utBlack Forest Labs · Downloadable
FLUX.2-dev
Creates or edits images. Check the model card for supported inputs and output settings.
- Source listed
- Nov 22, 2025
- Parameters
- 32.2B
- 4-bit weights only
- ≈ 16.1 GB
- License
- other
WHAT’S NEW
New AI models.
Keep up without the noise.
The latest source listings from makers we track, covering language, images, video, audio, and 3D. Catalog checked Oct 28, 2026.
Sorted by the date a source repository was created, which may precede public release. This is a feed of new listings, not confirmed release announcements. Downloadable weights do not automatically mean an open-source license. Coverage and date meanings.
Images listings
147 dated recordsBAAI · Downloadable
URSA-0.6B-IBQ1024
Creates or edits images. Check the model card for supported inputs and output settings.
- Source listed
- Nov 2, 2025
- Parameters
- 600M
- 4-bit weights only
- ≈ 0.3 GB
- License
- apache-2.0
BAAI · Downloadable
Emu3.5-Image
Creates or edits images. Check the model card for supported inputs and output settings.
- Source listed
- Oct 31, 2025
- Parameters
- 34.1B
- 4-bit weights only
- ≈ 17.1 GB
- License
- apache-2.0
inclusionAI · Downloadable
TwinFlow
Creates or edits images. Check the model card for supported inputs and output settings.
- Source listed
- Oct 24, 2025
- Parameters
- Not reported
- 4-bit weights only
- Not reported
- License
- apache-2.0
BAAI · Downloadable
URSA-1.7B-IBQ1024
Creates or edits images. Check the model card for supported inputs and output settings.
- Source listed
- Oct 23, 2025
- Parameters
- 1.7B
- 4-bit weights only
- ≈ 0.9 GB
- License
- apache-2.0
BRIA AI · Downloadable
FIBO
Creates or edits images. Check the model card for supported inputs and output settings.
- Source listed
- Oct 9, 2025
- Parameters
- 8.3B
- 4-bit weights only
- ≈ 4.1 GB
- License
- other
OpenAI · Cloud
gpt-image-1-mini
Cloud API for vision, image generation, image editing, chat & writing. Capabilities are catalog-listed, not independently scored.
- Source listed
- Sep 26, 2025
- License
- Provider terms
Tencent · Downloadable
HunyuanImage-3.0-Instruct
Creates or edits images. Check the model card for supported inputs and output settings.
- Source listed
- Sep 25, 2025
- Parameters
- 83B
- 4-bit weights only
- ≈ 41.5 GB
- License
- other
Tencent · Downloadable
HunyuanImage-3.0
Creates or edits images. Check the model card for supported inputs and output settings.
- Source listed
- Sep 25, 2025
- Parameters
- 83B
- 4-bit weights only
- ≈ 41.5 GB
- License
- other
Qwen · Alibaba · Downloadable
Qwen-Image-Edit-2509
Creates or edits images. Check the model card for supported inputs and output settings.
- Source listed
- Sep 22, 2025
- Parameters
- 20.4B
- 4-bit weights only
- ≈ 10.2 GB
- License
- apache-2.0
Tencent · Downloadable
SRPO
Creates or edits images. Check the model card for supported inputs and output settings.
- Source listed
- Sep 8, 2025
- Parameters
- 11.9B
- 4-bit weights only
- ≈ 6 GB
- License
- other
StepFun · Preview
Step1X-Edit-v1p2-preview
Creates or edits images. Check the model card for supported inputs and output settings.
- Source listed
- Sep 7, 2025
- Parameters
- 12.4B
- 4-bit weights only
- ≈ 6.2 GB
- License
- apache-2.0
Tencent · Downloadable
HunyuanImage-2.1
Creates or edits images. Check the model card for supported inputs and output settings.
- Source listed
- Sep 5, 2025
- Parameters
- Not reported
- 4-bit weights only
- Not reported
- License
- other
StepFun · Downloadable
Step1X-Edit-v1p1-diffusers
Creates or edits images. Check the model card for supported inputs and output settings.
- Source listed
- Aug 27, 2025
- Parameters
- 12.4B
- 4-bit weights only
- ≈ 6.2 GB
- License
- apache-2.0
Google · Cloud
Nano Banana
Cloud API for vision, image generation, image editing, chat & writing. Capabilities are catalog-listed, not independently scored.
- Source listed
- Aug 26, 2025
- License
- Provider terms
Qwen · Alibaba · Downloadable
Qwen-Image-Edit
Creates or edits images. Check the model card for supported inputs and output settings.
- Source listed
- Aug 17, 2025
- Parameters
- 20.4B
- 4-bit weights only
- ≈ 10.2 GB
- License
- apache-2.0
StepFun · Downloadable
NextStep-1-Large-Pretrain
Creates or edits images. Check the model card for supported inputs and output settings.
- Source listed
- Aug 15, 2025
- Parameters
- 15B
- 4-bit weights only
- ≈ 7.5 GB
- License
- apache-2.0
StepFun · Downloadable
NextStep-1-Large
Creates or edits images. Check the model card for supported inputs and output settings.
- Source listed
- Aug 12, 2025
- Parameters
- 15B
- 4-bit weights only
- ≈ 7.5 GB
- License
- apache-2.0
StepFun · Downloadable
NextStep-1-Large-Edit
Creates or edits images. Check the model card for supported inputs and output settings.
- Source listed
- Aug 12, 2025
- Parameters
- 15B
- 4-bit weights only
- ≈ 7.5 GB
- License
- apache-2.0
Qwen · Alibaba · Downloadable
Qwen-Image
Creates or edits images. Check the model card for supported inputs and output settings.
- Source listed
- Aug 2, 2025
- Parameters
- 20.4B
- 4-bit weights only
- ≈ 10.2 GB
- License
- apache-2.0
Black Forest Labs · Downloadable
FLUX.1-Krea-dev
Creates or edits images. Check the model card for supported inputs and output settings.
- Source listed
- Jul 7, 2025
- Parameters
- 11.9B
- 4-bit weights only
- ≈ 6 GB
- License
- other
Black Forest Labs · Downloadable
FLUX.1-Kontext-dev
Creates or edits images. Check the model card for supported inputs and output settings.
- Source listed
- May 28, 2025
- Parameters
- 11.9B
- 4-bit weights only
- ≈ 6 GB
- License
- other
Microsoft · Downloadable
renderformer-v1.1-swin-large
Creates or edits images. Check the model card for supported inputs and output settings.
- Source listed
- May 15, 2025
- Parameters
- 483.3M
- 4-bit weights only
- ≈ 0.2 GB
- License
- mit
Microsoft · Downloadable
renderformer-v1-base
Creates or edits images. Check the model card for supported inputs and output settings.
- Source listed
- May 15, 2025
- Parameters
- 205.2M
- 4-bit weights only
- ≈ 0.1 GB
- License
- mit
What makes this feed useful?
Capability tags distinguish a model that reads images from one that creates them. Each listing links to its source and a permanent profile, so you can inspect its license and compare it with a model you already know.
Does this cover every new release?
No. The current feed tracks public Hugging Face metadata from selected makers. It can miss untracked makers, cloud-only releases, and records beyond a source’s retrieval limit. Announced models without a source listing are not included. Check Sources & methodology for the current coverage.
Listings update with the catalog automatically. A missing or delayed source can leave older information visible; each model profile shows when it was checked.