Model comparison
Stable Diffusion (CompVis) vs Claude 4 Sonnet
Capability radar, value bars, and side-by-side posture.
Stable Diffusion (CompVis)
Not scored
value score
Claude 4 Sonnet
91
value score
Stable Diffusion (CompVis) ctx
—
Claude 4 Sonnet ctx
200K
Capability radar
Value · context · multimodal · openness · speed posture
Value head-to-head
- Claude 4 Sonnet91
Attribute tape
| Field | Stable Diffusion (CompVis) | Claude 4 Sonnet |
|---|---|---|
| Developer | CompVis | Anthropic |
| Context | — | 200K |
| Modalities | Text, Code, Image | |
| Openness | — | Proprietary Model |
| Speed | — | Fast |
| Price | — | $3/1M in · $15/1M out |
| Value score | — | 91 |
| Summary | The original open-source text-to-image latent diffusion model released by LMU Munich's CompVis lab in collaboration with Stability AI and Runway. It generates photorealistic images from text prompts and runs on consumer GPUs, with weights and code publicly available. | Balanced Claude model for coding and agents. |