YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

comfy-zimage-turbo

Consolidated model bundle for serverless Z-Image Turbo text-to-image generation on RunPod.

What this repo is

This is a RunPod-Cached-Models-shaped consolidation of three upstream files into one HF repo, so a serverless endpoint can pull everything in a single warmup pass.

Files

Path Size Upstream
diffusion_models/z_image_turbo_bf16.safetensors 12.3 GB Comfy-Org/z_image_turbo
text_encoders/qwen_3_4b.safetensors 8.0 GB Comfy-Org/z_image_turbo
vae/ae.safetensors 0.3 GB Comfy-Org/z_image_turbo (FLUX-style VAE)

Total: ~20.7 GB.

Runtime layout

comfy_paths.json declares the mapping from this repo's flat dirs to ComfyUI's models/<subdir>/ tree. The container's boot script (symlink-models.sh) reads this manifest and creates symlinks — no copies, no path-munging logic.

Workflow

workflow.json is the canonical ComfyUI workflow this endpoint serves. Sourced from ComfyUI's bundled templates package (comfyui_workflow_templates_media_image/image_z_image_turbo.json).

License

Z-Image Turbo weights are governed by the upstream model license (Comfy-Org / Tongyi-MAI). Use of this consolidated repo is subject to the same terms.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support