replace stable-diffusion-1-5 model

Tianfu18 / diff-feats-pose

[CVPR 2024 Highlight] PyTorch implementation of "Object Pose Estimation via the Aggregation of Diffusion Features"

29 stars 1 forks source link

replace stable-diffusion-1-5 model #3

Closed lxmaczj closed 2 months ago

lxmaczj commented 2 months ago

I changed stable-diffusion-1-5 from config_run to stable-diffusion-3-medium-diffusers,but there is a mistake here: Pipeline <class 'diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline'> expected {'vae', 'unet', 'image_encoder', 'text_encoder', 'feature_extractor', 'tokenizer', 'safety_checker', 'scheduler'}, but only {'vae', 'scheduler', 'tokenizer', 'text_encoder'} were passed. How should it be solved?

Tianfu18 commented 2 months ago

Our code currently does not support SD-V3. Please carefully check the network structure of both SD-V3 and SD-V1-5.