1,011 models · refreshed nightly
Text to image models
Every model in the catalog with its licence, estimated VRAM and daily-tracked downloads. Filters update the URL — share any view.
| # | Model | Params | Context | Commercial use | 30d | Min VRAM |
|---|---|---|---|---|---|---|
| 101 | Wan2.2-I2V_General-NSFW-LoRA | — | — | unknown | 29 K | from 1.8 GB |
| 102 | FLUX.2-klein-4B-SDNQ-4bit-dynamic | 2.2 B | — | ✓ apache-2.0 | 29 K | from 6.8 GB |
| 103 | DMD2 | — | — | ✗ cc-by-nc-4.0 | 29 K | from 7.4 GB |
| 104 | Juggernaut-XI-v11 | — | — | ✗ cc-by-nc-nd-4.0 | 28 K | from 8.3 GB |
| 105 | controlnet-scribble-sdxl-1.0 | 1.3 B | — | ✓ apache-2.0 | 27 K | from 3.4 GB |
| 106 | realisticVisionV51_v51VAE-inpainting | 860 M | — | ⚠ creativeml-openrail-m | 26 K | from 3.6 GB |
| 107 | flux2-klein-9b-uncensored-text-encoder | 8.2 B | — | other | 26 K | from 7.3 GB |
| 108 | Krea2-realism-V2 | — | — | ✓ mit | 26 K | from 2.2 GB |
| 109 | krea2_turbo_training_adapter | — | — | other | 26 K | from 0.8 GB |
| 110 | girlslike-zimage | — | — | ✓ apache-2.0 | 24 K | from 6.5 GB |
| 111 | Chroma-GGUF | — | — | ✓ apache-2.0 | 24 K | from 6.0 GB |
| 112 | Qwen-Image-2512-Turbo-LoRA-2-Steps | — | — | ✓ apache-2.0 | 23 K | from 3.1 GB |
| 113 | stable-diffusion-v1-5-GGUF | — | — | ⚠ creativeml-openrail-m | 22 K | from 2.2 GB |
| 114 | LUSTIFY-v2.0 | 2.6 B | — | unknown | 22 K | from 31.4 GB |
| 115 | RealVisXL_V5.0_Lightning | 2.6 B | — | ⚠ openrail++ | 22 K | from 46.7 GB |
| 116 | Juggernaut-X-v10 | — | — | ⚠ creativeml-openrail-m | 22 K | from 8.3 GB |
| 117 | Photon_v1 | 860 M | — | other | 22 K | from 10.0 GB |
| 118 | pony-v7-base | 6.9 B | — | other | 22 K | from 5.9 GB |
| 119 | Z-Image | 6.2 B | — | ✓ apache-2.0 | 22 K | from 24.0 GB |
| 120 | controlnet-canny-sdxl-1.0 | 1.3 B | — | ✓ apache-2.0 | 21 K | from 6.2 GB |
| 121 | nunchaku-qwen-image-edit-2509 | — | — | ✓ apache-2.0 | 21 K | from 271.1 GB |
| 122 | NetaYume-Lumina-Image-2.0 | — | — | ✓ apache-2.0 | 21 K | from 99.5 GB |
| 123 | controlnet-canny-sdxl-1.0 | 1.3 B | — | ⚠ openrail++ | 21 K | from 8.9 GB |
| 124 | realistic-vision-v51 | 860 M | — | ⚠ creativeml-openrail-m | 20 K | from 3.6 GB |
| 125 | Chroma1-Base | 8.9 B | — | ✓ apache-2.0 | 20 K | from 51.7 GB |
| 126 | stable-diffusion-2-1 | 870 M | — | ⚠ openrail++ | 20 K | from 20.6 GB |
| 127 | bigaspv2-5 | 2.6 B | — | unknown | 20 K | from 16.1 GB |
| 128 | stable-diffusion-3.5-large-GGUF | — | — | other | 20 K | from 6.1 GB |
| 129 | controlnet-depth-sdxl-1.0 | 1.3 B | — | ⚠ openrail++ | 19 K | from 8.9 GB |
| 130 | Z-Image-Turbo_Models | — | — | other | 19 K | from 13.2 GB |
| 131 | waiIllustriousSDXL_v170 | — | — | cdla-permissive-2.0 | 19 K | from 8.1 GB |
| 132 | HiDream-I1-Full | 17.1 B | — | ✓ mit | 18 K | from 55.0 GB |
| 133 | moeFussion | — | — | ⚠ creativeml-openrail-m | 18 K | from 471.8 GB |
| 134 | Krea-2-Realism-LoRA | — | — | other | 18 K | from 1.0 GB |
| 135 | controlnet-depth-sdxl-1.0 | 1.3 B | — | ✓ apache-2.0 | 17 K | from 3.4 GB |
| 136 | AWPortrait-FL | 11.9 B | — | other | 17 K | from 79.3 GB |
| 137 | krea2-gguf | — | — | other | 17 K | from 9.6 GB |
| 138 | controlnet-tile-sdxl-1.0 | 1.3 B | — | ✓ apache-2.0 | 17 K | from 3.4 GB |
| 139 | flux-ip-adapter | — | — | other | 16 K | from 1.6 GB |
| 140 | chilloutmix | — | — | ⚠ creativeml-openrail-m | 16 K | — |
| 141 | stable-diffusion-3.5-medium-GGUF | — | — | other | 16 K | from 2.0 GB |
| 142 | ProteusV0.3 | — | — | gpl-3.0 | 16 K | from 8.1 GB |
| 143 | ERNIE-Image | 8.0 B | — | ✓ apache-2.0 | 16 K | from 36.5 GB |
| 144 | ProteusV0.2 | — | — | gpl-3.0 | 16 K | from 8.1 GB |
| 145 | epiCRealism | 860 M | — | ⚠ creativeml-openrail-m | 16 K | from 6.7 GB |
| 146 | RealVisXL_V3.0 | 2.6 B | — | ⚠ openrail++ | 16 K | from 31.4 GB |
| 147 | FLUX.1-dev-ControlNet-Union-Pro-2.0 | 2.1 B | — | other | 16 K | from 5.5 GB |
| 148 | true-pencil-xl-v100-sdxl | 2.6 B | — | other | 16 K | from 8.5 GB |
| 149 | autismmix-sdxl-autismmix-pony-sdxl | 2.6 B | — | other | 16 K | from 8.5 GB |
| 150 | HunyuanImage-3.0 | 83.0 B | 23 K | other | 16 K | from 198.3 GB |
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API.