Text-to-Image
Diffusers
Safetensors
English
AuroraIMG2Pipeline
flow-matching
rectified-flow
diffusion-transformer
tiny-model
from-scratch
muon
diloco
custom_code
Instructions to use cpral/IMG-50M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use cpral/IMG-50M with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("cpral/IMG-50M", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Download tokenizer/tokenizer_config.json from cpral/IMG-50M: direct link, hf CLI and curl.
- Browser
- Download file 249 Bytes
-
https://huggingface.co/cpral/IMG-50M/resolve/main/tokenizer/tokenizer_config.json
- Command line
-
hf download hf://cpral/IMG-50M/tokenizer/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/cpral/IMG-50M/resolve/main/tokenizer/tokenizer_config.json
249 Bytes
| { | |
| "backend": "tokenizers", | |
| "bos_token": "[BOS]", | |
| "eos_token": "[EOS]", | |
| "mask_token": "[MASK]", | |
| "model_max_length": 1000000000000000019884624838656, | |
| "pad_token": "[PAD]", | |
| "tokenizer_class": "TokenizersBackend", | |
| "unk_token": "[UNK]" | |
| } | |