Qwen Image 2512 + PiD
Generate an image with Qwen Image 2512, then upscale it through PiD.
All workflows
Workflow preview
52 KB · JSON file
Need a hand? Load your workflow or troubleshoot your Runpod setup.
- Replace prompt placeholders and supply your own input images, video or audio before running.
- Save the PiD download as ComfyUI/models/diffusion_models/qwen_image_pid.pth.
Models to download
Check the required model files before running this workflow.
- gemma_2_2b_it_elm_bf16.safetensors (ComfyUI/models/text_encoders)Model source for gemma_2_2b_it_elm_bf16.safetensors (ComfyUI/models/text_encoders)
- qwen_2.5_vl_7b_fp8_scaled.safetensors (ComfyUI/models/text_encoders)Model source for qwen_2.5_vl_7b_fp8_scaled.safetensors (ComfyUI/models/text_encoders)
- qwen_image_2512_bf16.safetensors (ComfyUI/models/diffusion_models)Model source for qwen_image_2512_bf16.safetensors (ComfyUI/models/diffusion_models)
- qwen_image_pid.pth (PiD checkpoint) (ComfyUI/models/diffusion_models)Model source for qwen_image_pid.pth (PiD checkpoint) (ComfyUI/models/diffusion_models)
- qwen_image_vae.safetensors (ComfyUI/models/vae)Model source for qwen_image_vae.safetensors (ComfyUI/models/vae)
- Qwen-Image-Lightning-8steps-V2.0.safetensors (ComfyUI/models/loras)Model source for Qwen-Image-Lightning-8steps-V2.0.safetensors (ComfyUI/models/loras)