| Provider | Model Name / API ID | Output Type | Notes |
|---|---|---|---|
gemini-3.1-flash-image |
Image | Nano Banana 2 | |
gemini-2.5-flash-image |
Image | Nano Banana | |
gemini-3-pro-image-preview |
Image | Nano Banana Pro | |
imagen-3 |
Image | High-quality | |
| OpenAI | gpt-image-1 |
Image | Official OpenAI T2I |
| OpenAI | gpt-video-1 |
Video | Official OpenAI Video |
| Meta (LLaVA / Make-A-Video) | Make-A-Video (MAV) | Video | Meta research model |
| Stability AI | Stable Diffusion XL | Image | Popular open model |
| Stability AI | SDXL-Video | Video | SD-based video |
| Adobe | Firefly Image | Image | Enterprise API |
| Adobe | Firefly Video | Video | Enterprise API |
| Midjourney | MJ Image API | Image | Creative styles |
| Runway | Gen-2 | Video | Text→Video |
| Runway | Gen-1 | Image | Prior generation |
| Anthropic | Claude Image | Image | Claude multimodal |
| Tencent | Hunyuan | Image | CN market |
| Alibaba | Tongyi | Image/Video | CN market |
| Baidu | ERNIE-Vision | Image/Video | CN market |
| Mistral | Mistral Image | Image | Open model |
| Hugging Face | Diffusers API | Image/Video | Hosted open models |