Instructions to use HiDream-ai/HiDream-I1-Full with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use HiDream-ai/HiDream-I1-Full with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("HiDream-ai/HiDream-I1-Full", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
the prompt token limit 77 ?
#40
by wmoon - opened
when i use "HiDream-ai/HiDream-I1-Full" in comfyui , the error of prompt token limit 77 shows:
Token indices sequence length is longer than the specified maximum sequence length for this model (83 > 77). Running this sequence through the model will result in indexing errors
other AI model has K level token length ,why HiDream only 77 Token length limit ?
it's a bug or other consider ?
anyone has the same problem ?
