Imagen Models by Google DeepMind
Google DeepMindProprietary
Google DeepMind releases · 50 in the last 12 monthsChangelog →
9 models2024
Last refreshed 2026-05-19. Next refresh: weekly.
Details
ResearcherGoogle DeepMind
LicenseProprietary
Commercial useCommercial use: conditional
Models9
Released2024
Capabilities
Vision4 of 9 models
Multimodal4 of 9 models
About
Google's Imagen family of image generation models, capable of producing high-quality, photorealistic images from text prompts. Includes Imagen 3.0 and 4.0 variants for different speed/quality trade-offs.
Decision facts
- Best fit
- imagevision and multimodal work
- Capability starting point
- Imagen Product Recontext with multimodal inputs
- Lowest tracked input
- Not tracked
- Closest related family
- DiffusionGemma
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
9 in view
Imagen Product RecontextCurrent
Use when the workload needs image and multimodal inputs.
2024-10imagemultimodal inputs
Virtual Try-OnCurrent
Use when the workload needs image and multimodal inputs.
2024-09imagemultimodal inputs
Use when the workload needs image and multimodal inputs.
2024-08imagemultimodal inputs
Imagen 3Current
Use when the workload needs image and multimodal inputs.
2024-08imagemultimodal inputs
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Imagen 4 Fast | Use when the workload needs image. | 2024-11 | image | Current |
| Imagen 4 | Use when the workload needs image. | 2024-11 | image | Current |
| Imagen 4 Ultra | Use when the workload needs image. | 2024-11 | image | Current |
| Imagen Product Recontext | Use when the workload needs image and multimodal inputs. | 2024-10 | imagemultimodal inputs | Current |
| Virtual Try-On | Use when the workload needs image and multimodal inputs. | 2024-09 | imagemultimodal inputs | Current |
| Imagen 3 for Editing and Customization | Use when the workload needs image and multimodal inputs. | 2024-08 | imagemultimodal inputs | Current |
| Imagen 3 Fast | Use when the workload needs image. | 2024-08 | image | Current |
| Imagen 3 | Use when the workload needs image and multimodal inputs. | 2024-08 | imagemultimodal inputs | Current |
| Imagen 3 | Use when the workload needs image. | 2024-08 | image | Current |
Release Timeline
4 release groups2024-11
3 current
2024-10
1 current
Imagen Product Recontext
Currentimagemultimodal inputs
2024-09
1 current
Virtual Try-On
Currentimagemultimodal inputs
2024-08
4 current
Imagen 3
Currentimagemultimodal inputs
Imagen 3
Currentimage
Imagen 3 Fast
Currentimage
Imagen 3 for Editing and Customization
Currentimagemultimodal inputs
Specifications(9 models)
| Model | Released | Vision | Multimodal |
|---|---|---|---|
| Imagen 4 Fast | 2024-11 | No | No |
| Imagen 4 | 2024-11 | No | No |
| Imagen 4 Ultra | 2024-11 | No | No |
| Imagen Product Recontext | 2024-10 | Yes | Yes |
| Virtual Try-On | 2024-09 | Yes | Yes |
| Imagen 3 for Editing and Customization | 2024-08 | Yes | Yes |
| Imagen 3 Fast | 2024-08 | No | No |
| Imagen 3 | 2024-08 | Yes | Yes |
| Imagen 3 | 2024-08 | No | No |
Available From(3 providers)
Related Model Families
Models(9)
Imagen 4 Fast
2024-113 providers
Imagen 4
2024-113 providers
Imagen 4 Ultra
2024-113 providers
Imagen Product Recontext
2024-101 provider
Multimodal
Virtual Try-On
2024-091 provider
Multimodal
Imagen 3 for Editing and Customization
2024-081 provider
Multimodal
Imagen 3 Fast
2024-081 provider
Imagen 3
2024-081 provider
Multimodal
Imagen 3
2024-081 provider