Text-to-Image
Diffusers
Safetensors
Cosmos
English
Cosmos3OmniPipeline
nvidia
cosmos3
world-model
diffusion
image-generation
quantized
bitsandbytes
nf4
4-bit precision
8-bit precision
Instructions to use SanDiegoDude/Cosmos3-Super-Text2Image-nf4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use SanDiegoDude/Cosmos3-Super-Text2Image-nf4 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("SanDiegoDude/Cosmos3-Super-Text2Image-nf4", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Cosmos
How to use SanDiegoDude/Cosmos3-Super-Text2Image-nf4 with Cosmos:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Download model_index.json from SanDiegoDude/Cosmos3-Super-Text2Image-nf4: direct link, hf CLI and curl.
- Browser
- Download file 562 Bytes
-
https://huggingface.co/SanDiegoDude/Cosmos3-Super-Text2Image-nf4/resolve/main/model_index.json
- Command line
-
hf download hf://SanDiegoDude/Cosmos3-Super-Text2Image-nf4/model_index.json
-
curl -L -o model_index.json https://huggingface.co/SanDiegoDude/Cosmos3-Super-Text2Image-nf4/resolve/main/model_index.json
562 Bytes
| { | |
| "_class_name": "Cosmos3OmniPipeline", | |
| "_diffusers_version": "0.39.0.dev0", | |
| "_name_or_path": "/home/nathan/shared/ComfyUI/models/Cosmos3/Cosmos3-Super-Text2Image", | |
| "safety_checker": [ | |
| null, | |
| null | |
| ], | |
| "scheduler": [ | |
| "diffusers", | |
| "UniPCMultistepScheduler" | |
| ], | |
| "sound_tokenizer": [ | |
| "diffusers", | |
| "Cosmos3AVAEAudioTokenizer" | |
| ], | |
| "text_tokenizer": [ | |
| "transformers", | |
| "Qwen2TokenizerFast" | |
| ], | |
| "transformer": [ | |
| "diffusers", | |
| "Cosmos3OmniTransformer" | |
| ], | |
| "vae": [ | |
| "diffusers", | |
| "AutoencoderKLWan" | |
| ] | |
| } | |