How to use TurboDiffusion/TurboH3-FL2VA-I2VA with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("TurboDiffusion/TurboH3-FL2VA-I2VA", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0]
too large , it will be great if you can give us a lora only weight
Thanks for suggestion. Unfortunately, the checkpoint is trained full-parameter using DMD, so there is no LoRA to extract.
· Sign up or log in to comment
