ComfyUI Prompt Control
Nodes for convenient prompt editing, making many common operations prompt-controllable
Nodes (36)
AttentionMaskHookExperimental — a raw attention-masking hook, explicitly for testing
ConditioningCutoff — stopping one word's attribute from bleeding into another, BlenderNeko-style
CondLinearInterpolate — smoothly blending between two prompts instead of hard-cutting
EditableCLIPEncode — the old encoder node this pack has since replaced
Pulling one tagged slice out of a Prompt Control schedule
Jinja2 templating for your prompt text
Prompt Control's old LoRA node — use PC: Schedule LoRas instead
Attach Mask — feeding regional masks to your prompt with IMASK()
Attach Mask (multi) — four regional masks in one node instead of a chain
Anima Attention Couple Model Patch — regional prompting ported to Anima
Attaching a PCScheduleSettings bundle to your Prompt Control schedule
Attention Couple (batch negative) — keeping regional masks in sync across a batch
Show Prompt (PCExtractScheduledPrompt): the fastest way to debug Prompt Control syntax
Schedule LoRAs — turn a LoRALoader into something that can fade LoRAs in and out over time
Schedule LoRAs (Advanced) — access to the raw hooks, plus multi-pass filtering
Schedule Prompt — A1111-style prompt scheduling in ComfyUI, without the noodle soup
Schedule Prompt (Advanced) — prompt scheduling with multi-pass filtering
LoRA Hooks From Text (non-lazy): building a HOOKS object straight from LoRA syntax
Expand Macros — preview what your DEF macros actually turn into
The node that shoves wires into your text prompt
Reading back the exact prompt text at a point in your schedule
Save Expanded Workflow (for debug): seeing the graph Prompt Control builds behind your back
Wiring up to four masks for regional prompting on the schedule path
Step counts and SDXL micro-conditioning for a Prompt Control schedule
Configure Logging — turning up Prompt Control's debug output
Configure PCTextEncode — set your SDXL micro-conditioning and mask defaults once
PCSplitSampling — toggling how Prompt Control handles schedule breakpoints during sampling
Text Encode — the drop-in CLIPTextEncode upgrade that does most of Prompt Control's real work
Text Encode with Range — a slightly faster PCTextEncode when you already know the window
Making Prompt Control's scheduling work inside SamplerCustomAdvanced
PromptControlSimple — LoRA scheduling and positive/negative encoding in one node
Turning A1111-style bracket syntax into something ComfyUI nodes can chew on
ScheduleToCond — turning a parsed prompt schedule into conditioning, for graph builders
Applying LoRA scheduling from a PROMPT_SCHEDULE straight onto your model
Seeded random text substitution, Prompt Control's take on A1111 wildcards
Joining up to four strings before they hit your prompt or template
ComfyUI prompt control
Control LoRA and prompt scheduling, advanced text encoding, regional prompting, and much more, through your text prompt. Prompt Control generates dynamic graphs that are literally identical to handcrafted noodle soup, condensing complicated workflows with dozens of nodes into simple text prompts.
Prompt Control comes with PCTextEncode, which provides advanced text encoding with many additional features compared to ComfyUI's base CLIPTextEncode.
A Basic Text to Image template is included with the extension, and can be loaded from ComfyUI's template library.
[!NOTE] v3.0.0 is backwards compatible with existing workflows, but requires at least ComfyUI v0.8.0 The parser was rewritten using parsy. It is intended to have the same behaviour as the old parser, but is significantly faster. Please report any bugs or incompatibilities you find.
What can it do?
- A1111-style prompt scheduling and filtering without noodle soup.
- LoRA loading and scheduling using ComfyUI's built-in hook system.
- Masking, composition and area control (regional prompting) with an implementation of Attention Couple, also fully schedulable.
- Advanced prompt encoding
- Per-encoder prompts for models with multiple text encoders, such as SDXL and Flux.
- Prompt combinators like
BREAK, as well asCAT,AVG()andANDcorresponding to ComfyUI'sConditioningConcat,ConditioningAverageandConditioningCombinenodes. - Different weight interpretation types (ComfyUI, A1111, compel, etc.)
- Prompt masking with an implementation of cutoff.
- Organize complicated prompts with segments and prompt macros.
- Schedule your own encoder nodes, allowing prompt control of eg. video or audio models with non-text inputs.
All features are fully schedulable unless otherwise stated. See the scheduling syntax documentation to get started.
If you find prompt scheduling inconvenient for some reason, PCTextEncode can be used as a drop-in replacement for CLIPTextEncode to get everything else.
This workflow shows LoRA scheduling and prompt editing and compares it with the same prompt implemented with built-in ComfyUI nodes. You can also find it in the template library.
Compatibility
Prompt Control uses graph generation, and tries to delegate functionality to core ComfyUI wherever possible, implementing any hooks and patches in a way that is maximally compatible. This means that it should just work in most cases, even with models and nodes not explicitly supported.
If you encounter issues as a user or if you're a node developer and Prompt Control somehow breaks something, feel free to file a bug report.
Requirements
The v3 node schema uses features that require at least ComfyUI v0.8.0
If you run into problems, update ComfyUI first.
Core nodes
Note: The documentation refers to the nodes with their internal names for consistency. The display name may change, but ComfyUI's search will always find the nodes with the internal name. PCLazyTextEncode and PCLazyLoraLoader are the main ones you'll want to use, also known as PC: Schedule Prompt and PC: Schedule LoRas.
PCLazyTextEncode and PCLazyTextEncodeAdvanced
PCLazyTextEncode uses ComfyUI's lazy graph execution mechanism to generate a graph of PCTextEncode and SetConditioningTimestepRange nodes from a prompt with schedules. This has the advantage that if a part of the schedule doesn't change, ComfyUI's caching mechanism allows you to avoid re-encoding the non-changed part.
for example, if you first encode [cat:dog:0.1] and later change that to [cat:dog:0.5], no re-encoding takes place.
The advanced node enables filtering the prompt for multi-pass workflows.
PCLazyLoraLoader and PCLazyLoraLoaderAdvanced
This node reads LoRA expressions from the scheduled prompt and constructs a graph of LoraLoaders and CreateHookLoras as necessary to provide the necessary LoRA scheduling. Just use it in place of a LoRALoader and use the output normally.
The Advanced node gives you access to the generated hooks. If you have apply_hooks set to true, you do not need to apply the HOOKS output to a CLIP model separately; it's provided in case you want to use it elsewhere. The advanced node also enables filtering the prompt for multi-pass workflows.
PCTextEncode
Encodes a single prompt with advanced (non-scheduling) syntax enabled. This is what actually does most of the work under the hood.
Note: PCTextEncode does not ignore <lora:...:1> and will treat it as part of the prompt. To use a combined prompt for LoRAs and your input, use PCLazyTextEncode and PCLazyLoraLoader
PCAddMaskToCLIP
This node attaches masks to a CLIP model so that they can be referred to when using the IMASK custom mask function of PCTextEncode.
PCSetTextEncodeSettings
This node configures PCTextEncode default values for some functions by attaching the information to a CLIP model.
Known issues
-
ComfyUI's caching mechanism has an issue that makes it unnecessarily invalidate caches for certain inputs; you'll still get some benefit from the lazy nodes, but changing inputs that shouldn't affect downstream nodes (especially if using filtering) will still cause them to be recomputed because ComfyUI doesn't realize the inputs haven't changed.
-
Cutoff does not work with models that use non-CLIP text encoders, like Flux. This might be fixable, but it's uncertain if cutoff even makes sense for those models.