Instructions to use Pclanglais/TintinIA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Pclanglais/TintinIA with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("Pclanglais/TintinIA") prompt = "drawing of tintin riding giant snowydog, flying in the air, night sky with stars, close-up" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Where is Chiquito ? :)
#2
by Slater0013 - opened
Hello,
Would you describe us how you trained your model ? So we could maybe add some more characters !
Thanks,
GS
Here is a blogpost from the author about the model (french): https://www.lebonllm.fr/tintinia-re-entrainer-un-modele-de-generation-dimages-sdxl/
Hello. Chiquito is already part of the model and you may be able to generate something approaching. The big issue is that there are not many images of him in the original comics. Even Haddock is not perfect still and I have nearly >50 portraits already.
Anyway, I plan to do a bigger update with more characters and roughly 500 panels whenever I have the time (and the compute, which I may soon have).