Instructions to use ali-vilab/In-Context-LoRA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ali-vilab/In-Context-LoRA with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("ali-vilab/In-Context-LoRA") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
The maximum number of tokens is 77?
#11
by Emilia515 - opened
Hello, when I use the model, I encounter the problem of the maximum number of tokens 77, and the model will directly cut off the content behind my token. Is this normal? Even the official sample did not generate the image correctly because some tokens were truncated