import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("wfen/Cosmos3-Nano-NVFP4-Blockwise", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Cosmos3-Nano NVFP4 Quantized Checkpoint
This is a quantized checkpoint of Cosmos3-Nano. The inference quality is quite close to the FP8 checkpoint, but NVFP4 is Blackwell architecture only for now.
Quick Example
Checkout Cosmos3-Nano-WebUI to setup a quick web interface for generating images/videos/reasoning/actions with this checkpoint. Screenshots and walkthrough is available here.
- Downloads last month
- 11
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for wfen/Cosmos3-Nano-NVFP4-Blockwise
Base model
nvidia/Cosmos3-Nano