Loop ForgeColorize: Jin's page
Works, from MOSS-Image add-ons, tested locally
- Model
- MOSS-Image Base (moss_image_base_int8_convrot.safetensors)
- Output
- 864×1152
- Sampling
- 50 steps, CFG 3, er_sde / normal
- Seed
- 1
- Without LoRA
- 169.6 s, peak VRAM 10.1 GiB
- Colorize
- 99.1 s, peak VRAM 10.2 GiB
- Ran on
- RTX 3060, 12GB (local)
What was wired in
Input page
Jin's comic page (colorize)Comic page drawn from the Jin cast photo with the Qwen-Image 2.1 edit template (not MOSS), black and whiteDownload PNG2.1 MB
It kept the line work on all three pages. Some came out brighter than others, and on one the hoodie and the hair stayed quite pale.
"summary":"caption":"comic"
worst quality, greyscale, blurry, jpeg artifact
Notes
Colorize is its own LoRA (moss_colorize_3k_v4) on MOSS Base, loaded by the MOSS i2i Reference node together with the input page. The prompt is the helper's "comic" caption, and the negative is the one from the LoRA's card.
Times on this page are for these two runs.
sorryhyun/MOSS-I2I-LORAs on Hugging Face
Run it yourself
Download everything for this test (.zip, 2.1 MB). It holds the workflow, every input it loads and a README. Copy the inputs into ComfyUI/input, put the models below in place and drag the workflow onto ComfyUI.
| File | Put it in | Size |
|---|---|---|
| moss_image_base_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 |
| moss_colorize_3k_v4.safetensors | models/loras | 148.7 MB |
Custom nodes: ComfyUI-MOSS-Toolkit at commit 53ee3b3. Everything else is part of ComfyUI 0.43.1 (frontend 1.57.6, templates 0.11.100).