1,226 models · 1,226 open weights · 200 API-only · refreshed nightly
Open-weights models
Models whose weights are published on Hugging Face — download them and run them on your own hardware. Many are also served by hosted providers; those carry an "Also via API" badge with live prices.
| # | Model | Params | Context | Commercial use | 30d | Min VRAM |
|---|---|---|---|---|---|---|
| 01 | stable-diffusion-xl-base-1.0 | 2.6 B | — | ⚠ openrail++ | 4.1 M | from 39.7 GB |
| 02 | Qwen-Image-2.1-Uncensored-Quantized | 7.1 B | — | other | 2.4 M | from 6.1 GB |
| 03 | Qwen-Image-2.1-Uncensored-GGUF | 7.1 B | — | other | 2.2 M | from 6.1 GB |
| 04 | Qwen-Image-2.1-GGUF | 7.1 B | — | other | 1.5 M | from 4.3 GB |
| 05 | stable-diffusion-v1-5 | 860 M | — | ⚠ creativeml-openrail-m | 1.1 M | from 26.6 GB |
| 06 | Z-Image-Turbo-GGUF | — | — | ✓ apache-2.0 | 1.1 M | from 4.5 GB |
| 07 | dreamshaper-7 | 860 M | — | ⚠ creativeml-openrail-m | 846 K | from 9.7 GB |
| 08 | RealVisXL_V5.0 | 2.6 B | — | ⚠ openrail++ | 781 K | from 46.7 GB |
| 09 | sd-turbo | 870 M | — | unknown | 732 K | from 14.9 GB |
| 10 | Z-Image-Turbo | 6.2 B | — | ✓ apache-2.0 | 651 K | from 37.5 GB |
| 11 | FLUX.1-dev | 11.9 B | — | other | 627 K | from 66.0 GB |
| 12 | sdxl-turbo | 2.6 B | — | other | 610 K | from 46.7 GB |
| 13 | FLUX.1-schnell | 11.9 B | — | ✓ apache-2.0 | 536 K | from 65.9 GB |
| 14 | Qwen-Image-2.1-viggle-turbo | 7.1 B | — | other | 521 K | from 6.3 GB |
| 15 | Pruna-Q-Image-2.1 | 7.1 B | — | other | 516 K | from 2.3 GB |
| 16 | Pruna-Qage-2.1 | 7.1 B | — | other | 514 K | from 2.3 GB |
| 17 | animagine-xl-4.0 | 2.6 B | — | ⚠ openrail++ | 514 K | from 23.8 GB |
| 18 | Pruna-Qwen-Image-2.1 | 7.1 B | — | other | 513 K | from 2.3 GB |
| 19 | Qwen-Image-2.1-Turbo-GGUF | — | — | other | 495 K | from 3.2 GB |
| 20 | stable-diffusion-v1-4 | 860 M | — | ⚠ creativeml-openrail-m | 484 K | from 13.5 GB |
| 21 | Qwen-Image-2.1-Turbo-Uncensored-GGUF | 8.8 B | — | ✓ apache-2.0 | 468 K | from 5.5 GB |
| 22 | Qwen-Image-2.1-FP8 | 7.1 B | — | other | 419 K | from 46.7 GB |
| 23 | Realistic_Vision_V5.1_noVAE | 860 M | — | ⚠ creativeml-openrail-m | 349 K | from 19.4 GB |
| 24 | Juggernaut-XL-v9 | — | — | ⚠ creativeml-openrail-m | 338 K | from 15.9 GB |
| 25 | Qwen-Image-2512-GGUF | — | — | ✓ apache-2.0 | 318 K | from 8.6 GB |
| 26 | Qwen-Image | 20.4 B | — | ✓ apache-2.0 | 285 K | from 67.0 GB |
| 27 | Noct-Q-Uncensored-Qwen-Image-2.1 | 7.1 B | — | other | 280 K | from 17.5 GB |
| 28 | noobai-XL-1.1 | 2.6 B | — | other | 266 K | from 16.3 GB |
| 29 | Pony_Diffusion_V6_XL | — | — | cdla-permissive-2.0 | 247 K | from 8.5 GB |
| 30 | Qwen-Image-2.1-Turbo-GGUF | — | — | other | 234 K | from 3.1 GB |
| 31 | Z-Image-Lora | 6.2 B | — | ✓ apache-2.0 | 233 K | from 114.5 GB |
| 32 | DreamShaper | — | — | other | 231 K | from 185.3 GB |
| 33 | IP-Adapter-FaceID | — | — | unknown | 220 K | from 1.5 GB |
| 34 | Qwen-Image-2.1 | 7.1 B | — | other | 209 K | from 38.0 GB |
| 35 | Qwen-Image-Lightning | 20.4 B | — | ✓ apache-2.0 | 208 K | from 75.6 GB |
| 36 | FLUX.1-dev-gguf | — | — | other | 199 K | from 4.9 GB |
| 37 | stable-diffusion-inpainting | — | — | ⚠ creativeml-openrail-m | 199 K | from 3.5 GB |
| 38 | controlnet-openpose-sdxl-1.0 | 1.3 B | — | ✓ apache-2.0 | 197 K | from 6.2 GB |
| 39 | Qwen-Image-2.1-Turbo-FP8 | 7.1 B | — | other | 192 K | from 61.1 GB |
| 40 | Qwen-Image-2.1-Lightning | 7.1 B | — | unknown | 191 K | from 1.6 GB |
| 41 | animagine-xl-3.1 | 2.6 B | — | ⚠ openrail++ | 186 K | from 16.1 GB |
| 42 | revanimated | — | — | ⚠ creativeml-openrail-m | 184 K | — |
| 43 | HunyuanDiT-v1.1-Diffusers-Distilled | 1.5 B | — | other | 174 K | from 16.7 GB |
| 44 | Qwen-Image-2.1-Turbo-GGUF | — | — | other | 172 K | from 3.3 GB |
| 45 | Qwen-Image-2.1 | 7.1 B | — | other | 171 K | from 38.0 GB |
| 46 | Krea-2-Turbo | 12.8 B | — | other | 169 K | from 70.6 GB |
| 47 | stable-diffusion-v1-1 | — | — | ⚠ creativeml-openrail-m | 168 K | from 3.5 GB |
| 48 | nova-furry-xl-il-v120-sdxl | 2.6 B | — | other | 156 K | from 8.5 GB |
| 49 | LCM_Dreamshaper_v7 | 860 M | — | ✓ mit | 152 K | from 10.4 GB |
| 50 | Qwen-Image-2.1-GGUF | — | — | unknown | 145 K | from 3.3 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.