Text-to-image models trending today
5 of the 40 models on Hugging Face’s trending list carry this task tag today, in Hugging Face’s order, with entries held back when likes are not matched by downloads.
Collected · snapshot shipped with the site build, not a live feed
5 of 5 models · Hugging Face order
Number 1: OpenMOSS-Team/MOSS-Image-SFT
Text to image5.08B parameters
No. 4 by Hugging Face trending score (444) · repository created 13 days ago · +4 likes since 2026-10-23.
7,658 downloads in 30 days · 660 likes
Apache-2.0· commercial use allowedNumber 2: OpenMOSS-Team/MOSS-Image-Base
Text to image5.08B parameters
No. 8 by Hugging Face trending score (330) · repository created 13 days ago · +2 likes since 2026-10-23.
5,618 downloads in 30 days · 524 likes
Apache-2.0· commercial use allowedNumber 3: abenzerps/Qwen-Image-2.1-Uncensored-Quantized
Text to image
No. 9 by Hugging Face trending score (317) · +5 likes since 2026-10-23 · 2,398,071 downloads in the last 30 days.
2.4M downloads in 30 days · 4,917 likes
Other (custom terms)· read the termsNumber 4: lodestones/Kromoss
Text to image5.08B parameters
No. 19 by Hugging Face trending score (231) · repository created 5 days ago · +3 likes since 2026-10-23.
16.4K downloads in 30 days · 236 likes
Apache-2.0· commercial use allowedNumber 5: briaai/Fibo-2.0-dev
Text to image8.13B parameters
No. 34 by Hugging Face trending score (131) · repository created 5 days ago.
753 downloads in 30 days · 132 likes
Other (custom terms)· read the terms
Positions follow Hugging Face’s trending order with 0 of 40 entries held back for likes that downloads do not confirm. Sorting by another column changes the order on your screen only.
Source: Hugging Face public API · updated
About text-to-image models
Text-to-image covers models that draw a picture from a written prompt, together with the fine-tunes, LoRA adapters and quantised copies built on them. Licences in this task are more often custom than in language models, so the licence column matters here more than anywhere else.
Before you pick one
Read the licence before the gallery
Many image models are released under a vendor licence tagged "other", with conditions on commercial use or on revenue. The tag does not tell you the conditions; the licence file in the repository does.
A LoRA is not a model
Small repositories with a base model listed are usually adapters: a few hundred megabytes that only work on top of the base weights. Check the base model line on the model page.
Formats tell you the tool
Safetensors with a diffusers layout loads in the diffusers library. Single-file or GGUF checkpoints are meant for ComfyUI and similar interfaces.
Questions readers ask
Why do GGUF image models have so many downloads?
Quantised checkpoints make large image models fit on consumer graphics cards, and interface tools download them automatically. One popular workflow can account for a large share of the count.
Are the images made by these models free to use?
That depends on the model licence and on the law where you are, not on this list. Some licences restrict commercial use of outputs; read the terms of the specific model.
Why is an "uncensored" copy sometimes above the original?
Trending measures recent attention, and modified copies of a new release often gather likes faster than the original for a few days. Both are listed; the model page names the base model.