Skip to content

feat: support Qwen-Image/Wan VAE with original naming#1713

Open
stduhpf wants to merge 1 commit into
leejet:masterfrom
stduhpf:orig-qwen-vae
Open

feat: support Qwen-Image/Wan VAE with original naming#1713
stduhpf wants to merge 1 commit into
leejet:masterfrom
stduhpf:orig-qwen-vae

Conversation

@stduhpf

@stduhpf stduhpf commented Jun 26, 2026

Copy link
Copy Markdown
Contributor

Summary

Adds support for Qwen-Image VAE downladed from https://huggingface.co/Qwen/Qwen-Image-Edit-2511/blob/main/vae/diffusion_pytorch_model.safetensors instead of https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/blob/main/split_files/vae/qwen_image_vae.safetensors.

This is a first step towards implementing #1610

Related Issue / Discussion

N/A

Additional Information

N/A

Checklist

@stduhpf stduhpf mentioned this pull request Jun 26, 2026
1 task
Comment thread src/name_conversion.cpp
}

std::string convert_first_stage_model_name(std::string name, std::string prefix) {
std::string convert_original_qwen_to_comfy(std::string name) {

Copy link
Copy Markdown
Owner

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This should be named convert_diffusers_to_original_wan_vae.

https://github.com/Wan-Video/Wan2.1/blob/main/wan%2Fmodules%2Fvae.py

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants