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

Best image models under $0.001 per image

A leaderboard of the best image models that cost $0.001 or less per image. Qwen-Image-2.1 is #1 right now, followed by Ideogram 4.0 and Cosmos3-Super-Text2Image. Models are ranked by one score that combines 73 published benchmarks. Filter by your computer or budget to find the best one you can use.

90 models · scores combine 73 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]

Filter by your hardware and budget · up to $0.0010/image · reset

+ more

set[all sets][LMArena text-to-image · 197][CVTG-2K word accuracy · 3]

Filter the model list while keeping overall 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

     │                                                       ERNIE-Image-Turbo            ● Ideogram 4.0
  60 ┤ · · · · · · · · · · · · · · · · · · · · · · · · · · ·●──────∘────∘──────∘──────∘───┘· · ∘ ∘ ∘ · · ·∘· ·
     │                ●─────────────────────────●─Z-Image-Turbo    ∘        ∘  ∘       ∘                ∘
  40 ┤ · · · · · · · ·│· · · · · ∘ · · ∘ · · · · · · · · · ··· · · · · · · ·∘· · ∘ · · · · ·∘·∘· · ∘ · · ·∘· ·
     │   ●────────────┘         ∘
     └───────────────┬──────────────────────────────────────┬──────────────────────────────────────┬──────────
                  $0.001                                  $0.01                                  $0.1

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

#	model	score↓	where↓	RAM↓	get it	sources
18	Qwen-Image-2.1 Alibaba	69±2	local	~12GB	how to run ›
23	Ideogram 4.0 Ideogram	66±2*	local	~6.1GB	how to run ›
35	Cosmos3-Super-Text2Image NVIDIA	63±2	local	~154GB	how to run ›
38	HunyuanImage 3.0-Instruct Tencent	62±3*	local	~203GB	how to run ›
47	ERNIE-Image-Turbo Baidu	61±3†	local	~17GB	how to run ›
48	Emu3.5-Image BAAI	60±5*	local	~85GB	how to run ›
49	ERNIE-Image Baidu	60±2	local	~17GB	how to run ›
56	Krea 2 Turbo Krea	59±3*	local	~20GB	how to run ›
59	Qwen-Image-Edit-2509 Alibaba	59±3	local	~26GB	how to run ›
60	HiDream-O1-Image HiDream	58±2	local	~5.3GB	how to run ›
61	FLUX.2 [dev] Black Forest Labs	58±1	local	~20GB	how to run ›	+8
63	Z-Image (Base) Alibaba (Tongyi-MAI)	58±2	local	~10GB	how to run ›
65	HunyuanImage 2.1 Tencent	58±2*	local	~64GB	how to run ›
66	Qwen-Image-Edit-2511 Alibaba	58±2	local	~37GB	how to run ›	+2
68	HunyuanImage 3.0 Tencent	57±2	local	~49GB	how to run ›	+3
69	Emu3.5 BAAI	57±5*	local	~85GB	how to run ›
72	LongCat-Image-Edit Meituan	56±2	local	~36GB	how to run ›
76	Qwen-Image-2512 Alibaba	56±1	local	~22GB	how to run ›	+1
78	Z-Image-Turbo Alibaba (Tongyi-MAI)	55±1	local	~7.7GB	how to run ›	+1
79	LLaDA-Image Ant Group	55±3†	local	~22GB	how to run ›
80	Qwen-Image-Edit Alibaba	55±2	local	~27GB	how to run ›	+4
82	FLUX.2 [klein] 9B Black Forest Labs	55±2	local	~11GB	how to run ›
85	Qwen-Image Alibaba	54±1	local	~13GB	how to run ›	+8
87	LLaDA-Image-Turbo Ant Group	54±3†	local	~22GB	how to run ›
88	LongCat-Image Meituan	53±4	local	~15GB	how to run ›
89	Step1X-Edit v1.2 StepFun	53±2	local	~51GB	how to run ›
97	FLUX.2 [klein] 4B Black Forest Labs	52±2	local	~2.9GB	how to run ›
102	GLM-Image Z.ai	50±2	local	~39GB	how to run ›
106	Latent Diffusion text2img-large (LDM-KL-8-G, LAION-400M) CompVis	48±15*	local	~7.5GB	how to run ›
107	Kandinsky 3 AI Forever	48±11*	local	~32GB	how to run ›
108	Step1X-Edit v1.1 StepFun	48±3	local	~51GB	how to run ›
110	VQ-Diffusion (ITHQ) Microsoft	48±15*	local	~4.1GB	how to run ›
113	Ovis-Image-7B Alibaba (AIDC-AI)	48±7*	local	~12GB	how to run ›
114	FLUX.1 Krea [dev] Black Forest Labs / Krea	47±3	local	~41GB	how to run ›
116	HiDream-I1-Full HiDream	47±2	local	~76GB	how to run ›
126	FLUX.1 Kontext [dev] Black Forest Labs	44±1	local	~21GB	how to run ›	+7
127	FLUX.1 [dev] Black Forest Labs	44±1	local	~7.7GB	how to run ›	+5
129	UNO ByteDance	43±4*	local	~16GB	how to run ›
130	ChronoEdit-14B NVIDIA	43±3*	local	~34GB	how to run ›
131	Lumina-Image 2.0 Alpha-VLLM (Shanghai AI Lab)	43±4*	local	~13GB	how to run ›
133	BAGEL ByteDance Seed	42±1	local	~12GB	how to run ›	+14
135	FLUX.1 [schnell] Black Forest Labs	42±2	local	~7.7GB	how to run ›
136	OmniGen2 BAAI	42±2	local	~17GB	how to run ›	+6
137	Stable Diffusion 3.5 Large Stability AI	42±1	local	~5.4GB	how to run ›	+4
138	Show-o2 7B Show Lab, NUS	42±3	local	~23GB	how to run ›
139	Playground v2 (1024px aesthetic) Playground	41±4*	local	~4.9GB	how to run ›
140	Playground v2.5 Playground	41±2	local	~8.8GB	how to run ›	+1
141	Stable Diffusion 3.5 Medium Stability AI	41±3	local	~20GB	how to run ›
146	Show-o2 1.5B-HQ Show Lab, NUS	40±3*	local	~7.9GB	how to run ›
148	Stable Diffusion XL 0.9 (base) Stability AI	40±6*	local	~4.9GB	how to run ›
149	Stable Diffusion 3 Medium Stability AI	40±2	local	~11GB	how to run ›
150	Kolors Kuaishou (Kolors team)	39±3	local	~22GB	how to run ›
151	BLIP3-o 8B Salesforce Research	38±3	local	~41GB	how to run ›
152	Stable Cascade Stability AI	38±4*	local	~13GB	how to run ›
153	Janus-Pro-7B DeepSeek	38±2	local	~18GB	how to run ›
156	SDXL-Lightning (4-step UNet) ByteDance	37±3*	local	~4.9GB	how to run ›
157	Kandinsky 2.2 AI Forever	37±5*†	local	~12GB	how to run ›
158	Janus-Pro-1B DeepSeek	36±4	api $0.0005/image +local	~5.5GB	deepinfra.com ↗
159	Show-o (show-o-demo-512) Show Lab, NUS	36±3*	local	~7.9GB	how to run ›
161	SSD-1B Segmind	36±4*	local	~3.3GB	how to run ›
163	PixArt-α (PixArt-XL-2-1024-MS) PixArt (Huawei Noah's Ark Lab et al.)	36±2	local	~14GB	how to run ›
164	Emu3 BAAI	36±2	local	~22GB	how to run ›
166	IF-XL DeepFloyd	35±2	local	~29GB	how to run ›	+1
167	Stable Diffusion XL 1.0 Stability AI	34±1	local	~4.9GB	how to run ›	+8
168	LCM-SDXL latent-consistency	34±3	local	~8.9GB	how to run ›
169	OmniGen (v1) BAAI	34±4	local	~9GB	how to run ›
170	SDXL-Turbo Stability AI	34±2	local	~4.9GB	how to run ›
171	IF-L DeepFloyd	33±3	local	~14GB	how to run ›
172	Lumina-DiMOO Alpha-VLLM (Shanghai AI Lab)	32±4*	local	~39GB	how to run ›
174	VILA-U 7B (256px) MIT Han Lab / NVIDIA	32±7*	local	~20GB	how to run ›
175	LCM-SSD-1B latent-consistency	32±4*	local	~3.6GB	how to run ›
176	Janus-1.3B DeepSeek	32±4	local	~5.5GB	how to run ›
177	IF-M DeepFloyd	31±3	local	~14GB	how to run ›
178	Dreamlike Photoreal 2.0 Dreamlike.art	30±3	local	~2.1GB	how to run ›
182	Versatile Diffusion v1.0 SHI Labs	29±4	local	~7.2GB	how to run ›
183	DALL·E Mega (minDALL-E) DALL·E Mini / minDALL-E	29±4	local	~8GB	how to run ›
185	Openjourney PromptHero	28±2	local	~2.1GB	how to run ›
186	Stable Diffusion v1.4 CompVis	27±2	local	~2.1GB	how to run ›
187	Stable Diffusion v1.3 CompVis	27±4*	local	~2.1GB	how to run ›
188	Stable Diffusion v1.1 CompVis	26±3	local	~2.1GB	how to run ›
189	Stable Diffusion v1.2 CompVis	26±3*	local	~2.1GB	how to run ›
191	Stable Diffusion v1.5 Stability AI	26±2	local	~2.1GB	how to run ›	+1
192	OneCAT-3B Meituan (OneCAT team)	24±5*	local	~25GB	how to run ›
193	LCM Dreamshaper v7 SimianLuo (LCM authors)	23±4*	local	~1.7GB	how to run ›
194	InstructPix2Pix UC Berkeley (Brooks, Holynski, Efros)	19±3	local	~2.6GB	how to run ›
197	CogView2 THUDM	1±4	local	~14GB	how to run ›
—	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 ›

+ 112 more don't fit your machine or budget · show them

202 of 202 catalogue models listed here · sources and licences

* 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