Instructions to use toxicdog/ERNIE-Image-Turbo-INT4-ConvRot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use toxicdog/ERNIE-Image-Turbo-INT4-ConvRot with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("toxicdog/ERNIE-Image-Turbo-INT4-ConvRot", 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
Commit History
-
Enable Hub download tracking
Verified signatureUse the Diffusers query-file rule so downloads of the root single-file checkpoint are counted.d50354a -
Add ERNIE Image Turbo INT4 ConvRot model
Verified signatureAdd a ComfyUI native ConvRot W4A4 conversion of the ERNIE Image Turbo diffusion transformer, with source details, protected-layer notes, checksum, license, and Radiant Canvas testing link.742b7cb -
initial commit
Verified signatureb38609e