import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("city96/Cosmos-Predict2-14B-Text2Image-gguf", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]This is a direct GGUF conversion of nvidia/Cosmos-Predict2-14B-Text2Image.
The model files can be used in ComfyUI with the ComfyUI-GGUF custom node. Place the required model(s) in the following folders:
| Type | Name | Location | Download |
|---|---|---|---|
| Main Model | Cosmos-Predict2-14B-Text2Image | ComfyUI/models/diffusion_models |
GGUF (this repo) |
| Text Encoder | (old) T5-XXL-Encoder | ComfyUI/models/text_encoders |
Safetensors |
| VAE | Wan 2.1 VAE | ComfyUI/models/vae |
Safetensors |
Example workflow - based on the official example workflow
Example outputs - sample size of 1, not strictly representative
Notes
As this is a quantized model not a finetune, all the same restrictions/original license terms still apply.
- Downloads last month
- 878
Hardware compatibility
Log In to add your hardware
3-bit
4-bit
5-bit
6-bit
8-bit
16-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for city96/Cosmos-Predict2-14B-Text2Image-gguf
Base model
nvidia/Cosmos-Predict2-14B-Text2Image