This is a basic checkpoint that works normally with comfyui. It's recommended to set --fp8_e5m2-unet --fp8_e5m2-text-enc to prevent crashes.

It's slower than sdxl, perhaps because it's new and the code isn't optimized, but it's much better. It works between 512 pixels and 2048 pixels, and at various extreme ratios.

cfg 2-10 between

steps 15-60 between

I'm not the original creator of the model. I just compiled it into a single file to make it easier for artists.

The model is excellent by all standards, very good at anatomy, safe, and excellent at composition.

Cosmos features four models: Cosmos-Predict2-2B-Text2Image and Cosmos-Predict2-14B-Text2Image for text-to-image generation for creating high-quality images from text descriptions, and Cosmos-Predict2-2B-Video2World and Cosmos-Predict2-14B-Video2World for video-to-world generation for producing visual simulations from image or video inputs. To accelerate the development of world models for Physical AI, we make our code, model weights, and the benchmark (PBench) available under the NVIDIA Open Model License.