- Home
- Image model comparison
- OmniGen2 vs. SANA-1.5 4.8B 1024px
VectorSpaceLabNVIDIA ResearchImage model matchup
OmniGen2vs.SANA-1.5 4.8B 1024px
Which one is better?
In our own benchmark GraduallyBench Image v2, OmniGen2 is slightly ahead, but not certainly. Neither is in the arena. Neither has an API price.
OmniGen2
Rank 95 of 108
SANA-1.5 4.8B 1024px
Rank 99 of 108
Ranks among the 21 image models with an arena rating and the 108 with a GraduallyBench Image v2 run; prices compared with 28 models with an API price.
Test images from GraduallyBench Image v2
Same task, the first image of each. The task with the biggest difference is preselected.


Result for “Product photography”:OmniGen2 slightly ahead
What the rating looks at: Materials, reflections, and fine details.
“Ahead”: the 95 % ranges of both values do not overlap. “Slightly ahead”: a higher value, but the ranges overlap.
Test protocol of the images
Each test attempt uses the same archived prompt and one request. The first output of that attempt counts. Repeats after technical test failures are disclosed for the affected images. Files are normalized to 1,024 × 1,024 pixels without cropping. Provider resolution, randomness, quality tier and prompt processing can still differ. The images are a practical visual test, not a reconstruction of the arena configuration.
Character and detail
OmniGen2: fal, image_size=1024x1024, n=1, seed=639237469, Estimate reserves 2 MP at Fal's $0.15 per MP rate, estimated cost $0.300000, generated Nov 2, 2026, 3:27 PM. Source
SANA-1.5 4.8B 1024px: manual, local PyTorch 2.13.0, Diffusers 0.36.0; Efficient-Large-Model/SANA1.5_4.8B_1024px_diffusers@9468102c3cebb657f8c4b5f1e5a71e989a15f10d; native 1024x1024, 1:1; one request, first output; steps=20, guidance=4.5, seed=6914427587596023045; mps for text encoder and denoising; cpu for native VAE decode; bfloat16 for text encoder and transformer; float32 for VAE; native prompt preprocessing lowercases input; optional instruction disabled, generated Nov 2, 2026, 5:42 PM. Source
Protocol gradually-image-comparison-v1. Prompt SHA 256: 985a75b38642a9f0e5e0c0e0c67f1b7f67780d42bd2168fa24e9a7a7a94b0da6
OmniGen2 image SHA 256: 8c39f2555d07eae2728c45591a183a4343d5ab1b9eaba4ec75a83b26f50665d0
SANA-1.5 4.8B 1024px image SHA 256: 97badf740db81367de7d6af73cc9313f1dfc4fe8383183ddbd9fc12cc67b35ee
Infographic
OmniGen2: fal, image_size=1024x1024, n=1, seed=672021196, Estimate reserves 2 MP at Fal's $0.15 per MP rate, estimated cost $0.300000, generated Nov 2, 2026, 3:27 PM. Source
SANA-1.5 4.8B 1024px: manual, local PyTorch 2.13.0, Diffusers 0.36.0; Efficient-Large-Model/SANA1.5_4.8B_1024px_diffusers@9468102c3cebb657f8c4b5f1e5a71e989a15f10d; native 1024x1024, 1:1; one request, first output; steps=20, guidance=4.5, seed=3447101042619426797; mps for text encoder and denoising; cpu for native VAE decode; bfloat16 for text encoder and transformer; float32 for VAE; native prompt preprocessing lowercases input; optional instruction disabled, generated Nov 2, 2026, 5:43 PM. Source
Protocol gradually-image-comparison-v1. Prompt SHA 256: ed65cb4e6a51e2336f8b149ad4cbb16e020f07d527ad94362e719d2dcf91d94f
OmniGen2 image SHA 256: 2f1a66d64a4f6a41d1c7228eb46ff9c2f5c27b684cf43d5dc8ba18aa7a2cd783
SANA-1.5 4.8B 1024px image SHA 256: 6c23b2df82d085e155c012c16915d04dd3a1aacdb78c9604eb74668309e07b38
Product photography
OmniGen2: fal, image_size=1024x1024, n=1, seed=355687008, Estimate reserves 2 MP at Fal's $0.15 per MP rate, estimated cost $0.300000, generated Nov 2, 2026, 3:27 PM. Source
SANA-1.5 4.8B 1024px: manual, local PyTorch 2.13.0, Diffusers 0.36.0; Efficient-Large-Model/SANA1.5_4.8B_1024px_diffusers@9468102c3cebb657f8c4b5f1e5a71e989a15f10d; native 1024x1024, 1:1; one request, first output; steps=20, guidance=4.5, seed=1122699157863902383; mps for text encoder and denoising; cpu for native VAE decode; bfloat16 for text encoder and transformer; float32 for VAE; native prompt preprocessing lowercases input; optional instruction disabled, generated Nov 2, 2026, 5:41 PM. Source
Protocol gradually-image-comparison-v1. Prompt SHA 256: c67fd71e91304458a2feef5c91efa8677260fab0c0099a29a2c52cb579f5b2f3
OmniGen2 image SHA 256: 31e9ddbf26881a576ca95a7bbd2642fae4a96c4205362abe3859ade6a3da8dc7
SANA-1.5 4.8B 1024px image SHA 256: 0ceaa96a83bc85d12c7f56b925226a346ee9b42f831fa5a9592edc4fc1e7ce81
Typography and layout
OmniGen2: fal, image_size=1024x1024, n=1, seed=713672340, Estimate reserves 2 MP at Fal's $0.15 per MP rate, estimated cost $0.300000, generated Nov 2, 2026, 3:27 PM. Source
SANA-1.5 4.8B 1024px: manual, local PyTorch 2.13.0, Diffusers 0.36.0; Efficient-Large-Model/SANA1.5_4.8B_1024px_diffusers@9468102c3cebb657f8c4b5f1e5a71e989a15f10d; native 1024x1024, 1:1; one request, first output; steps=20, guidance=4.5, seed=623973358981804157; mps for text encoder and denoising; cpu for native VAE decode; bfloat16 for text encoder and transformer; float32 for VAE; native prompt preprocessing lowercases input; optional instruction disabled, generated Nov 2, 2026, 5:40 PM. Source
Protocol gradually-image-comparison-v1. Prompt SHA 256: 2e012c3d14ee5dd02203a94f394ca80a5038cdebd6032b25a8b8a221f2255419
OmniGen2 image SHA 256: f4413e92d9fca652ec3e6bbb768a0003f064d7286b0652c1385c26b646b0c890
SANA-1.5 4.8B 1024px image SHA 256: 8371e0e35ad4472b71165cedd1940eb0339b19c24f801c3b956874c090a327fc
Subscription and API
OmniGen2
- Subscription
- n/a No plan in Germany names exactly this model.
- Via API
- No API price known (access: local, Web app).
- Weights
- Open weights.
SANA-1.5 4.8B 1024px
- Subscription
- n/a No plan in Germany names exactly this model.
- Via API
- No API price known (access: local).
- Weights
- Open weights.
Subscriptions only count plans that name exactly this model. Subscription prices include VAT, API prices are in dollars.
GraduallyBench Image v2 from Nov 7, 2026 · Subscription database from Sep 29, 2026 (46 days old)
All data side by side
The better value is bold. For ratings only when the gap is clear.
| Kennzahl | OmniGen2 | SANA-1.5 4.8B 1024px |
|---|---|---|
| Ratings | ||
| Arena ratingfrom votes by users, higher is better | n/a | n/a |
| Arena rank | n/a | n/a |
| Arena votesmore votes, a safer rating | n/a | n/a |
| GraduallyBench Image v2our own benchmark, 0 to 100 | 15 | 12 |
| GraduallyBench Image v2 by task | ||
| Typography and layoutLegible text, hierarchy, and composition | 18 | 24 |
| Product photographyMaterials, reflections, and fine details | 24 | 8 |
| Character and detailAnatomy, clothing, and spatial consistency | 10 | 7 |
| InfographicNumbers, labels, and visual organization | 10 | 11 |
| API price | ||
| Per imagelower is better | n/a | n/a |
| 100 images | n/a | n/a |
| Profile | ||
| Released | Jun 16, 2025 | Mar 16, 2025 |
| Weightsopen means: runs locally | open | open |
| Access | local, Web app | local |
| Parameters | not published | 4.8 billion |
| Largest output | not consistently published | not consistently published |
| Plans in Germanynaming exactly this model | n/a | n/a |
API prices for one image at 1,024 × 1,024 pixels according to Artificial Analysis.
Sources: OmniGen2 model source (verified Nov 1, 2026) · SANA-1.5 4.8B 1024px model source (verified Nov 1, 2026)
Arena ratings by category
From blind votes on Artificial Analysis and LMArena; the sources are named under the card. “Ahead” means the lead is clear.
No shared arena score in the stored snapshot
The stored benchmark database contains no measurement for OmniGen2 and SANA-1.5 4.8B 1024px from the same arena and category. Older model versions are not used as substitutes.