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 text_encoder/config.json from cpral/IMG-50M: direct link, hf CLI and curl.
- Browser
- Download file 292 Bytes
-
https://huggingface.co/cpral/IMG-50M/resolve/main/text_encoder/config.json
- Command line
-
hf download hf://cpral/IMG-50M/text_encoder/config.json
-
curl -L -o config.json https://huggingface.co/cpral/IMG-50M/resolve/main/text_encoder/config.json
292 Bytes
| { | |
| "_class_name": "AuroraTextEncoder", | |
| "_diffusers_version": "0.42.1", | |
| "bos_id": 2, | |
| "depth": 6, | |
| "dim": 384, | |
| "eos_id": 3, | |
| "head_dim": 64, | |
| "heads": 6, | |
| "kv_heads": 2, | |
| "mask_id": 5, | |
| "max_tokens": 64, | |
| "mlp_hidden": 1024, | |
| "null_id": 4, | |
| "pad_id": 0, | |
| "vocab_size": 8192 | |
| } |