1,423 models · 1,213 open weights · 210 API-only · refreshed nightly
Text to image models
Every model in the catalog — open weights you can self-host and API-only models — with licence or API price, estimated VRAM and daily-tracked downloads. Filters update the URL — share any view.
| # | Model | Params | Context | Commercial use | 30d | Min VRAM |
|---|---|---|---|---|---|---|
| 01 | Qwen-Image-2.1 | 7.1 B | — | other | 10.2 M | from 136.7 GB |
| 02 | stable-diffusion-xl-base-1.0 | 2.6 B | — | ⚠ openrail++ | 4.6 M | from 39.7 GB |
| 03 | Krea-2 | 12.8 B | — | other | 4.5 M | from 183.2 GB |
| 04 | Qwen-Image-2.1-Uncensored-Quantized | 7.1 B | — | other | 2.5 M | from 6.1 GB |
| 05 | Qwen-Image-2.1-Uncensored-GGUF | 7.1 B | — | other | 2.2 M | from 6.1 GB |
| 06 | Qwen-Image-2.1-GGUF | 7.1 B | — | other | 1.6 M | from 4.3 GB |
| 07 | Qwen-Image-2.1-Turbo-GGUF | — | — | other | 1.4 M | from 3.2 GB |
| 08 | RealVisXL_V5.0 | 2.6 B | — | ⚠ openrail++ | 1.3 M | from 46.7 GB |
| 09 | Flux-2-Klein-4B | 4.0 B | — | ✓ apache-2.0 | 1.3 M | from 31.6 GB |
| 10 | Flux-1-Dev | 11.9 B | — | other | 1.3 M | from 110.9 GB |
| 11 | stable-diffusion-v1-5 | 860 M | — | ⚠ creativeml-openrail-m | 1.0 M | from 26.6 GB |
| 12 | animagine-xl-4.0 | 2.6 B | — | ⚠ openrail++ | 1.0 M | from 23.8 GB |
| 13 | Flux-2-Dev | — | — | other | 998 K | from 118.4 GB |
| 14 | Z-Image-Turbo-GGUF | 6.2 B | — | ✓ apache-2.0 | 963 K | from 4.0 GB |
| 15 | Qwen-Image-2.1-FP8 | 7.1 B | — | other | 915 K | from 46.7 GB |
| 16 | dreamshaper-7 | 860 M | — | ⚠ creativeml-openrail-m | 902 K | from 9.7 GB |
| 17 | Qwen-Image-2.1-Turbo-Uncensored-GGUF | 8.8 B | — | ✓ apache-2.0 | 761 K | from 5.5 GB |
| 18 | Z-Image-Turbo | 6.2 B | — | ✓ apache-2.0 | 715 K | from 37.5 GB |
| 19 | Flux-2-Klein-9B | 9.0 B | — | other | 707 K | from 37.3 GB |
| 20 | P-H3-Image-Comfy | — | — | other | 704 K | from 153.8 GB |
| 21 | noobai-XL-1.1 | 2.6 B | — | other | 662 K | from 16.3 GB |
| 22 | sdxl-turbo | 2.6 B | — | other | 626 K | from 46.7 GB |
| 23 | Juggernaut-XL-v9 | — | — | ⚠ creativeml-openrail-m | 579 K | from 15.9 GB |
| 24 | Qwen-Image-2.1 | 7.1 B | — | other | 553 K | from 38.0 GB |
| 25 | Pruna-Qage-2.1 | 7.1 B | — | other | 514 K | from 2.3 GB |
| 26 | Pruna-Qwen-Image-2.1 | 7.1 B | — | other | 513 K | from 2.3 GB |
| 27 | Pruna-Q-Image-2.1 | 7.1 B | — | other | 510 K | from 2.3 GB |
| 28 | FLUX.1-dev | 11.9 B | — | other | 496 K | from 66.0 GB |
| 29 | stable-diffusion-v1-4 | 860 M | — | ⚠ creativeml-openrail-m | 483 K | from 13.5 GB |
| 30 | sd-turbo | 870 M | — | unknown | 454 K | from 14.9 GB |
| 31 | Qwen-Image-2.1-Lightning | 7.1 B | — | unknown | 436 K | from 1.6 GB |
| 32 | Qwen-Image-2.1-Turbo-FP8 | 7.1 B | — | other | 427 K | from 61.1 GB |
| 33 | Qwen-Image-2512-GGUF | 20.4 B | — | ✓ apache-2.0 | 420 K | from 12.1 GB |
| 34 | Qwen-Image-2.1-Turbo-GGUF | — | — | other | 379 K | from 3.1 GB |
| 35 | DreamShaper | — | — | other | 366 K | from 185.3 GB |
| 36 | Z-Image-Lora | 6.2 B | — | ✓ apache-2.0 | 336 K | from 118.0 GB |
| 37 | Pony_Diffusion_V6_XL | — | — | cdla-permissive-2.0 | 335 K | from 8.5 GB |
| 38 | Z-Image-Turbo | 6.2 B | — | ✓ apache-2.0 | 329 K | from 37.5 GB |
| 39 | Flux-1-Schnell | 11.9 B | — | ✓ apache-2.0 | 325 K | from 47.4 GB |
| 40 | Qwen-Image | 20.4 B | — | ✓ apache-2.0 | 325 K | from 67.0 GB |
| 41 | Krea-2-Turbo | 12.8 B | — | other | 302 K | from 70.6 GB |
| 42 | animagine-xl-3.1 | 2.6 B | — | ⚠ openrail++ | 286 K | from 16.1 GB |
| 43 | controlnet-openpose-sdxl-1.0 | 1.3 B | — | ✓ apache-2.0 | 285 K | from 6.2 GB |
| 44 | FLUX.1-schnell | 11.9 B | — | ✓ apache-2.0 | 278 K | from 65.9 GB |
| 45 | IP-Adapter-FaceID | — | — | unknown | 274 K | from 1.5 GB |
| 46 | Noct-Q-Uncensored-Qwen-Image-2.1 | 7.1 B | — | other | 269 K | from 17.5 GB |
| 47 | Qwen-Image-2.1-Turbo-GGUF | — | — | other | 259 K | from 3.3 GB |
| 48 | waiIllustriousSDXL_v170 | — | — | cdla-permissive-2.0 | 259 K | from 8.1 GB |
| 49 | SDXL-Lightning | — | — | ⚠ openrail++ | 256 K | from 54.9 GB |
| 50 | Qwen-Image-2.1 | 7.1 B | — | other | 253 K | from 38.0 GB |
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API; API prices (blended 3:1 input:output per 1M tokens) and Artificial Analysis indices from OpenRouter.