Sign In
homemodelsimagesvideos3D Modelshubsarticlescomicscruciblesupdatesshop

DIV2K Photorealism

1.1k

Updated: Aug 24, 2026

style

Loaded

Download

1 variant available

fp16 SafeTensor

div2k_anima_v1-step00000360.safetensors

Half precision, best balance • 126.34 MB

Verified:

Type
LoRA
Stats

340

1.1K

1.1K

Generation

Loaded

Reviews

(31)

Published

Aug 15, 2026

Base Model

Anima

Training
Steps: 360
Usage Tips
Strength: 1
Hash
AutoV2
DAA71E3910
Trigger Words
realistic, photo \(medium\),real life,masterpiece, best quality, score_7,
default creator card background decoration
Followers - 1936

1.9K

Downloads - 84340

84.3K

Generations - 774498

774.5K

Second Birthday Badge

License:

Anima

The Anima Model is licensed by CircleStone Labs LLC. Copyright CircleStone Labs LLC. IN NO EVENT SHALL CIRCLESTONE LABS LLC BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.

Built on NVIDIA Cosmos

8e688793-2f72-4327-8823-124431cdfd4d-3.jpg

Trained on a tagged subset of the publicly available div2k photo dataset. Removed the 'realistic/photo/etc' style tags, so tags are not needed to get the effect of the lora, but adding the suggested tags helps a lot if you want photorealism. No tags makes it more like a semi-realism detailer.