analyze_workflow
ChatGPTList the custom nodes and model files a ComfyUI workflow needs, and how each would be found. Free. Each model comes with its size and a resolution: already on RunComfy, a known download, or one the user must supply (for example a gated Hugging Face file they have no access to). Use it before start_workflow_setup so the user knows what the setup will install.
cancel_model_request
ChatGPTCancel a queued Model API request. Backs `POST /v1/requests/{request_id}/cancel. Returns cancelled if accepted, not_cancellable` if the request is already in progress or finished.
cancel_request
ChatGPTCancel a queued or running request. Backs `POST /prod/v1/deployments/{deployment_id}/requests/{request_id}/cancel. Returns cancelled if accepted, not_cancellable` if already done.
cancel_training_job
ChatGPTCancel a queued or running training job. Backs `POST /prod/v1/trainers/ai-toolkit/jobs/{job_id}/cancel. Progress stops, but get_training_job_result` still returns any checkpoints produced so far.
create_dataset
ChatGPTCreate an empty training dataset. Backs POST /prod/v1/trainers/datasets. A new dataset starts in DRAFT; only a READY dataset can be mounted by training. name is unique within the account and identifies /app/ai-toolkit/datasets/{dataset_name} in an AI Toolkit config. An omitted name is generated by RunComfy.
create_deployment
ChatGPTCreate a Serverless API (ComfyUI) deployment. Backs POST /prod/v2/deployments. LoRA deployment creation is outside this tool's scope. name is a human-readable name; workflow_id is the ComfyUI workflow UUID; workflow_version is its version label. hardware accepts TURING_16, AMPERE_24, AMPERE_48, ADA_48_PLUS, AMPERE_80, ADA_80_PLUS, or HOPPER_141. min_instances is 0..30 and a nonzero warm-instance floor is billable. max_instances is 1..60; queue_size and keep_warm_duration_in_seconds are nonnegative.
delete_dataset
ChatGPTPermanently delete a training dataset. Backs `DELETE /prod/v1/trainers/datasets/{dataset_id}`. This cannot be undone.
delete_deployment
ChatGPTPermanently delete a Serverless API deployment. Backs DELETE /prod/v2/deployments/{deployment_id}. Deletion cannot be undone.
edit_flux_kontext_pro_image
ChatGPTEdit one image from a text instruction with FLUX Kontext Pro. Uses RunComfy balance. The model is fixed and no deployment is required. Read this model's current price with get_model(model_id="blackforestlabs/flux-1-kontext/pro/edit") and obtain approval before the billable submission. File inputs must be public HTTPS URLs without credentials. Prefer wait_for_completion=false: keep the returned request ID, poll get_model_request_status, and fetch outputs with get_model_request_result. Never call this tool to check progress or blindly retry after a timeout; verify request history first.
edit_gpt_image_2_5_image
ChatGPTEdit or combine reference images from a text instruction with GPT Image 2.5 Sunburst. Uses RunComfy balance. The model is fixed and no deployment is required. Read this model's current price with get_model(model_id="openai/gpt-image-2.5/sunburst/edit") and obtain approval before the billable submission. File inputs must be public HTTPS URLs without credentials. Prefer wait_for_completion=false: keep the returned request ID, poll get_model_request_status, and fetch outputs with get_model_request_result. Never call this tool to check progress or blindly retry after a timeout; verify request history first.
edit_nano_banana_2_1_image
ChatGPTEdit or combine reference images from a text instruction with Nano Banana 2.1. Uses RunComfy balance. The model is fixed and no deployment is required. Read this model's current price with get_model(model_id="google/nano-banana-2.1/edit") and obtain approval before the billable submission. File inputs must be public HTTPS URLs without credentials. Prefer wait_for_completion=false: keep the returned request ID, poll get_model_request_status, and fetch outputs with get_model_request_result. Never call this tool to check progress or blindly retry after a timeout; verify request history first.
edit_nano_banana_2_image
ChatGPTEdit or combine reference images from a text instruction with Nano Banana 2. Uses RunComfy balance. The model is fixed and no deployment is required. Read this model's current price with get_model(model_id="google/nano-banana-2/edit") and obtain approval before the billable submission. File inputs must be public HTTPS URLs without credentials. Prefer wait_for_completion=false: keep the returned request ID, poll get_model_request_status, and fetch outputs with get_model_request_result. Never call this tool to check progress or blindly retry after a timeout; verify request history first.
edit_nano_banana_pro_image
ChatGPTEdit or combine reference images from a text instruction with Nano Banana Pro. Uses RunComfy balance. The model is fixed and no deployment is required. Read this model's current price with get_model(model_id="google/nano-banana/pro/edit") and obtain approval before the billable submission. File inputs must be public HTTPS URLs without credentials. Prefer wait_for_completion=false: keep the returned request ID, poll get_model_request_status, and fetch outputs with get_model_request_result. Never call this tool to check progress or blindly retry after a timeout; verify request history first.
edit_qwen_image_3_pro_image
ChatGPTEdit images from a text instruction with Qwen Image 3.0 Pro. Uses RunComfy balance. The model is fixed and no deployment is required. Read this model's current price with get_model(model_id="qwen/qwen-image-3.0/pro/edit") and obtain approval before the billable submission. File inputs must be public HTTPS URLs without credentials. Prefer wait_for_completion=false: keep the returned request ID, poll get_model_request_status, and fetch outputs with get_model_request_result. Never call this tool to check progress or blindly retry after a timeout; verify request history first.
edit_seedream_5_pro_image
ChatGPTEdit or combine reference images from a text instruction with Seedream 5.0 Pro. Uses RunComfy balance. The model is fixed and no deployment is required. Read this model's current price with get_model(model_id="bytedance/seedream-5.0-pro/image-to-image") and obtain approval before the billable submission. File inputs must be public HTTPS URLs without credentials. Prefer wait_for_completion=false: keep the returned request ID, poll get_model_request_status, and fetch outputs with get_model_request_result. Never call this tool to check progress or blindly retry after a timeout; verify request history first.
edit_training_job
ChatGPTReplace the config of a non-running training job. Backs POST /prod/v1/trainers/ai-toolkit/jobs/{job_id}/edit. The job must be STOPPED, CANCELED, or FAILED, and config.name must match its original name. Editing changes configuration without queuing compute. GPU type and count are selected when the job is resumed.
generate_3d
ChatGPTRun a hosted RunComfy model by catalog model_id using account balance. inputs is the request body defined by that model's input JSON Schema. File inputs must be publicly accessible HTTPS URLs. No deployment is required. Each new generation is billable and requires user authorization; current pricing is available in the model metadata. wait_for_completion=false returns a request ID for later status and result retrieval. A timeout or unknown submission outcome can still represent a billable request; another submission can create duplicate work, including with the same key. An echoed idempotency key is not confirmation of backend duplicate protection.
generate_ace_step_music
ChatGPTGenerate a song or instrumental track from style tags and optional lyrics with ACE-Step 1.5. Uses RunComfy balance. The model is fixed and no deployment is required. Read this model's current price with get_model(model_id="acestep-ai/ace-step-1.5/text-to-audio") and obtain approval before the billable submission. File inputs must be public HTTPS URLs without credentials. Prefer wait_for_completion=false: keep the returned request ID, poll get_model_request_status, and fetch outputs with get_model_request_result. Never call this tool to check progress or blindly retry after a timeout; verify request history first.
generate_audio
ChatGPTRun a hosted RunComfy model by catalog model_id using account balance. inputs is the request body defined by that model's input JSON Schema. File inputs must be publicly accessible HTTPS URLs. No deployment is required. Each new generation is billable and requires user authorization; current pricing is available in the model metadata. wait_for_completion=false returns a request ID for later status and result retrieval. A timeout or unknown submission outcome can still represent a billable request; another submission can create duplicate work, including with the same key. An echoed idempotency key is not confirmation of backend duplicate protection.
generate_flux_schnell_image
ChatGPTGenerate one image with FLUX.1 Schnell text-to-image using RunComfy balance. This fixed model requires no deployment. seed=-1 requests a random seed. Each new generation is billable and requires user authorization; current pricing is available in the model metadata. wait_for_completion=false returns a request ID for later status and result retrieval. A timeout or unknown submission outcome can still represent a billable request; another submission can create duplicate work. An echoed idempotency key is not confirmation of backend duplicate protection.
generate_gpt_image_2_5_image
ChatGPTGenerate one or more images from a text prompt with GPT Image 2.5 Sunburst, which keeps words on labels and posters accurate. Uses RunComfy balance. The model is fixed and no deployment is required. Read this model's current price with get_model(model_id="openai/gpt-image-2.5/sunburst/text-to-image") and obtain approval before the billable submission. File inputs must be public HTTPS URLs without credentials. Prefer wait_for_completion=false: keep the returned request ID, poll get_model_request_status, and fetch outputs with get_model_request_result. Never call this tool to check progress or blindly retry after a timeout; verify request history first.
generate_heygen_voice_speech
ChatGPTTurn text into a spoken voiceover with HeyGen Voice. Uses RunComfy balance. The model is fixed and no deployment is required. Read this model's current price with get_model(model_id="heygen/heygen-voice/text-to-audio") and obtain approval before the billable submission. File inputs must be public HTTPS URLs without credentials. Prefer wait_for_completion=false: keep the returned request ID, poll get_model_request_status, and fetch outputs with get_model_request_result. Never call this tool to check progress or blindly retry after a timeout; verify request history first.
generate_image
ChatGPTRun a hosted RunComfy model by catalog model_id using account balance. inputs is the request body defined by that model's input JSON Schema. File inputs must be publicly accessible HTTPS URLs. No deployment is required. Each new generation is billable and requires user authorization; current pricing is available in the model metadata. wait_for_completion=false returns a request ID for later status and result retrieval. A timeout or unknown submission outcome can still represent a billable request; another submission can create duplicate work, including with the same key. An echoed idempotency key is not confirmation of backend duplicate protection.
generate_kling_3_pro_video
ChatGPTTurn a starting image into a video with Kling 3.0 Pro. Uses RunComfy balance. The model is fixed and no deployment is required. Read this model's current price with get_model(model_id="kling/kling-3.0/pro/image-to-video") and obtain approval before the billable submission. File inputs must be public HTTPS URLs without credentials. Prefer wait_for_completion=false: keep the returned request ID, poll get_model_request_status, and fetch outputs with get_model_request_result. Never call this tool to check progress or blindly retry after a timeout; verify request history first.
generate_qwen_image_3_pro_image
ChatGPTGenerate an image from a text prompt with Qwen Image 3.0 Pro. Uses RunComfy balance. The model is fixed and no deployment is required. Read this model's current price with get_model(model_id="qwen/qwen-image-3.0/pro/text-to-image") and obtain approval before the billable submission. File inputs must be public HTTPS URLs without credentials. Prefer wait_for_completion=false: keep the returned request ID, poll get_model_request_status, and fetch outputs with get_model_request_result. Never call this tool to check progress or blindly retry after a timeout; verify request history first.
generate_seedance_2_5_video
ChatGPTGenerate a 720p video from a text prompt and optional reference images, video or audio with Seedance 2.5. Uses RunComfy balance. The model is fixed and no deployment is required. Read this model's current price with get_model(model_id="bytedance/seedance-2.5/reference-to-video/720p") and obtain approval before the billable submission. File inputs must be public HTTPS URLs without credentials. Prefer wait_for_completion=false: keep the returned request ID, poll get_model_request_status, and fetch outputs with get_model_request_result. Never call this tool to check progress or blindly retry after a timeout; verify request history first.
generate_seedance_pro_fast_video
ChatGPTGenerate one video from an image with Seedance 1.0 Pro Fast using RunComfy balance. This fixed model requires no deployment. duration is in seconds; duration and resolution affect cost. Each new generation is billable and requires user authorization; current pricing is available in the model metadata. image_url must support an unauthenticated HTTPS GET and contain no credentials. Backend image-content validation is separate from URL syntax validation. wait_for_completion=false returns a request ID for later status and results. A timeout or unknown submission outcome can still represent a billable request; another submission can create duplicate work. An echoed idempotency key is not confirmation of backend duplicate protection.
generate_seedream_5_pro_image
ChatGPTGenerate an image from a text prompt with Seedream 5.0 Pro. Uses RunComfy balance. The model is fixed and no deployment is required. Read this model's current price with get_model(model_id="bytedance/seedream-5.0-pro/text-to-image") and obtain approval before the billable submission. File inputs must be public HTTPS URLs without credentials. Prefer wait_for_completion=false: keep the returned request ID, poll get_model_request_status, and fetch outputs with get_model_request_result. Never call this tool to check progress or blindly retry after a timeout; verify request history first.
generate_veo_3_1_fast_video
ChatGPTGenerate a video from a text prompt with Veo 3.1 Fast. Uses RunComfy balance. The model is fixed and no deployment is required. Read this model's current price with get_model(model_id="google-deepmind/veo-3-1/fast/text-to-video") and obtain approval before the billable submission. File inputs must be public HTTPS URLs without credentials. Prefer wait_for_completion=false: keep the returned request ID, poll get_model_request_status, and fetch outputs with get_model_request_result. Never call this tool to check progress or blindly retry after a timeout; verify request history first.
generate_video
ChatGPTRun a hosted RunComfy model by catalog model_id using account balance. inputs is the request body defined by that model's input JSON Schema. File inputs must be publicly accessible HTTPS URLs. No deployment is required. Each new generation is billable and requires user authorization; current pricing is available in the model metadata. wait_for_completion=false returns a request ID for later status and result retrieval. A timeout or unknown submission outcome can still represent a billable request; another submission can create duplicate work, including with the same key. An echoed idempotency key is not confirmation of backend duplicate protection.
generate_wan_3_video
ChatGPTTurn a starting image into a video with Wan 3.0. Uses RunComfy balance. The model is fixed and no deployment is required. Read this model's current price with get_model(model_id="wan-ai/wan-3.0/image-to-video") and obtain approval before the billable submission. File inputs must be public HTTPS URLs without credentials. Prefer wait_for_completion=false: keep the returned request ID, poll get_model_request_status, and fetch outputs with get_model_request_result. Never call this tool to check progress or blindly retry after a timeout; verify request history first.
get_asset_download_url
ChatGPTGet a link that downloads one My Assets file, valid for an hour.
get_asset_import_status
ChatGPTCheck a My Assets import started by import_asset_from_url.
get_balance
ChatGPTGet the account's remaining RunComfy balance. Backs `GET /prod/v2/balance. One wallet funds every product, so this is the figure Serverless deployments, hosted generation requests, and training jobs all draw down — and the one that gets checked before work is allowed to start. Returns balance_usd for reading and balance_microdollars` (millionths of a dollar) for exact arithmetic.
get_dataset_status
ChatGPTGet a dataset's status and its successfully uploaded files. Backs `GET /prod/v1/trainers/datasets/{dataset_id}/status. Lifecycle: DRAFT → UPLOADING → READY (or FAILED, which sets error). Only READY datasets can be mounted by a training job. Files still uploading or failed do not appear in files`.
get_dataset_upload_urls
ChatGPTCreate signed upload URLs for dataset files, including local or large files. Backs POST /prod/v1/trainers/datasets/{dataset_id}/get-upload-endpoint. filename_to_byte_size maps each filename to its exact positive byte size. Each response contains an upload_url, method, and headers for the file's PUT. An incorrect size is rejected by storage. The URLs expire; a new call issues fresh URLs. Dataset readiness is reconciled separately after file uploads.
get_deployment
ChatGPTGet one Serverless API deployment by ID. Backs GET /prod/v2/deployments/{deployment_id}. include_payload=true includes the deployed workflow_api_json and default overrides. Their node IDs and input names identify the fields accepted in inference overrides. include_readme=true includes the deployment's README markdown.
get_library_workflow
ChatGPTWhat running a workflow from the public library takes, with no copy in My Workflows. Free. workflow_version_id goes to request_machine_start, and workflow_id with workflow_version to create_deployment. workflow_api_json is the prompt for run_on_machine; its sample files are on the machine, so it runs unchanged. inputs lists the fields to change for other files or text. Finished files land in My Assets under output/, and get_asset_download_url gives a link to them.
get_machine
ChatGPTGet one ComfyUI machine: status, type, ComfyUI link and when it stops.
get_model
ChatGPTGet a hosted model's metadata, pricing, and input JSON Schema. Backs GET /v1/models/{model_id}. model_id includes its publisher and slash-separated path. input_schema defines the model request body's property types, defaults, enums, and ranges. Properties whose format is image_uri, video_uri, or audio_uri accept public HTTPS URLs. The response also includes description, categories, base_price_usd per price_unit, and model_url.
get_model_request_result
ChatGPTFetch a completed hosted Model API generation request's outputs. Backs GET /v1/requests/{request_id}/result. The model's output schema defines the output shape; hosted asset URLs are also flattened into output_urls. This request namespace is separate from Serverless deployment inference.
get_model_request_status
ChatGPTGet the status of a hosted Model API generation request. Backs GET /v1/requests/{request_id}/status. Lifecycle: in_queue -> in_progress -> completed / cancelled. An in_queue payload also includes queue_position. This request namespace is separate from Serverless deployment inference.
get_request_result
ChatGPTFetch a completed Serverless deployment inference request's outputs. Backs GET /prod/v1/deployments/{deployment_id}/requests/{request_id}/result. Output URLs are hosted for 7 days. This request namespace belongs to deployment inference, separate from Model API requests.
get_request_status
ChatGPTGet the status of a Serverless deployment inference request. Backs GET /prod/v1/deployments/{deployment_id}/requests/{request_id}/status. Lifecycle: in_queue -> in_progress -> completed / cancelled. This request namespace belongs to deployment inference, separate from Model API requests.
get_training_job_result
ChatGPTFetch a training job's artifacts as hosted URLs without changing the job. Backs GET /prod/v1/trainers/ai-toolkit/jobs/{job_id}/result. Artifacts include .safetensors checkpoints, resolved config, and sample outputs. Results are available during RUNNING and after FAILED or CANCELED; the artifact list can grow over time. Each call fetches once, without an internal publication wait. Config publication is independent of training completion. Only explicit config_publication_status=published confirms backend publication. pending means publication metadata has not arrived; unconfirmed includes older backends without the field. STOPPED and a URL's hostname do not establish publication. Raw result.artifacts.config remains for compatibility, but unpublished URLs appear in provisional_config_urls rather than artifact_urls. Checkpoint and sample URLs are unchanged. Publication alone does not verify a download or its contents. Config publication is separate from changing or rerunning training. The two fixed hosted generation operations do not accept arbitrary LoRA checkpoints.
get_training_job_status
ChatGPTPoll a training job's status and step progress. Backs `GET /prod/v1/trainers/ai-toolkit/jobs/{job_id}/status. Lifecycle: IN_QUEUE → RUNNING → STOPPED (finished or preempted), FAILED (error explains why), or CANCELED`.
get_workflow_setup_status
ChatGPTCheck one Auto Setup submission: queued, running, ready or rejected. Setup usually takes 30-60 minutes, and 2-3 hours when it needs a different machine type. While it is queued or running the result says when to check again (check_again_in_minutes); do not check more often, and let the user carry on meanwhile: RunComfy emails them when it finishes. When it is ready it returns the workflow_id and workflow_version that create_deployment takes, and the workflow_version_id that starting a machine takes; when it is rejected, the reason.
list_datasets
ChatGPTList training datasets in the caller's account. Backs GET /prod/v1/trainers/datasets. Each dataset's id identifies upload, status, and deletion requests; its name identifies the AI Toolkit folder_path. The listing excludes per-file detail. include_raw=true returns unabridged dataset payloads instead of compact summaries and increases response size.
list_deployments
ChatGPTList Serverless API deployments in the caller's account. Backs `GET /prod/v2/deployments`. Args: ids: Optional list of deployment IDs to filter to. include_payload: Include workflow_api_json, overrides, and object_info_url for each deployment. Larger response. include_readme: Include the deployment's README markdown.
list_library_models
ChatGPTBrowse RunComfy's built-in ComfyUI model library, which every machine has without downloading. Free, no machine needed.
list_library_workflows
ChatGPTSearch RunComfy's public ComfyUI workflows, the ones on runcomfy.com/comfyui-workflows. Free. Call get_library_workflow for what running one takes.
list_machines
ChatGPTList the user's ComfyUI machines that are starting, running or stopping, with when each stops.
list_model_categories
ChatGPTList the hosted model catalog's capability categories. Backs GET /v1/models/categories. Returned category values include text-to-image and image-to-video and are accepted by the model catalog's category filter.
list_models
ChatGPTBrowse the hosted RunComfy model catalog. Backs GET /v1/models. Entries include model_id, display_name, description, base_price_usd per price_unit, model_url, inputs, and required_inputs. search matches the ID, display name, or description without case sensitivity. category filters capabilities such as text-to-image or image-to-video; kind filters model, workflow, or inference execution. include_schema=true adds each full input_schema and increases response size. limit is 1..500; offset is the number of rows skipped, and total is the unpaged count.
list_my_assets
ChatGPTList the user's own files in My Assets: ComfyUI inputs, outputs and models every machine of theirs can use.
list_my_generations
ChatGPTList the account's finished model generations, newest first, from the website and the API alike. Each entry has the request_id, model_id, the inputs it ran with and its output_urls. Those links work as image, video or audio inputs to a new generation, so a past result can be the reference for a new one. Files are kept for a limited time: an entry past that time is not listed. A generation still running has no entry yet: use get_model_request_status.
list_my_workflows
ChatGPTList the saved versions in My Workflows. workflow_version is the label create_deployment takes, and workflow_version_id is what starting a machine takes.
list_workflow_setups
ChatGPTList the account's ten most recent Auto Setup submissions and the price of the next one.
resume_training_job
ChatGPTResume a stopped training job from its latest checkpoint. Backs POST /prod/v1/trainers/ai-toolkit/jobs/{job_id}/resume. Reuses the same job_id and restarts from the highest-step checkpoint, or step 0 if none exists. Resumed compute consumes RunComfy balance. A failed job's status includes the error; resuming alone does not change the job's configuration.
start_workflow_setup
ChatGPTHave RunComfy set up a ComfyUI workflow: a machine installs its custom nodes and models and saves it as a new version in My Workflows. This costs money. Call it first without confirmed_price_usd. That only returns the quote: the price ($0.20 for the account's first setup, $2.99 after that), the balance, and whether a pay-as-you-go account has room for another workflow. Tell the user the price, and that setup usually takes 30-60 minutes, or 2-3 hours when the workflow needs a different machine type. Only after they agree, call again with confirmed_price_usd set to the quoted price. Call it once per confirmation; if a call ends without an answer, check list_workflow_setups before trying again. After submitting, do not poll: check get_workflow_setup_status when it says to. RunComfy also emails the user when the setup finishes. When it is ready, create_deployment with its workflow_id and workflow_version publishes it as a Serverless API.
submit_request
ChatGPTSubmit an async inference request to a Serverless deployment. Backs POST /prod/v1/deployments/{deployment_id}/inference. Execution consumes RunComfy balance. overrides is a partial graph keyed by node ID, for example {"6": {"inputs": {"text": "a cat"}}}; node IDs and input names belong to the deployed workflow. workflow_api_json runs a different workflow without changing the deployment and is mutually exclusive with overrides. File input values accept public HTTPS URLs or Base64 data URIs. webhook_url receives status updates; webhook_intermediate_status includes nonterminal changes. wait_for_completion=true polls for results up to timeout_seconds; otherwise the response contains the submission and request ID.
submit_training_job
ChatGPTSubmit a billable AI Toolkit training job, typically LoRA training. Backs POST /prod/v1/trainers/ai-toolkit/jobs. The job mounts a READY dataset and runs config_file, a complete AI Toolkit YAML string. training_folder must be /app/ai-toolkit/output; dataset folder_path must be /app/ai-toolkit/datasets/{dataset_name}, using the dataset's name rather than ID. gpu_type is ADA_80_PLUS (H100) or HOPPER_141 (H200). gpu_count is 1 by default or 8 for multi-GPU on ADA_80_PLUS only. gpu_id is an optional selector such as "#1". Training can take hours; submission returns when the job is queued and consumes RunComfy balance as compute runs.
update_deployment
ChatGPTPartially update a Serverless API deployment. Backs PATCH /prod/v2/deployments/{deployment_id}. Only supplied fields change. is_enabled=false pauses the deployment; true re-enables it. Warm instances can consume account balance.
upload_dataset_file_from_url
ChatGPTAdd one dataset file fetched from a public HTTPS URL. Downloads source_url and stores it in the dataset through a signed upload URL, as get_dataset_upload_urls does. The image, video, or caption .txt file must be under 150 MB. filename defaults to the URL's basename. LoRA image/video captions use matching base names, such as img_0001.jpg and img_0001.txt. Re-uploading the same filename overwrites its previous contents. Local files and larger files require a direct signed-URL upload.
upload_dataset_text_file
ChatGPTAdd a text file — normally a caption — to a dataset. Backs `POST /prod/v1/trainers/datasets/{dataset_id}/upload with inline text, so captions can be written without hosting a file. Args: dataset_id: Target dataset. filename: Must share the base name of the media it captions: img_0001.jpg → img_0001.txt`. text: Caption body.
whoami
ChatGPTShow which RunComfy account this connection is signed in to: its email, username and account id. Use it when the user asks which account they are connected as, or when a balance, file, workflow or job they expect is missing: an AI app can hold connections to more than one RunComfy account.