Resource directory
Find what you need for your workflow.
Guides: techniques, setup, and troubleshootingSearch Sweet Tea Pipes, external workflows, models, node packs, and guides in one evidence-linked catalog.
Start with a workflow instead ↗Search results
All resources
20 shown of 41,740
ACE-Step music generator
Describe genre, instruments, mood, and tempo in the music prompt. Supply lyrics and section markers for vocals, or retain [instrumental] and arrangement cues for instrumental music. Lyrics strength controls lyric conditioning and remains available in either mode. The workflow uses zeroed negative conditioning, so there is no separate negative prompt. The source note advises manually transliterating multilingual lyrics and adding language markers such as [zh], [ja], or [ko].
HappyHorse reference to video
Generate one video from two reference images and a prompt describing the subjects, action and camera movement. Upload both reference images, then replace the supplied car-and-driver prompt with a description matching your uploads. For a first run, use an object or scene as Reference image 1 and a person as Reference image 2, following the example's arrangement. Start with 5 seconds, 720P and 16:9, and describe an action that fits the chosen duration. The images feed reference slots 1 and 2; they are not designated start and end frames. The example prompt uses @image1 and @image2, while the source's prompt guidance recommends identifiers such as character1 and character2 for reference characters. Clearly describe each subject and its role in words when adapting the prompt. Choose a duration from 3–15 seconds, resolution of 720P or 1080P, and aspect ratio of 16:9, 9:16, 1:1, 4:3 or 3:4. Select HappyHorse 1.0 or 1.1; the default is 1.0. Seed -1 randomizes each run, while a fixed seed requests the same generation seed. Enable Watermark to request an AI-generated watermark. Generation sends the references and prompt to the provider API, requires configured provider access and incurs provider charges. The Pipe returns one video for preview with automatic format and codec selection. The example's requests for consistent details and smooth motion are creative instructions, not guarantees.
SwitchX Video Edit
Create one edited video clip using SwitchX, guided by a prompt and optional reference image. For a first run, upload a source video, replace the example prompt with your desired look, and keep auto editing mode and 720p resolution. Start time defaults to 0 seconds and duration to 5 seconds. Shorten the duration if needed to stay within the 240-frame limit at your source video's frame rate. Enter auto to isolate the main subject automatically and edit the surrounding scene while preserving unmasked source pixels. Enter fill to regenerate the whole frame while preserving geometry; the subject's original pixels are not preserved, so this mode can change the subject's look or costume. Select and custom require first-frame keyframe or per-frame matte inputs unavailable in this Pipe; use auto or fill. The reference-image stage is disabled by default. Enable it and upload an image to guide the background, lighting or costume. Disable it for prompt-only editing. Provide a nonempty prompt or an enabled reference image; at least one is required. Prompts are limited to 2,000 characters. Start time and duration are in seconds. Duration 0 selects the remaining video, still subject to SwitchX's limits of 240 frames and approximately 2.77 megapixels per frame. Five seconds may exceed the frame limit for some videos. Enable strict duration to raise an error when the requested duration cannot be extracted; otherwise a shorter available clip is allowed. Enter 720p or 1080p for the maximum output resolution. Seed -1 randomizes on each run. Seed controls provider re-running rather than reproducibility; results remain nondeterministic with a fixed seed. The advanced video-output section provides file type and codec choices; keep both automatic for the first run. This Pipe returns the edited video, not SwitchX's separate alpha video. SwitchX uses an external Beeble provider call with provider billing.
Anima illustration with upscale and finishing
Generate an Anima illustration from prompts and return an enlarged, finished image batch. For a first run, describe your subject, scene, composition, and style in Positive prompt. The two additional prompt fields append optional details. Leave Negative prompt empty unless you want to specify unwanted content or visual traits. No uploaded image is needed. Choose the initial Size preset, Image count, and Enlargement factor. The default 832 × 1216 portrait preset and 2× enlargement produce 1664 × 2432 images. The factor multiplies both width and height. Leave the sampling defaults unchanged for a first run. Advanced generation controls provide the initial seed, steps, prompt guidance, sampler, scheduler, and denoise. Keep Generation denoise at 1 for the active empty-latent generation path. Generation and tile seeds are independent; -1 requests fresh randomization for that stage on each run. Fix both seeds when comparing changes without deliberately randomizing either stage. Finishing first applies the configured model upscaler, resizes to the chosen enlargement factor, and refines the enlarged image with tiled diffusion. Tile denoise controls how much is redrawn. Tile steps, scheduler, and sampler use the connected custom sampling nodes; the retained fallback fields are not the operative controls. Tile dimensions follow the original generated image dimensions. Tile padding supplies surrounding context in pixels, and Tile mask blur softens blending boundaries in pixels. Noise cleanup and Blur cleanup run after tiled refinement. Their strength choices range from Light to Maximum. Each cleanup stage can be bypassed independently. Strong cleanup can remove texture, so compare a lower strength or a bypassed stage if the result loses detail. Color correction offers Auto, Preset, Manual, and Colorize modes. Choose Preset to use Color preset and Preset variation; choose Manual for direct tonal tuning. Tint applies only in Manual mode. White balance shifts between cooler blue and warmer orange, while Green–magenta balance is a separate adjustment. Skin-tone preservation requires AI analysis. For Colorize mode, choose a colorization method; Force colorization overrides content detection that would otherwise skip art or anime. Sepia blend applies to vintage colorization. Bypass Color correction to return the preceding cleanup result. No color-reference image is connected, and palette and histogram outputs are not returned. The source's hand, face, and eye refinement passes and their detection chains are bypassed, with no Pipe switch to enable them. Their retained settings do not affect runs or provide anatomy repair. The uploaded-image and custom-width/height branches are also disabled; normal runs use the size preset. No LoRA entries are configured. The Pipe returns one final image collection through Sweet Tea's preview output rather than permanently saving through the original Image Saver. Larger batches, enlargement factors, and sampling workloads increase resource use.
CyberRealistic Negative - SDXL
Join The Tinkerer on Whop. Membership gets you early releases, private tools and a bunch of extra stuff.
ACE Step 1.5 music generator
Generate an MP3 music track from a music description and lyrics using ACE Step 1.5 XL Turbo. Describe the genre, instruments, mood, and vocal style, and supply lyrics with optional section markers. Adjust tempo, time signature, lyrics language, and musical key. Output duration and conditioning duration are independent controls in seconds; set them to match when changing track length. One shared seed controls conditioning and audio sampling; -1 selects randomization. Audio code generation is enabled by default and can be toggled, with separate guidance and sampling controls. Additional controls expose batch size, audio sampling settings, sampling shift, and MP3 encoding quality.
Vidu Q2 two-subject video
Generate one video featuring two reference subjects, with prompt-directed action, camera movement and optional generated audio. Upload one reference image for each subject; both uploads are required. Refer to the first as @subject1 and the second as @subject2 in the prompt. This interface supplies one image per subject. The references guide appearance rather than defining exact start or end frames. For a first run, upload both references, adapt the example prompt to their appearance, and keep the 5-second, 16:9, 720p defaults. Describe the setting, each subject's actions and the camera movement. Keep the requested action appropriate to the selected duration. Duration supports 1–10 seconds. Choose 720p or 1080p resolution and landscape, portrait or square framing through Aspect ratio. Movement selects auto, small, medium or large motion amplitude for objects in the frame; specify camera direction in the prompt. Generate audio is enabled by default. Include speech and sound directions in the prompt to request generated speech and background music, or disable it for video without generated audio. Seed -1 randomizes each run; a specified seed requests a particular generation variation. This tool uses the paid Vidu Q2 partner service and sends reference images and generation instructions to the provider. It returns one video for preview in Sweet Tea.
Qwen Image canvas outpainting
Extend an uploaded image on selected sides with prompted scene continuation using Qwen Image and inpainting ControlNet. The output is a resized, composited image with an automatically created padding mask. For a first run, upload an image and replace the example scene continuation prompt with content that fits its subject, lighting and style. The defaults add 200 pixels on the left, top and bottom and none on the right, before resizing the padded canvas to a longest edge of 1536 pixels. Set at least one extension amount above zero. Keep Lightning enabled at strength 1, with 4 steps, CFG 1, denoise 1, Euler and Simple for the initial run. Seed -1 randomizes each run; use a fixed seed to compare settings. Each extension is measured in original-image pixels before resizing. The padded image and its padding mask share the longest-edge target and resize together, retaining aspect ratio. Use a positive target size. The original image is also resampled, so preservation outside the generated region refers to the resized working image rather than the original file's exact pixels. No separate mask upload is needed. The region is derived from directional padding; uploaded alpha and loader edit masks are unused, and output transparency is not preserved. Boundary feathering acts before resizing. Mask expansion then grows or contracts the region in resized-mask pixels: positive values create overlap into the original image, while negative values contract it. Tapered corners affect nonzero expansion. Blur radius controls the Gaussian neighborhood and sigma independently controls its spread. The processed mask guides ControlNet and the final blend; softened boundaries mix original and generated pixels. The padded canvas is encoded and sampled without a separate latent noise mask. Final compositing determines where the generated result is visible, retaining the resized source outside the processed mask. Denoise controls how much of the encoded padded canvas is changed during sampling; lower values retain more initial structure. Control strength adjusts image-and-mask guidance. Guidance start and end are sampling-progress fractions from 0 to 1; keep start below end. The default interval covers the full sampling process. A negative prompt can discourage unwanted content, but has little or no effect at CFG 1. Sampler, scheduler and model-specific sampling shift are independent controls; retain Euler, Simple and shift 3.1 for the first run. Lightning is an optional adapter and starts enabled. Its toggle does not update steps or CFG. When disabling it, manually use the source baseline of 20 steps and CFG 2.5; when enabling it again at strength 1, return to 4 steps and CFG 1. For replacing a selected region inside an existing canvas using an uploaded edit mask, use the separate masked inpainting tool.
Recraft image generation from style references
Generate one to six images from a text prompt using a Recraft style created from four uploaded reference images. All four references are required and contribute to the shared style; they guide visual treatment rather than providing an image-editing canvas. For a first run, upload four references with a consistent look, replace the example image prompt with your subject and composition, and keep Output size at 1024x1024 pixels and Image count at 1. Choose realistic_image for a photographic base or digital_illustration for an illustrated base. Output size must be a Recraft-supported width-by-height value. Use Negative prompt to describe unwanted elements, or leave it blank. Image count supports 1–6 images with the same prompt and reference style. Leave Seed at -1 for a randomized re-run seed. A fixed seed controls re-run behavior but does not make Recraft results reproducible; generation remains nondeterministic. This tool requires access to the Recraft partner API. Reference images and generation inputs are sent to the service, and style creation and image generation use provider-priced calls. Style creation remains part of the connected generation path. Reusing a manually supplied style ID is not an available mode in this Pipe.
Wan 2.1 video outpainting
Expand a video's borders with prompt-guided content using Wan 2.1 VACE, producing a silent generated video. For a first run, upload a source video and enter a scene prompt describing its content, the surroundings to add and any desired motion. Keep the initial padding and generation settings, then adjust the padding on each edge to suit your composition. Padding is measured in source-frame pixels and creates the control canvas and outpainting mask; output width and height independently set the generated resolution. Choose output dimensions of at least 16 pixels in multiples of 16. Choose a positive frame count of 4n + 1, such as the default 81. These requirements are documented here because the dimension and frame-count fields have broad numeric ranges. Output FPS sets playback speed independently of source FPS. The default 81 frames at 16 FPS lasts about 5.1 seconds. Source audio is not carried into the result. Frame count is selected separately from the uploaded video's length; this tool does not promise to preserve the original duration or reproduce source pixels exactly. Advanced controls include unwanted-content prompting, VACE control strength, mask feathering and sampling settings. Seed -1 selects randomization; use a fixed nonnegative seed to reuse sampling noise with otherwise matching settings. Keep generation batch size at 1 for a single-video first run. The fixed CausVid LoRA is enabled by default, paired with 3 sampling steps and CFG 1. Its model and text encoder strengths are separately adjustable; text encoder strength only has an effect if the LoRA contains applicable weights. To use the supported bypass mode, bypass the CausVid stage and change sampling to the documented 20 steps and CFG 6. Bypassing does not change those sampling settings automatically. Video encoding offers automatic or explicit container and codec selection, plus CRF quality control; -1 retains the transport's default quality. Video creation defaults to 8-bit. The source describes optional 10-bit creation as retaining smoother gradients, with possible player or downstream compatibility limitations.
Flux Kontext multi-reference editing
Create an edited image from a primary image and up to two additional references using Flux.1 Kontext Pro. Each run also returns a preview of the assembled reference image sent to generation. For a first run, upload the required Primary image and replace the example Edit prompt with your desired change. Identify the referenced subjects and state what should remain unchanged. Both additional references are enabled initially: upload an image for each enabled reference, or disable any unused reference. Disable both for single-image editing; either additional reference can also be used independently. Keep the default layout initially. The second reference is placed above the primary image, and the third is placed to the right of that assembly. Advanced layout controls set each reference's position, joining-edge size matching, gap in pixels, and gap color. Third reference placement is relative to the primary image alone when the second reference is disabled. These controls change the assembled input, not the generated image's aspect ratio. Set Aspect ratio to the desired output width-to-height ratio, between 1:4 and 4:1. Generation controls include guidance strength and step count; their source defaults are 3 and 50. Seed -1 randomizes each run; a fixed seed reuses the seed setting. Prompt expansion lets the provider elaborate your instructions, but prevents exact repeatability even with a fixed seed. The reference preview accompanies generation; it is not a separate preview-only mode. This workflow uses a partner API and requires configured access and sufficient credits. Uploaded transparency is not preserved because only the image outputs, not the alpha masks, enter the reference assembly.
ACE-Step 1.5 song generator
Generate an MP3 song from a musical description, lyrics and musical settings using the fixed ACE-Step 1.5 XL SFT model. For a first run, keep the supplied English neo-soul description and lyrics, or replace both with your own. Describe genre, instruments, vocals, mood and arrangement in Music description. Enter the words to sing in Lyrics; optional section markers such as [Verse] and [Chorus] communicate arrangement. Keep Generate audio codes enabled, Batch size at 1, both duration fields at 120 seconds and the sampling defaults, then generate the MP3. Output length sets the audio canvas length in seconds. Conditioning duration tells the text-conditioning stage the intended song length. These controls do not synchronize automatically: normally change both together. Tempo is in beats per minute. Musical key, time signature and language provide musical direction rather than guarantees of exact performance. Time signature accepts the source codes 2, 3, 4 or 6, rather than arbitrary fractions. Language uses the supplied supported codes; en means English. E minor is the supplied musical-key value; other accepted key choices are not enumerated in the available evidence. Generate audio codes controls the preliminary language-model stage. Audio-code guidance, temperature, top-p, top-k and min-p apply when that stage is enabled. Disabling it leaves the subsequent audio diffusion stage active; this Pipe does not provide an audio-reference input. Audio-code guidance and Diffusion guidance control separate stages. One shared seed feeds both stages. Use -1 for randomization or a fixed nonnegative integer to reuse a seed. Advanced audio diffusion controls include steps, sampler, scheduler and denoising strength. Full denoising at 1 is the supplied setting for generation from an empty audio latent. Sampling shift adjusts the model noise schedule and defaults to 3. Batch size controls the number of audio latents generated with the shared song settings. Decoded audio is saved as MP3 with V0 variable quality, 128k or 320k encoding. Negative conditioning is automatically zeroed, so there is no editable negative prompt. This is text-and-lyrics generation, with no uploaded audio reference or audio-editing mode.
Wan 2.2 controlled video · Standard
Generate a silent video guided by uploaded control footage and a scene-and-motion prompt using Wan 2.2 14B Fun Control. This standard branch uses high-noise and low-noise models across a coordinated 20-step schedule; the separate four-step sibling uses Lightx2v LoRAs. For a first run, upload a control video and replace the saved scene prompt. Leave Canny edge extraction disabled if the footage already contains prepared control frames. For ordinary footage, enable Canny to extract edges before conditioning generation. Its low and high thresholds apply only while enabled; keep the low threshold below the high threshold. Reference-image conditioning is disabled initially. To use it, upload an image and enable Reference image. You can leave it disabled to generate with the prompt and control video alone. The reference upload supplies the loader's RGB image output, not its alpha mask. Defaults generate 640 × 640 pixels and 81 frames at 16 FPS, approximately 5.1 seconds. Width and height use increments of 16; frame count follows 1 + 4n. Playback FPS changes duration independently of frame count. The result does not inherit source audio or source FPS. Keep batch size at 1 for a first run; this Pipe returns through one video output rather than separate named outputs for batch items. Advanced controls include the negative prompt, random seed, independent prompt guidance for each generation stage, samplers, schedulers and model schedule shifts. Seed -1 randomizes initial noise; a fixed nonnegative seed reuses initial noise with otherwise unchanged settings. Preserve the saved sampling setup initially. If editing schedules, keep both total-step values equal, use coordinated schedulers, and make Initial end step equal Refinement start step within that schedule. The default handoff is step 10 of 20. Refinement continues the initial latent without adding new noise. Video output offers automatic or explicit container and codec choices, plus CRF encoding quality. CRF -1 uses the transport default. Video construction defaults to 8-bit; 10-bit is available but may have player or downstream compatibility limitations. The output is newly generated footage guided by the control frames, rather than a copy of the uploaded clip.
CyberRealistic Positive (Pony)
Join The Tinkerer on Whop. Membership gets you early releases, private tools and a bunch of extra stuff.
Empire Style
This is a DreamArtist Textual Inversion Style Embedding trained on a single image of a Victorian city street, at night. You can get amazingly grand Victorian stone buildings, gas lamps (street lights), elegant...
Qwen-Image edge-guided restyling
The source image is resized to the chosen megapixel count while preserving its aspect ratio. It supplies both the starting image latent and the Canny edges used for structural guidance. Denoise controls how strongly the image is regenerated; control strength sets adherence to its edges. At the source default of full denoise, edge guidance provides the main structural constraint. Edge thresholds tune which details become guidance. The optional Lightning LoRA starts disabled, matching the source workflow. The source notes suggest 4 steps and CFG 1.0 when enabling it, versus the preserved defaults of 20 steps and CFG 2.5 without it. These settings remain separate controls.
Bria FIBO image edit
Edit an uploaded image with text instructions using Bria FIBO and receive one edited image in the Pipe's preview output. For a first run, upload a Source image, replace the architectural night-scene example in Edit instruction with your desired changes, and adapt Negative prompt to describe unwanted features. Leave Structured prompt empty and retain the initial Guidance and Steps values, then run the Pipe. The edit applies to the entire image. This workflow has no mask input or output-size controls, and it does not preserve uploaded transparency. The selected output returns an image preview rather than using the original SaveImage stage. The node's secondary text output is not exposed. Guidance ranges from 3 to 5; higher values make the image follow the instruction more closely. Steps sets sampling iterations from 20 to 50. Seed -1 requests fresh randomization on each run; use a fixed seed to control generation randomness. For programmatic editing, enter a Bria-compatible structured edit prompt as JSON in Structured prompt, using it instead of the ordinary edit instruction. Leave this field empty for normal text editing; it requires the provider's structured edit format rather than arbitrary JSON. Moderation settings controls whether the individual provider checks are supplied. With true selected, Prompt moderation, Source image moderation and Result moderation control their respective checks. The supplied defaults select true with all three checks disabled. Selecting false omits the individual settings. Generation uses the Bria partner API, sends the source image and editing inputs to the provider, and requires the runtime's Comfy API authentication. Provider charges apply.
Nano Banana 2 image generator
Generate images from a text prompt with Nano Banana 2 or Nano Banana 2 Lite and return the final images to Sweet Tea. A configured, authenticated Gemini API connection is required. Requests send your prompt and provider instructions to Gemini and use provider billing. This workflow has no reference-image input. For a first run, keep Nano Banana 2 Lite, aspect ratio 1:1 and resolution 1K. Use the supplied racing-poster prompt or replace it with a description of your subject, composition, style and desired text, then run the Pipe. Put unwanted elements into the same prompt as constraints; there is no separate negative prompt. Choose the model before resolution. Lite uses 1K; the existing guidance specifies 1K, 2K and 4K for Nano Banana 2. Return resolution to 1K before switching back to Lite. Choose an explicit aspect ratio for the desired framing; auto has no reference image to match in this workflow. Thinking level selects MINIMAL or HIGH. Temperature controls sampling randomness from 0 to 2, and top P controls the nucleus sampling threshold from 0 to 1. Keep their supplied defaults for a first run. Seed -1 requests fresh randomization; a fixed seed provides only best-effort consistency, and changing model or sampling settings can change the result. System instructions guide the provider's interpretation of your prompt; the supplied instructions prioritize image generation. IMAGE+TEXT can request accompanying provider text, but this Pipe returns only the final image output. Text and intermediate thinking images are not included. The output stage transports images to Sweet Tea without permanently saving PNG files.
Wan 2.1 first-to-last frame video
Generate a short, silent video transition between a first image and a last image, guided by a motion prompt. Both images are required. Wan 2.1 VACE conditions the endpoints; it does not guarantee pixel-exact reproduction. Uploaded alpha masks are not used. For a first run, upload endpoint images with matching dimensions and compatible framing, replace the example motion prompt, keep the 512 × 512 output, choose length setting 4 and leave Lightning disabled. Keep batch size 1 and the supplied sampling and encoding defaults. The negative prompt lists unwanted appearance and motion; its supplied Chinese exclusions can be retained or replaced. Choose output width and height as multiples of 16, each at least 16. Other values round down. The source recommends resolutions up to 720p and clips shorter than five seconds. Length is a positive integer setting converted to 16 × setting + 1 generated frames. Setting 4 gives 65 frames, approximately 4.06 seconds at 16 FPS. The preserved default of 5 gives 81 frames, approximately 5.06 seconds. Playback FPS changes speed and duration without generating additional frames. Lightning enables the fixed Lightx2v LoRA and switches to its separate steps and CFG controls: defaults of 6 steps and CFG 1, compared with standard defaults of 20 steps and CFG 6. Lightning LoRA strength applies only in Lightning mode. Frame guidance strength scales endpoint conditioning; CFG controls text guidance. Both modes share seed, sampler, scheduler, denoising amount and sampling shift. Seed -1 randomizes each run; use a fixed seed to compare changes with the same initial noise. Advanced playback and encoding settings include bit depth, file type, codec and CRF. The default uses 8-bit video creation and H.264 encoding with automatic file type. AV1 and other containers are selectable; choose compatible container and codec settings. Ten-bit video requires compatible encoding and playback. The graph has no audio input and this interface returns one video output.
Replace video background
Replace an uploaded video's background with a selected solid color using Bria. For a first run, upload your source video, keep Background color set to Black, and run the Pipe to download the processed video. Choose another listed background color to change the fill behind the foreground subject. The output uses a solid background; no transparent-output mode is provided. Rerun seed controls whether Bria processes the video again. Its default of -1 selects a random value on each run. Bria results remain non-deterministic even when you reuse a seed. Under advanced Video output settings, you can choose the file type and codec or leave both on auto. Quality (CRF) defaults to -1 for automatic quality and accepts explicit values from 0 to 63. These settings configure output encoding rather than background removal.
