Top open text-to-image models
Models that generate images from text descriptions.
How this list works: ranked by Hugging Face downloads in the last 30 days, among models with 1,000+ downloads.
| # | Model | Author | Downloads (30 days) | Likes | Size | License | Commercial use | Runs on |
|---|---|---|---|---|---|---|---|---|
| 1 | stable-diffusion-xl-base-1.0 | stabilityai | 4.3M | 8.4K | – | OpenRAIL++ | Yes, with conditions | CPU |
| 2 | Qwen-Image-2.1-Uncensored-Quantized | abenzerps | 2.7M | 4.6K | – | Custom (other) | Check the license | CPU |
| 3 | Qwen-Image-2.1-Uncensored-GGUF | abenzerps | 2.2M | 4K | – | Custom (other) | Check the license | CPU |
| 4 | Qwen-Image-2.1-GGUF | unsloth | 1.4M | 410 | – | Custom (other) | Check the license | CPU |
| 5 | stable-diffusion-v1-5 | stable-diffusion-v1-5 | 1.3M | 1.3K | – | CreativeML OpenRAIL-M | Yes, with conditions | GPU |
| 6 | Z-Image-Turbo-GGUF | unsloth | 1.1M | 280 | – | Apache 2.0 | Yes | CPU |
| 7 | dreamshaper-7 | Lykon | 875.9K | 69 | – | CreativeML OpenRAIL-M | Yes, with conditions | GPU |
| 8 | sd-turbo | stabilityai | 742.3K | 470 | – | Not stated | Check the license | GPU |
| 9 | RealVisXL_V5.0 | SG161222 | 739.6K | 257 | – | OpenRAIL++ | Yes, with conditions | GPU |
| 10 | sdxl-turbo | stabilityai | 685K | 2.7K | – | Custom (other) | Check the license | CPU |
| 11 | Z-Image-Turbo | Tongyi-MAI | 650.5K | 5.5K | – | Apache 2.0 | Yes | GPU |
| 12 | FLUX.1-dev | black-forest-labs | 647.2K | 15.6K | – | Custom (other) | Check the license | GPU |
| 13 | FLUX.1-schnell | black-forest-labs | 561.4K | 6.3K | – | Apache 2.0 | Yes | GPU |
| 14 | stable-diffusion-v1-4 | CompVis | 527.3K | 7.1K | – | CreativeML OpenRAIL-M | Yes, with conditions | GPU |
| 15 | Pruna-Qage-2.1 | PrunaAI | 514.2K | 157 | – | Custom (other) | Check the license | CPU or GPU |
| 16 | Pruna-Qwen-Image-2.1 | PrunaAI | 514.2K | 157 | – | Custom (other) | Check the license | CPU or GPU |
| 17 | Qwen-Image-2.1-viggle-turbo | Viggle | 509.6K | 756 | – | Custom (other) | Check the license | CPU |
| 18 | animagine-xl-4.0 | cagliostrolab | 478.4K | 555 | – | OpenRAIL++ | Yes, with conditions | GPU |
| 19 | Realistic_Vision_V5.1_noVAE | SG161222 | 409.2K | 271 | – | CreativeML OpenRAIL-M | Yes, with conditions | GPU |
| 20 | Qwen-Image-2.1-Turbo-Uncensored-GGUF | AtomicChat | 407.3K | 565 | – | Apache 2.0 | Yes | CPU |
| 21 | Qwen-Image-2.1-Turbo-GGUF | unsloth | 391.8K | 59 | – | Custom (other) | Check the license | CPU |
| 22 | Qwen-Image-2512-GGUF | unsloth | 330.5K | 428 | – | Apache 2.0 | Yes | CPU |
| 23 | Qwen-Image-2.1-FP8 | unsloth | 330.3K | 46 | – | Custom (other) | Check the license | CPU or GPU |
| 24 | Juggernaut-XL-v9 | RunDiffusion | 323.9K | 492 | – | CreativeML OpenRAIL-M | Yes, with conditions | CPU or GPU |
| 25 | Qwen-Image | Qwen | 282.4K | 2.7K | – | Apache 2.0 | Yes | GPU |
Other model comparisons
Top open language modelsTop open image modelsTop open audio modelsTop open video modelsTop open embedding modelsTop open multimodal modelsTop open text-generation models (LLMs)Top open text-to-speech modelsTop open speech-recognition modelsTop open feature-extraction modelsTop open sentence-similarity modelsTop open image-to-text modelsTop open vision-language modelsTop open image-classification modelsTop open image-segmentation modelsTop open object-detection modelsTop open depth-estimation modelsTop open audio-classification modelsTop open video-classification models