Loop ForgeA woman on the dunes
From MOSS-Image add-ons, tested locally
- Model
- MOSS-Image SFT (moss_image_sft_int8_convrot.safetensors)
- Output
- 1024×1024
- Sampling
- 25 steps, CFG 2.5, er_sde / simple
- Seed
- 101
- SFT template
- 41.8 s, peak VRAM 10.3 GiB
- Ran on
- RTX 3060, 12GB (local)
Wide landscape photograph: a woman with long straight blonde hair in a sage green tank top and white jeans walks along the crest of a pale sand dune at dusk, small in the frame. Above her a huge, smooth, cloudless sky fades from peach at the horizon to deep blue at the top. Calm, minimal, soft light.
nsfw, worst quality, bad anatomy, watermark, jpeg artifact
Notes
ComfyUI's MOSS-Image text to image template as it loads from the template browser, with its own settings. Its prompt enhancer (the text encoder rewrites your prompt before it runs) is switched off.
Comfy-Org workflow templates (the MOSS-Image templates ship with ComfyUI)
Run it yourself
This test loads no input files. Put the models below in place and drag the workflow onto ComfyUI.
| File | Put it in | Size |
|---|---|---|
| moss_image_sft_int8_convrot.safetensors | models/diffusion_models | 5.4 GB |
| qwen3.5_9b_w4a8_gptq.safetensors | models/text_encoders | 7.3 GB |
| flux2-vae_small.safetensors | models/vae | 249.5 MB |
No custom nodes. Every node is part of ComfyUI 0.43.1 (frontend 1.57.6, templates 0.11.100).