Which open-weight image and video generation models get downloaded most
A daily read of Hugging Face's top 5,000 models, focused on image and video generation models, the models that make pictures and clips from text, images or video: the most downloaded, new uploads in the top 5,000, what they are used for, and who makes them.
The most-downloaded open-weight image and video generation models
Ranked by downloads over the last 30 days. Fine-tuned versions count; most format conversions and re-uploads are left out. Counts include automated fetches, which lift models that tools and test suites pull by default. How models are placed is explained under About this data.
Across Hugging Face's top 5,000, ComfyUI repackages, which no page here counts, are 85 repos with 87.0M downloads in the last 30 days, 3.2% of all top-5,000 downloads; most carry no task tag.
| # | Model | Downloads | |
|---|---|---|---|
| 1 | stable-diffusion-xl-base-1.0 | 4.1M | |
| 2 | MiniMax-H3 | 3.6M | |
| 3 | stable-diffusion-v1-5 | 1.7M | |
| 4 | LTX-2.5 | 1.6M | |
| 5 | Minimax-h3-Turbo | 1.5M | |
| 6 | LTX-2.3 | 1.1M | |
| 7 | sdxl-turbo | 1.0M | |
| 8 | FastVideo-FastH3-4-step-Preview-v1-VSA-DataFree | 962K | |
| 9 | dreamshaper-7 | 884K | |
| 10 | LTX-Video | 778K | |
| 11 | FLUX.1-dev | 699K | |
| 12 | stable-diffusion-v1-4 | 684K | |
| 13 | Juggernaut-XL-v9 | 606K | |
| 14 | Z-Image-Turbo | 589K | Fine-tune one → |
| 15 | FLUX.1-schnell | 588K | Fine-tune one → |
| 16 | Realistic_Vision_V5.1_noVAE | 501K | |
| 17 | Minimax-h3_Singularity | 490K | |
| 18 | sd-turbo | 484K | |
| 19 | Qwen-Image-Edit-2509 | 465K | Fine-tune one → |
| 20 | RealVisXL_V5.0 | 452K | |
| 21 | FLUX.2-dev | 405K | |
| 22 | FLUX.2-klein-4B | 404K | Fine-tune one → |
| 23 | animagine-xl-4.0 | 368K | |
| 24 | HunyuanDiT-v1.1-Diffusers-Distilled | 358K | |
| 25 | Qwen-Image-Lightning | 358K | Fine-tune one → |
New image and video generation models in the top 5,000
Uploaded to Hugging Face in the last six months with at least 25 likes or a trending score of 10, ranked by downloads over the last 30 days. Most format conversions and re-uploads are left out.
Downloads by task
Share of downloads of image and video generation models in Hugging Face's top 5,000 on Oct 2, 2026, leaving out most format conversions and re-uploads.
Share of downloads by maker
Each repo counts under the account that uploaded it, leaving out most format conversions and re-uploads. Change is in percentage points since Jul 4, 2026.
Licences of the most-downloaded image and video generation models
As declared on each repo, leaving out most format conversions and re-uploads.