Add ComfyUI_RP_Cast to custom-node-list.json#2832
Open
AISeDam wants to merge 1 commit intoComfy-Org:mainfrom
Open
Add ComfyUI_RP_Cast to custom-node-list.json#2832AISeDam wants to merge 1 commit intoComfy-Org:mainfrom
AISeDam wants to merge 1 commit intoComfy-Org:mainfrom
Conversation
## Summary Adds `ComfyUI_RP_Cast` entry to `custom-node-list.json`. The node is already published on the Comfy Registry (publisher: AISeDam). The `id` field matches the registry node ID (`comfyui_rp_cast`) for proper cross-referencing. --- ## Overview A ComfyUI port and adaptation of [sd-webui-regional-prompter](https://github.com/hako-mikan/sd-webui-regional-prompter) by hako-mikan. Provides per-region prompt and LoRA control across multiple model architectures. Supports SDXL / SD1.5 with mask-based latent blending (denoised callback), and Z-Image / Qwen with unified prompt sampling. --- ## Nodes (8 total) | Node | Description | |------|-------------| | `RPPromptParser` | Parses multi-region prompts (ADDCOMM / ADDBASE / ADDCOL / ADDROW). Auto-calculates divide_ratio with canvas visualization. | | `RPRatioParser` | Converts divide_ratio + divide_mode + threshold into region structs. Canvas visualization of splits. | | `RPKSampler` | Regional KSampler for SDXL / SD1.5. Per-step region blending via denoised callback. | | `RPRegionalDetailer` | YOLO bbox-based regional inpainting for SDXL / SD1.5. Per-region LoRA isolation. | | `RPKSamplerZImage` | Regional KSampler for Z-Image. Merges region prompts with position labels into a single pass. | | `RPRegionalDetailerZImage` | YOLO + WD14 gender classification for Z-Image. Per-region LoRA isolation at inpaint stage. | | `RPKSamplerQwen` | Regional KSampler for Qwen. Builds scene-narrative prompt for natural multi-character composition. | | `RPRegionalDetailerQwen` | Delegates to RPRegionalDetailerZImage with Qwen VAE tensor normalization (5D → 4D). | --- ## Node details - **Repository**: https://github.com/AISeDam/ComfyUI_RP_Cast - **Registry**: https://registry.comfy.org/nodes/comfyui_rp_cast - **Author**: AISeDam - **License**: AGPL-3.0 - **Supported models**: SDXL, SD1.5, Z-Image, Qwen
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds
ComfyUI_RP_Castentry tocustom-node-list.json.The node is already published on the Comfy Registry (publisher: AISeDam).
The
idfield matches the registry node ID (comfyui_rp_cast) for proper cross-referencing.Overview
A ComfyUI port and adaptation of sd-webui-regional-prompter
by hako-mikan. Provides per-region prompt and LoRA control across multiple model architectures.
Supports SDXL / SD1.5 with mask-based latent blending (denoised callback),
and Z-Image / Qwen with unified prompt sampling.
Nodes (8 total)
RPPromptParserRPRatioParserRPKSamplerRPRegionalDetailerRPKSamplerZImageRPRegionalDetailerZImageRPKSamplerQwenRPRegionalDetailerQwenNode details