Text-to-Image
Diffusers
Safetensors
English
AuroraIMG2Pipeline
flow-matching
rectified-flow
diffusion-transformer
from-scratch
muon
diloco
repa
custom_code
Instructions to use cpral/IMG-253M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use cpral/IMG-253M 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-253M", 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-253M: direct link, hf CLI and curl.
- Browser
- Download file 476 Bytes
-
https://huggingface.co/cpral/IMG-253M/resolve/main/text_encoder/config.json
- Command line
-
hf download hf://cpral/IMG-253M/text_encoder/config.json
-
curl -L -o config.json https://huggingface.co/cpral/IMG-253M/resolve/main/text_encoder/config.json
476 Bytes
| { | |
| "_class_name": "AuroraLMTextEncoder", | |
| "_diffusers_version": "0.42.1", | |
| "kind": "lm", | |
| "vocab_size": 12288, | |
| "lm_blocks": 18, | |
| "lm_dim": 768, | |
| "lm_heads": 12, | |
| "lm_ffn_mult": 2.8125, | |
| "lm_norm_eps": 1e-06, | |
| "lm_rope_theta": 100000.0, | |
| "lm_value_residual": true, | |
| "lm_qk_norm": true, | |
| "dim": 768, | |
| "depth": 2, | |
| "heads": 12, | |
| "kv_heads": 4, | |
| "head_dim": 64, | |
| "mlp_hidden": 2048, | |
| "max_tokens": 96, | |
| "bos_id": 12285, | |
| "pad_id": 65535, | |
| "null_id": 65534 | |
| } |