Instructions to use ixim/ERNIE-Image-INT8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ixim/ERNIE-Image-INT8 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("ixim/ERNIE-Image-INT8", 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
- Draw Things
- DiffusionBee
| { | |
| "_class_name": "ErnieImageTransformer2DModel", | |
| "_diffusers_version": "0.38.0.dev0", | |
| "_name_or_path": "Baidu/ERNIE-Image", | |
| "eps": 1e-06, | |
| "ffn_hidden_size": 12288, | |
| "hidden_size": 4096, | |
| "in_channels": 128, | |
| "num_attention_heads": 32, | |
| "num_layers": 36, | |
| "out_channels": 128, | |
| "patch_size": 1, | |
| "qk_layernorm": true, | |
| "quantization_config": { | |
| "modules_to_not_convert": [ | |
| "norm", | |
| "layer_norm", | |
| "ln", | |
| "embed_tokens", | |
| "lm_head", | |
| "proj_out" | |
| ], | |
| "quant_method": "quanto", | |
| "weights_dtype": "int8" | |
| }, | |
| "rope_axes_dim": [ | |
| 32, | |
| 48, | |
| 48 | |
| ], | |
| "rope_theta": 256, | |
| "text_in_dim": 3072 | |
| } |