how to quantization wan 2.2 vace after loading lora?

[chaowenguo]

diffusers.WanVACEPipeline.from_pretrained('linoyts/Wan2.2-VACE-Fun-14B-diffusers', vae=diffusers.AutoencoderKLWan.from_pretrained('linoyts/Wan2.2-VACE-Fun-14B-diffusers', subfolder='vae', torch_dtype=torch.float32), torch_dtype=torch.bfloat16, quantization_config=diffusers.PipelineQuantizationConfig(quant_backend='bitsandbytes_8bit', quant_kwargs={'load_in_8bit':True}, components_to_quantize=['transformer', 'transformer_2'])).save_pretrained('wan')

normally I can save the quantization model in this way
But now I want to merge lora and the quantization and then save the model with lora. How?

wan = diffusers.WanVACEPipeline.from_pretrained('linoyts/Wan2.2-VACE-Fun-14B-diffusers', vae=diffusers.AutoencoderKLWan.from_pretrained('linoyts/Wan2.2-VACE-Fun-14B-diffusers', subfolder='vae', torch_dtype=torch.float32), torch_dtype=torch.bfloat16)
wan.load_lora_weights('lightx2v/Wan2.2-Lightning', weight_name='Wan2.2-I2V-A14B-4steps-lora-rank64-Seko-V1/high_noise_model.safetensors', adapter_name='lightning')
wan.load_lora_weights('lightx2v/Wan2.2-Lightning', weight_name='Wan2.2-I2V-A14B-4steps-lora-rank64-Seko-V1/low_noise_model.safetensors', adapter_name='lightning_2', load_into_transformer_2=True)
wan.set_adapters(['lightning', 'lightning_2'], adapter_weights=[1] * 2)

how to quantization and save_pretrained?

@yiyixuxu @DN6

[JoeGaffney]

I think you need to fuse the loras then save. Possibly you only need to save the two transformers as well

[github-actions[bot]]

This issue has been automatically marked as stale because it has not had recent activity. If you think this still needs to be addressed please comment on this thread.

Please note that issues that do not follow the contributing guidelines are likely to be ignored.