MOSS-Image Layout — posters, covers, title cards

Draw the boxes. MOSS puts the words and the people where you said.

Text boxes render their text, object boxes get a caption, and MOSS-Image's layout prompt turns them plus your scene description into the JSON layout it was trained on. For the lettering jobs Krea 2 and H3 cannot do reliably.

Model: MOSS-Image
VRAM: 16 GB+
Level: Intermediate

Download workflow — free

Drag the .json onto ComfyUI. Runs best on the Gmanski RunPod template.

You get

Gmanski MOSS (Layout) workflow with an example poster layout

You need

ComfyUI 0.42+
16 GB VRAM

Model packs · Text to image

mossmoss-turbo

On the template: gmanski-packs install moss moss-turbo

Pairs well with.

MiniMax H3new

H3 Image Edit — up to 8 references

Edit a picture with other pictures, in 8 steps.

Intermediate · 24–48 GB$19

MiniMax H3

Character Portrait — one photo

A new photo of a person from a single reference picture. No training.

Beginner · 48 GB+$24

MiniMax H3new

H3 Image — P-H3, 8 steps

H3's eye for light and skin as a still-image model.

Beginner · 24–48 GBFree