Depth control: a ballerina
==========================

From the Loop Forge project "MOSS-Image add-ons, tested locally": https://loopforge.cc/projects/moss-image/depth-ballet/

What is in here
- 2 ComfyUI workflow file(s), the one that made each image on the test page
- inputs/: every image the workflows load, under the name they load it by

To run it
1. Copy the files in inputs/ into ComfyUI/input.
2. Put the models below in the ComfyUI/models folders shown.
3. Drag a workflow onto ComfyUI and press Run.

Models
- moss_image_sft_int8_convrot.safetensors -> models/diffusion_models (https://huggingface.co/Comfy-Org/MOSS-Image/resolve/main/diffusion_models/moss_image_sft_int8_convrot.safetensors)
- qwen3.5_9b_w4a8_gptq.safetensors -> models/text_encoders (https://huggingface.co/Comfy-Org/MOSS-Image/resolve/main/text_encoders/qwen3.5_9b_w4a8_gptq.safetensors)
- flux2-vae_small.safetensors -> models/vae (https://huggingface.co/Comfy-Org/MOSS-Image/resolve/main/vae/flux2-vae_small.safetensors)
- moge_3_vitg_fp16.safetensors -> models/geometry_estimation (https://huggingface.co/Comfy-Org/MoGe/resolve/main/geometry_estimation/moge_3_vitg_fp16.safetensors)
- moss_image_color_depth_control.safetensors -> models/loras (https://huggingface.co/Comfy-Org/MOSS-Image/resolve/main/loras/moss_image_color_depth_control.safetensors)

No custom nodes: every node is part of ComfyUI.

Made and tested with ComfyUI 0.43.1 (frontend 1.57.6, templates 0.11.100).
