft V4.1 Utility Pro Recraft	64±2*	api $0.21/image		www.recraft.ai ↗
27	FLUX.2 [max] Black Forest Labs	63±2	api $0.070/image		docs.bfl.ai ↗
28	Grok Imagine Image Pro SpaceXAI (xAI)	63±2*	api $0.050/image		docs.x.ai ↗
29	Seedream 5.0 Lite ByteDance Seed	63±2	api $0.035/image		docs.byteplus.com ↗
30	FLUX.2 [flex] Black Forest Labs	63±2*	api $0.050/image		docs.bfl.ai ↗
31	Reve V1.5 Reve	63±2*	comparison only
32	FLUX.2 [pro] Black Forest Labs	62±2	api $0.030/image		docs.bfl.ai ↗
33	Seedream 4.5 ByteDance	62±2	api $0.040/image		docs.byteplus.com ↗
34	ERNIE-Image Baidu	62±3	api $0.030/image +local	~17GB	fal.ai ↗
35	Nano Banana (Gemini 2.5 Flash Image) Google	62±2	api $0.039/image		ai.google.dev ↗
36	Cosmos3-Super-Text2Image NVIDIA	62±2	local	~154GB	how to run ›
37	ERNIE-Image-Turbo Baidu	61±3†	api $0.010/image +local	~17GB	fal.ai ↗
38	GPT Image 1 OpenAI	61±1	api $0.042/image		developers.openai.com ↗	+3
39	Imagen 4 Ultra Google	61±2	api $0.060/image		cloud.google.com ↗
40	Wan 2.6 Text-to-Image Alibaba	61±2*	api $0.030/image		deepinfra.com ↗
41	Seedream 4.0 ByteDance Seed	60±1	api $0.040/image		deepinfra.com ↗
42	Recraft V4.1 Pro Recraft	60±2*	api $0.21/image		www.recraft.ai ↗
43	DeepGen 1.0 DeepGen Team	60±6*	comparison only
44	Emu3.5-Image BAAI	60±5*	local	~85GB	how to run ›
45	Krea 2 Medium Krea	59±2*	api $0.030/image		www.krea.ai ↗
46	Wan 2.7 Image Pro Alibaba	59±2*	api $0.075/image		www.alibabacloud.com ↗
47	Imagen 4 Google	59±2	api $0.040/image		cloud.google.com ↗
48	FLUX.2 [dev] Black Forest Labs	59±1	api $0.046/image +local	~20GB	developers.cloudflare.com ↗	+1
49	Wan 2.5 Text-to-Image Preview Alibaba	58±2*	api $0.030/image		www.alibabacloud.com ↗
50	Recraft V4 Recraft	58±2*	api $0.040/image		www.recraft.ai ↗
51	GPT Image 1 Mini OpenAI	58±2*	api $0.011/image		developers.openai.com ↗
52	Krea 2 Turbo Krea	58±2*	api $0.015/image +local	~20GB	www.krea.ai ↗
53	Z-Image (Base) Alibaba (Tongyi-MAI)	58±2	api $0.010/image +local	~10GB	fal.ai ↗
54	Krea 2 Large Krea	58±2*	api $0.060/image		www.krea.ai ↗
55	HiDream-O1-Image HiDream	58±2	api $0.010/image +local	~5.3GB	fal.ai ↗
56	HunyuanImage 3.0 Tencent	58±2	api $0.080/image +local	~49GB	replicate.com ↗	+2
57	Qwen-Image-2512 Alibaba	57±1	api $0.020/image +local	~22GB	replicate.com ↗
58	Wan 2.7 Image Alibaba	57±2*	api $0.030/image		www.alibabacloud.com ↗
59	Recraft V4.1 Flash Recraft	57±2*	api $0.0070/image		www.recraft.ai ↗
60	Emu3.5 BAAI	56±5*	local	~85GB	how to run ›
61	MAI-Image-1 Microsoft AI	56±2*	comparison only
62	Z-Image-Turbo Alibaba (Tongyi-MAI)	56±1	api $0.0050/image +local	~7.7GB	replicate.com ↗	+1
63	LLaDA-Image Ant Group	55±3†	local	~22GB	how to run ›
64	Seedream 3.0 ByteDance Seed	55±2	comparison only
65	HunyuanImage 2.1 Tencent	55±6*	api $0.10/image +local	~64GB	fal.ai ↗
66	FLUX.1 Kontext [max] Black Forest Labs	54±2*	api $0.080/image		docs.bfl.ai ↗
67	HiDream-O1-Image-Dev HiDream	54±5*	comparison only
68	LongCat-Image Meituan	54±4	api $0.13/image +local	~15GB	fal.ai ↗
69	LLaDA-Image-Turbo Ant Group	53±3†	local	~22GB	how to run ›
70	FLUX.2 [klein] 9B Black Forest Labs	53±2	api $0.015/image +local	~11GB	developers.cloudflare.com ↗
71	Qwen-Image Alibaba	53±1	api $0.025/image +local	~13GB	replicate.com ↗	+5
72	Kling Image 2.1 Kuaishou	53±7*	api $0.014/image		kling.ai ↗
73	Ideogram 3.0 Ideogram	52±2*	api $0.060/image		fal.ai ↗
74	FLUX.1 Kontext [pro] Black Forest Labs	52±2*	api $0.040/image		docs.bfl.ai ↗
75	Imagen 3 (imagen-3.0-generate-002) Google	51±2	comparison only
76	Photon Luma AI	51±2	api $0.019/image		fal.ai ↗
77	P-Image Pruna	50±2*	api $0.0050/image		replicate.com ↗
78	FLUX.2 [klein] 4B Black Forest Labs	49±2	api $0.0011/image +local	~2.9GB	developers.cloudflare.com ↗
79	Runway Gen-4 Image Runway	49±2*	api $0.050/image		docs.dev.runwayml.com ↗
80	GLM-Image Z.ai	49±2	api $0.015/image +local	~39GB	docs.z.ai ↗
81	Recraft V3 Recraft	49±2	api $0.040/image		www.recraft.ai ↗
82	Kandinsky 3 AI Forever	48±10*	local	~32GB	how to run ›
83	Lucid Origin Leonardo.Ai	48±2*	api $0.017/image		replicate.com ↗
84	UniWorld-V1 PKU-YuanGroup	48±6*†	comparison only
85	MetaQuery-XL Meta / NYU	48±6*	comparison only
86	Ovis-Image-7B Alibaba (AIDC-AI)	48±7*	local	~12GB	how to run ›
87	FLUX.1 Krea [dev] Black Forest Labs / Krea	48±4*	api $0.025/image +local	~41GB	replicate.com ↗
88	HiDream-I1-Full HiDream	47±2	api $0.050/image +local	~76GB	fal.ai ↗
89	Ideogram 2.0 Ideogram	46±2	api $0.080/image		replicate.com ↗
90	Gemini 2.0 Flash Image Generation (preview) Google	46±2	comparison only
91	Infinity-8B ByteDance (FoundationVision)	46±5*	comparison only
92	FLUX1.1 [pro] Black Forest Labs	45±2	api $0.040/image		docs.bfl.ai ↗
93	Show-o2 1.5B Show Lab, NUS	45±5*†	comparison only
94	Midjourney V6 Midjourney	45±7*	comparison only
95	UNO ByteDance	44±4*	local	~16GB	how to run ›
96	DALL·E 3 OpenAI	44±1	comparison only			+4
97	FLUX.1 [dev] Black Forest Labs	43±1	api $0.025/image +local	~7.7GB	replicate.com ↗	+3
98	Playground v2 (1024px aesthetic) Playground	43±4*	local	~4.9GB	how to run ›
99	BLIP3o-NEXT-GRPO-Text-3B Salesforce Research	42±3*	comparison only
100	Lumina-Image 2.0 Alpha-VLLM (Shanghai AI Lab)	42±4*	api $0.075/image +local	~13GB	fal.ai ↗
101	FLUX.1 [schnell] Black Forest Labs	42±3*	api $0.0030/image +local	~7.7GB	replicate.com ↗
102	Show-o2 7B Show Lab, NUS	42±3	local	~23GB	how to run ›
103	Midjourney V6.1 Midjourney	42±3*	comparison only
104	Playground v2.5 Playground	41±2	local	~8.8GB	how to run ›	+1
105	Stable Diffusion 3.5 Large Stability AI	41±1	api $0.065/image +local	~5.4GB	replicate.com ↗	+1
106	BAGEL ByteDance Seed	41±1	api $0.10/image +local	~12GB	fal.ai ↗	+2
107	FLUX.1 Kontext [dev] Black Forest Labs	40±2*	api $0.025/image +local	~21GB	replicate.com ↗
108	Stable Diffusion 3.5 Medium Stability AI	40±3*	api $0.035/image +local	~20GB	platform.stability.ai ↗
109	Show-o2 1.5B-HQ Show Lab, NUS	40±4*	local	~7.9GB	how to run ›
110	CogView4-6B Z.ai	40±5*	comparison only
111	OmniGen2 BAAI	40±4*	api $0.15/image +local	~17GB	fal.ai ↗
112	Stable Cascade Stability AI	40±4*	local	~13GB	how to run ›
113	SDXL-Lightning (4-step UNet) ByteDance	40±4*	local	~4.9GB	how to run ›
114	Stable Diffusion 3 Medium Stability AI	39±2	api $0.035/image +local	~11GB	fal.ai ↗
115	Midjourney V7 Midjourney	39±4*	comparison only
116	BLIP3-o 8B Salesforce Research	39±3	local	~41GB	how to run ›
117	Kolors Kuaishou (Kolors team)	38±3	local	~22GB	how to run ›
118	SeedEdit 3.0 ByteDance Seed	38±6*	comparison only
119	PixArt-α (PixArt-XL-2-1024-MS) PixArt (Huawei Noah's Ark Lab et al.)	38±3	local	~14GB	how to run ›
120	Janus-Pro-7B DeepSeek	37±2	api $0.0020/image +local	~18GB	deepinfra.com ↗
121	Kandinsky 2.2 AI Forever	37±5*†	local	~12GB	how to run ›
122	SSD-1B Segmind	36±3*	local	~3.3GB	how to run ›
123	Show-o (show-o-demo-512) Show Lab, NUS	36±3*	local	~7.9GB	how to run ›
124	Janus-Pro-1B DeepSeek	36±4	api $0.0005/image +local	~5.5GB	deepinfra.com ↗
125	JanusFlow-1.3B DeepSeek	36±6*	comparison only
126	Emu3 BAAI	35±2	local	~22GB	how to run ›
127	Stable Diffusion XL 0.9 (base) Stability AI	35±3*	local	~4.9GB	how to run ›
128	SDXL-Turbo Stability AI	35±2	local	~4.9GB	how to run ›
129	Stable Diffusion XL 1.0 Stability AI	35±1	api $0.0019/image +local	~4.9GB	www.together.ai ↗	+5
130	IF-XL DeepFloyd	34±2	local	~29GB	how to run ›
131	IF-L DeepFloyd	34±4*	local	~14GB	how to run ›
132	LCM-SDXL latent-consistency	34±3*	local	~8.9GB	how to run ›
133	Dreamlike Photoreal 2.0 Dreamlike.art	34±4*	local	~2.1GB	how to run ›
134	IF-M DeepFloyd	33±4*	local	~14GB	how to run ›
135	Versatile Diffusion v1.0 SHI Labs	33±4*	local	~7.2GB	how to run ›
136	CogView2 THUDM	32±4*	local	~14GB	how to run ›
137	LCM-SSD-1B latent-consistency	32±3*	local	~3.6GB	how to run ›
138	Stable Diffusion v2.0 Stability AI	32±3*	comparison only
139	DALL·E 2 OpenAI	32±3*	comparison only
140	VILA-U 7B (256px) MIT Han Lab / NVIDIA	32±6*	local	~20GB	how to run ›
141	Latent Diffusion text2img-large (LDM-KL-8-G, LAION-400M) CompVis	32±4*	local	~7.5GB	how to run ›
142	FuseDream (BigGAN 512) FuseDream authors	31±4*	comparison only
143	Janus-1.3B DeepSeek	31±4	local	~5.5GB	how to run ›
144	VQ-Diffusion (ITHQ) Microsoft	31±4*	local	~4.1GB	how to run ›
145	LAFITE (HPS v2 checkpoint) LAFITE authors	31±4*	comparison only
146	DALL·E Mega (minDALL-E) DALL·E Mini / minDALL-E	31±3*	local	~8GB	how to run ›
147	Stable Diffusion v2.1 Stability AI	30±2	comparison only
148	GLIDE (filtered) OpenAI	30±4*	comparison only
149	Openjourney PromptHero	29±2	local	~2.1GB	how to run ›
150	Stable Diffusion v1.4 CompVis	28±2	local	~2.1GB	how to run ›
151	Stable Diffusion v1.3 CompVis	28±4*	local	~2.1GB	how to run ›
152	Stable Diffusion v1.1 CompVis	27±3	local	~2.1GB	how to run ›
153	Stable Diffusion v1.5 Stability AI	27±2	local	~2.1GB	how to run ›
154	Stable Diffusion v1.2 CompVis	27±3*	local	~2.1GB	how to run ›
155	LCM Dreamshaper v7 SimianLuo (LCM authors)	24±4*	local	~1.7GB	how to run ›
156	X-LXMERT UNC Chapel Hill	18±4*	comparison only
157	AttnGAN (COCO) Microsoft / Rutgers / Duke	17±4*	comparison only
—	Kandinsky 2.1 AI Forever	not scored yet	local	~12GB	how to run ›
—	Mage-Flow Microsoft	not yet calibrated	local	~8.9GB	how to run ›
—	Mage-Flow-Base Microsoft	not yet calibrated	local	~14GB	how to run ›
—	Mage-Flow-Turbo Microsoft	not yet calibrated	local	~8.9GB	how to run ›

Includes 31 comparison-only models with no verified API or download · hide them

161 of 162 catalogue models listed here · sources and licences

Models outside this leaderboard (1 models)

Raw results, insufficient overlap for an overall score: Kandinsky 2.0

* new or thinly tested: ranked on too few benchmark results · † only the maker’s own numbers so far · ~RAM is estimated; full context may need more memory