Instructions to use AIDC-AI/Ovis-Image-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use AIDC-AI/Ovis-Image-7B with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("AIDC-AI/Ovis-Image-7B", 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
- Draw Things
- DiffusionBee
More prompt examples?
#2
by notafraud - opened
Thank you for this model! I see that it uses CFG 5, but the examples only have positive prompts. Is there a recommended negative prompt or an example of it?
Thank you for your interest in our work! As demonstrated in our example implementation, we simply setting negative_prompt="" within the model configuration. You can explore it on your own if you are interested in setting this parameter.