How to load from_pretrained version 0.9.8-dev and the spatial upscaler 0.9.8
#105
by
andylele
- opened
import torch
from diffusers import LTXConditionPipeline, LTXLatentUpsamplePipeline
from diffusers.pipelines.ltx.pipeline_ltx_condition import LTXVideoCondition
from diffusers.utils import export_to_video, load_image, load_video
pipe = LTXConditionPipeline.from_pretrained("Lightricks/LTX-Video-0.9.8-dev", torch_dtype=torch.bfloat16)
pipe_upsample = LTXLatentUpsamplePipeline.from_pretrained("Lightricks/ltxv-spatial-upscaler-0.9.8", vae=pipe.vae, torch_dtype=torch.bfloat16)
This raise error that the repo_id cannot be found. Please help! Thank you
@andylele Please use the 0.9.7 repo for both models. They are the same as 0.9.8-dev and upscaler-0.9.8 (only the distilled model were changed in 0.9.8).