ComfyUI Node
H3 Regional Prompt (mask)
Bias H3's attention so a fragment of the prompt describes the MASKED region specifically: the zone's pixels listen harder to those words, the rest of the frame stops listening to them. Pairs with the Soft Denoise Zone (same mask) for region swaps; also places subjects spatially in plain generation. EXPERIMENTAL — first regional prompting on H3.
H3 Regional Prompt (mask)
- model
- clip
- conditioning
- mask
- MODEL
◄region_text►
◄strength1.5►
◄containment0.50►
◄mask_feather0.10►
Categorymodel/conditioning/minimax
Inputs (8)
| Name | Type | Default | Description |
|---|---|---|---|
| model | MODEL | — | |
| clip | CLIP | The H3 text encoder — used to measure the fragment's token span. | |
| conditioning | CONDITIONING | The Guide node's positive conditioning (read-only — it carries the final prompt text). The SAME conditioning still goes to the sampler as usual. | |
| region_text | STRING | The part of the prompt that describes what belongs in the masked region. Must appear VERBATIM in the prompt (copy-paste it). Example: prompt '...a woman in a red coat walks through the market...' -> region_text 'a woman in a red coat'. | |
| strength | FLOAT | 1.50–5 | Additive attention-logit bias pulling the region's pixels toward the fragment's tokens. ~1.0-2.5 is the expected usable range; too high degrades composition. 0 disarms the node. |
| containment | FLOAT | 0.500–1 | Fraction of strength applied as a NEGATIVE bias from pixels OUTSIDE the mask to the fragment's tokens — keeps the description from leaking into the rest of the frame. 0 = attract only. |
| mask_feather | FLOAT | 0.100–0.5 | Softens the mask outward (fraction of the short side), interior kept at full strength — same dial as the Soft Denoise Zone. |
| mask | MASK | WHERE the fragment belongs. Single mask = whole clip; a per-frame batch (SAM2 video segmentation) follows the subject through time. Same input as the Soft Denoise Zone — share the wire. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| MODEL | MODEL | Wire to the sampler in place of the plain model (stack after the Soft Denoise Zone if both are used). |