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
18 shown of 41,727
MoGe valid geometry mask
Estimate a geometry-validity mask from one perspective image. For a first run, upload an image, leave Automatic resizing enabled and keep Detail level at 2. Each run performs MoGe geometry inference, renders predicted validity and converts the rendered red channel into the output mask. The mask identifies regions with valid predicted geometry. It is not foreground segmentation or an object cutout; sky and other regions with undefined geometry may be excluded. Prediction uses the uploaded RGB image, independently of uploaded transparency. This Pipe exports a mask, not depth, normal maps or a mesh. Automatic resizing checks image width. Images wider than 2048 pixels are resized to a fixed 2048-pixel longer edge before inference. Images at most 2048 pixels wide remain unchanged, even when their height exceeds 2048. Disable Automatic resizing to use the original image. The mask follows the dimensions used for inference, so resizing can change its dimensions relative to the upload. Open Geometry estimation for inference controls. Detail level ranges from 0 to 9; the source identifies 0 as fastest and 9 as most detailed. Horizontal field of view is measured in degrees: leave 0 for automatic recovery from predicted points, or enter a known camera value for geometry unprojection. Exclude invalid geometry sets invalid points and depth to infinity when enabled; disabling it retains raw predicted geometry. The validity mask is returned separately in either mode. Inference batch size controls images per inference call and does not create additional variants from the single upload. Force projection starts enabled; its precise effect is not documented in the supplied source, so retain the default for a first run. These settings do not select other output types. Mask rendering and red-channel conversion are fixed to preserve the validity-mask result. The workflow uses the fixed model moge_2_vitl_normal_fp16.safetensors. For a manually managed ComfyUI installation, the source specifies models/geometry_estimation/ as its location and https://huggingface.co/Comfy-Org/MoGe/resolve/main/geometry_estimation/moge_2_vitl_normal_fp16.safetensors as its download source.
Princess Style
This is a Style embedding which turns your image subjects into bonafide Princesses! Think pearls, tiaras, and ballgowns! Simply throw Style-Princess on to the end of your prompt (or the start, if the effect doesn't...
Z Image Turbo pixel-art image generator
Generate one image or a batch from text using the fixed Z Image Turbo model, with optional pixel-art styling. No uploaded image is required. For a first run, leave pixel-art style enabled, edit the pixel-art prompt, and keep the 1024 × 1024 size, batch size 1, LoRA strength 1 and four sampling steps. The source prompt begins with “Pixel art style, retro”; use that as a starting point when describing your own subject. Run the Pipe to receive the generated images. The style toggle switches both the model branch and the prompt. When disabled, the base model uses the separate unstyled prompt. Edit both prompts when comparing modes; changes to one do not update the other. LoRA strength affects only the enabled pixel-art branch. Width and height are output pixels and must be multiples of 16. Batch size controls how many images are returned. The output stage does not permanently save images to the ComfyUI output folder. Advanced sampling controls include seed, steps, guidance scale, sampler, scheduler and denoise fraction. Seed -1 randomizes each run; use a fixed seed to compare changes with otherwise unchanged settings. The source defaults are four steps, guidance 1, res_multistep sampling, the simple scheduler and denoise fraction 1. Negative conditioning is zeroed automatically, so there is no editable negative prompt. The optional sampling-shift stage starts bypassed, matching the source workflow. Enable it before adjusting its shift value; the source value is 3. While bypassed, shift has no effect. Generation starts from an empty latent and does not support image-to-image input. Reducing denoise fraction changes sampling but does not preserve an uploaded image. The model, text encoder, VAE and pixel-art LoRA are fixed by this Pipe.
Video to pose animation
Turn a source video into a rendered whole-body pose animation using SDPose. The output is one pose video, rather than an overlay on the original footage or a downloadable keypoint dataset. It uses the source frame rate and includes source audio when available. For a first run, upload a clip with one clearly visible person, keep the default 1024-pixel longer edge and drawing settings, and run the Pipe. The required checkpoint is sdpose_wholebody_fp16.safetensors. Frames are resized while preserving aspect ratio before pose extraction; Longer edge sets both detection resolution and rendered frame dimensions. Use Draw body, Draw hands, Draw face, Draw feet and Draw head to choose the rendered features. These switches change visualization, not what the model extracts. Confidence threshold controls which keypoints are drawn: higher values suppress uncertain points, while lower values include more points. Line width and Face point size are measured in output pixels; Face point size applies when Draw face is enabled. Resampling method controls frame resizing before detection. Area is suited to downscaling and Lanczos to upscaling. Processing batch size controls how many frames the extractor processes together; lower it if memory is limited. It does not change video duration. Frame rate is inherited from the source and cannot be independently adjusted here. This workflow supplies no bounding boxes, which the extractor requires for multi-person detection. Use single-person footage rather than expecting reliable multi-person capture. Advanced output controls select the container, codec, encoding quality and video bit depth. Keep File type and Codec on automatic, Quality (CRF) at -1 and Bit depth at 8 for a first run. Explicit container and codec choices must be compatible. The 10-bit option requires compatible encoding and playback and does not improve pose detection.
OmniGen2: Text to Image
Generate a single image or a batch from text with OmniGen2. No uploaded image is required; the diffusion model, Qwen text encoder, and VAE are fixed by this workflow. For a first run, enter the subject, composition, lighting, and style in Positive prompt. Negative prompt describes unwanted features. Leave the sampling defaults in place and generate one 1024 × 1024 image. Width and height are measured in pixels and must be multiples of 16; together they determine the aspect ratio. Images per run sets the batch size. Larger dimensions and batches increase memory use. Advanced settings expose guidance, seed, and sampling controls. Guidance defaults to 5. Guidance mode selects the source dual guider's regular or nested combination. Negative prompt feeds both its secondary and negative branches; there is no separate secondary prompt. Secondary guidance defaults to 2 and is not an independent negative-prompt strength in regular mode. Seed -1 chooses new random noise for each run. Use a fixed nonnegative seed when comparing settings. Sampling defaults are 20 steps, Euler sampler, and the simple scheduler. Steps sets the sampling step count, Sampler chooses the sampling algorithm, and Scheduler sets the distribution of noise levels. Denoise selects the fraction of the schedule used and defaults to 1 for the full schedule. Sampling begins from an empty latent. Lowering Denoise does not enable image editing, and this tool has no reference-image input. All decoded images in the batch are returned through Sweet Tea's preview output. The workflow requires omnigen2_fp16.safetensors, qwen_2.5_vl_fp16.safetensors, and ae.safetensors; model selection is not exposed.
LTX-2.5 text to video with audio
Create one video with generated audio from a text prompt using the fixed LTX-2.5 distilled model. Describe subjects, action, camera movement, lighting and desired sounds in Positive prompt. No image or audio upload is required. For a first run, replace the example prompt or try it as supplied, then keep 5 seconds, 24 FPS, widescreen aspect ratio and the 0.9-megapixel resolution target. Leave output file type and codec on auto. Prompt enhancement is enabled: it expands your text before video conditioning. Disable Enhance prompt to encode your original wording directly. Expansion tuning affects the output only when enhancement is enabled; sampling seed, temperature and token filters apply when Prompt sampling is on. The pipeline jointly generates audio and video at half the selected spatial dimensions, upscales the video latent with the fixed 2× spatial upscaler, then refines audio and video together. Both streams are decoded and assembled into the returned video. Upscaling and refinement are integrated stages, with no bypass controls. Aspect ratio and megapixels jointly determine approximate final dimensions through the resolution selector. They are shape and pixel-budget choices, not separate width and height overrides. Duration is in positive whole seconds. Use a whole-number frame rate from 1 to 120 FPS. The graph requests duration × FPS + 1 frames: keep duration × FPS divisible by eight and no greater than 999, respecting the audio latent stage's 1,000-frame maximum. At 24 FPS, whole-second durations from 1 to 41 meet these frame-count requirements. Playback includes the extra frame. Larger dimensions and more frames increase processing and memory requirements. Advanced controls separate initial generation from refinement. Each stage has its own seed, video guidance, audio guidance, sampler and comma-separated noise schedule. Keep the supplied guidance value of 1, samplers and distilled-model schedules for the first run. Negative prompt supplies unwanted-content conditioning to both stages; its influence depends on their guidance settings. A seed of -1 randomizes each run. To hold the exposed random inputs constant, fix both stage seeds and, when sampled prompt enhancement is enabled, its separate seed. Fixing only Generation seed leaves other random inputs variable. Video decode tiling controls spatial tile sizes and overlap in pixels, plus temporal chunk sizes and overlap in frames. It does not set output resolution or duration. Video output encoding offers automatic settings or explicit container, codec and CRF choices; use compatible container and codec selections and keep CRF at -1 for the transport default. The runtime needs the fixed transformer, generation text encoder, enhancement text model, audio and video VAEs, and latent upscaler named in the workflow. This tool returns video with generated audio and does not offer uploaded audio, a silent-output switch, independent audio export or automatic duration prediction. Audio and video batch fields remain at one for this single-video interface.
SDXL image remix
Remix an uploaded image using a text prompt and the fixed waiNSFWIllustrious_v130.safetensors checkpoint, with optional LoRAs, tiled enlargement and subject refinement. The saved result includes every enabled finishing stage. For a first run, upload a source image, replace the example positive prompt with your desired subject, appearance and style, and review the negative prompt for unwanted content. Keep automatic resizing enabled and the default 1024 × 1024 generation dimensions. Leave LoRAs, upscaling and subject refinement off initially. Denoise starts at 0.75: lower values retain more of the source, while higher values allow stronger reinterpretation. Width and height apply to base generation when automatic resizing is enabled; source-size handling with resizing disabled is determined by the toolkit. Seed -1 requests a fresh random seed each run. Use a fixed seed when comparing prompts or settings. Steps, CFG, sampler and scheduler control base sampling. The checkpoint and baked VAE are fixed; CLIP skip is available under advanced model settings. Each of the three LoRA slots has an independent enable switch, installed LoRA name and strength. Select a LoRA compatible with the fixed Illustrious checkpoint and enable its slot. Multiple enabled slots combine in the same generation. Optional upscaling runs after base generation and before subject refinement. It uses the fixed 4x_NMKD-Siax_200k.pth model; the upscale factor multiplies the base image dimensions. Upscale denoise controls changes during enlargement. Tile width, height and padding are in pixels. Seam correction starts at None; its related settings apply when a supported seam mode is selected. Prompt cleanup, tile-processing mode, uniform tiles and tiled decoding are also available. Upscale sampler and scheduler start at Pipeline. Upscale steps retains the source value 0, whose exact fallback behavior is not established here; retain it initially and consult the installed toolkit before changing it. Optional subject refinement runs last, targets face by default and has its own denoise control. Enter only a subject category supported by the installed toolkit. Its advanced detection, crop, feather and mask controls preserve the source defaults. Several have undocumented types or units, including boolean guide size, integer noise mask 5 and detection threshold 1024. Consult the matching UmeAiRT Toolkit documentation before changing these values; no normalized confidence range or pixel interpretation is established for them. Requires ComfyUI-UmeAiRT-Toolkit (https://gitlab.com/UmeAiRT-Studio/ComfyUI-UmeAiRT-Toolkit.git) and waiNSFWIllustrious_v130.safetensors in ComfyUI/models/checkpoints/. Enabling upscaling additionally requires 4x_NMKD-Siax_200k.pth in ComfyUI/models/upscale_models/. Optional LoRAs belong in ComfyUI/models/loras/. The source describes subject-refinement detector and segmentation assets under models/ultralytics/bbox/, models/sams/ and models/ultralytics/segm/, with automatic downloads handled by the toolkit; exact asset names are not supplied. This Pipe requires an uploaded image and exposes one final remixed-image output. It does not expose checkpoint replacement, a separate text-to-image mode or standalone finishing of an upload without upstream generation.
Seedance image to video
Animate a starting image into one video using a motion prompt and ByteDance Seedance. Upload the image to use as the first frame, then describe the subject's action and desired camera movement. Generation sends the image and prompt to the ByteDance API and requires configured API access and sufficient credits. The result is returned through Sweet Tea's video output. For a first run, replace the example prompt to match your image and keep Seedance 1.0 Pro, 480p, adaptive aspect ratio and a duration of 5 seconds. Duration accepts whole seconds from 3 to 12. Resolution and aspect ratio set the requested output shape. Choose among the available Seedance models. Generate audio applies only to seedance-1-5-pro-251215; other models ignore it. Fixed camera adds a stationary-camera instruction to the prompt without guaranteeing the effect, so keep your motion prompt consistent with that request. Seed -1 randomizes each run; a specified seed controls generation randomness. AI watermark requests an “AI generated” mark on the video. Advanced Video output settings select the returned file container and codec. Leave both on auto and Quality (CRF) on -1 for default output encoding, or choose from the exposed encoding controls.
4× video upscale
Upscale an uploaded video to four times its source width and height using RealESRGAN x4plus. Upload a source video and run with the defaults: 8-bit output with automatic container and codec selection. Source audio, when present, and the source frame rate feed the reconstructed video. Advanced controls offer 8-bit or 10-bit video, containers auto/mp4/mkv/webm, and codecs auto/h264/av1. Manual container, codec and bit-depth choices must be compatible. 10-bit output can reduce gradient banding but requires compatible encoding and playback; it does not recover precision missing from the source. Each frame is upscaled independently. There is no temporal consistency stage, prompt or diffusion refinement, and no target-resolution resize control. Larger or longer videos require more processing and memory. The encoding quality control retains its source default because tuning semantics are not established in the supplied evidence.
ACE-Step 1.5 song generator
Generate an MP3 song from a musical description, lyrics and musical settings using ACE-Step 1.5 Turbo. Describe the genre, instruments, mood and arrangement in Music description, and enter the words to sing in Lyrics. No uploaded audio is required or supported. For a first run, use the supplied rock description and section-marked lyrics with 190 BPM, E minor, English (en), time-signature value 4 and Batch size 1. Keep both duration fields at 120 seconds, then run the tool and listen to the MP3 result. To make your own song, replace the description and lyrics; section markers such as [Verse 1] and [Chorus] describe the intended structure. Output duration sets the generated audio length in seconds. Song duration is a separate conditioning and audio-planning hint. When changing length, set both to the same number; they do not synchronize automatically. Batch size requests multiple audio latents with the same length and song conditioning; its default is one. Choose Language to match the lyrics. Language has a finite list of language codes, with en for English. Time signature accepts 2, 3, 4 or 6. Musical key starts at E minor; the source does not enumerate accepted alternatives, so other entries are not verified by this interface. Audio planning is enabled by default and uses an additional language-model stage to generate audio codes. Turning it off disables code planning while retaining the text-to-audio generation path; it does not enable an audio-reference input. Planning seed, Planning guidance and the temperature, top-p, top-k and min-p controls apply to planning. For top-p, use probability values between 0 and 1 despite the source field's broader numeric range. Zero disables the top-k and min-p filters. Planning seed and the audio diffusion Seed control separate random stages. Both default to -1, which randomizes on each run. Use explicit seeds for both stages when you want to retain their random choices. Advanced Audio diffusion controls include Steps, CFG, Sampler, Scheduler and Denoising strength. Start with the supplied eight steps, CFG 1, euler sampler, simple scheduler and denoising strength 1. Generation starts from an empty audio latent; reducing denoising strength does not preserve uploaded audio. Noise schedule shift is a separate model-level adjustment, defaulting to 3. Negative conditioning is zeroed internally, so there is no editable negative prompt. MP3 quality offers V0 variable-bitrate encoding and fixed bitrates of 128k or 320k, affecting compression and file size. The selected output is compressed MP3 rather than a lossless audio master.
Corneo's Mercy (Overwatch) Embedding
This is a textual inversion embedding for Mercy (Angela Ziegler) from Overwatch. Use corneomercy to activate.
Topaz image enhancement
Enhance an uploaded image with the workflow’s saved Topaz configuration. For your first run, upload a source image and run the Pipe. The enhanced image appears in the result preview. The saved configuration includes “Wonder 3.5.” Enhancement settings are fixed in this interface; there are no selectable enhancement modes, prompt controls or output-size controls. The resulting dimensions and degree of alteration depend on that configuration, and a specific upscale factor is not established. Uploaded transparency is not preserved through the source image connection. The selected output is an image preview; the original save node’s PNG format, bit depth and color-space settings do not apply to this output.
Kimberly Nobody (age slider)
Follow me to make sure you see new styles , poses and Nobodys when I post them. Things move fast on this site, it's easy to miss.
PMRF image enhancer
Upload a source image to produce a PMRF-enhanced image. For a first run, keep the source defaults of 2× scale, 25 steps, and Lanczos interpolation. Scale controls enlargement; use 1× to process at the original size. Larger scales increase output dimensions and resource requirements. Steps controls the processing iteration count and trades additional computation for a different restoration result. Interpolation selects the resizing method. Seed lets you vary the result; the default randomizes on each run. This workflow has no prompt or restoration-strength control. Uploaded transparency is not preserved because only the loader's RGB image output is connected.
Kling image generation
Generate one or more images from text using Kling, with controls for model, aspect ratio, and image count. For a first run, replace the supplied surreal portrait prompt with a description of your subject, scene, composition, and style, or use the example as supplied. Leave the negative prompt empty unless you want to discourage particular content or visual characteristics. Keep kling-v3, 16:9, and one image, then run the Pipe. Generated images appear together in the result preview. Choose kling-v3, kling-v2, or kling-v1-5 to change the generation model. Aspect ratio sets the image's width-to-height proportions; 16:9 produces a landscape composition. Image count supports 1–9 images per run. This Pipe supports text-driven generation only. It has no connected reference image or upload input, so the hidden reference settings provide no usable reference-image mode. Keep seed at -1 to randomize it each run. Seed controls whether the provider node re-runs; a fixed seed does not make image content reproducible. Generation sends your prompts to the external Kling provider and uses provider-priced calls.
Beauty In Evil - By HailoKnight
“When the people of the world all know beauty as beauty, there arises the recognition of ugliness. When they all know the good as good, there arises the recognition of evil.”
Flux 2 two-image design transfer
Generate a new image with Flux 2 using a design reference, a scene reference, and a prompt describing the transfer. For a first run, upload the design as Reference image 1 and the objects or scene as Reference image 2. Both uploads are required. Keep the supplied transfer prompt or describe precisely how each reference should contribute. Start with 1 output megapixel, 1 image, and Turbo mode off, then run to receive the generated image. Both references provide conditioning; generation starts from an empty latent. The result is a newly generated interpretation, so original pixels and object details are not guaranteed to remain unchanged. Output dimensions are derived from the resized first reference, following its aspect ratio subject to latent dimension rounding, even when the second reference supplies the scene. Output megapixels also controls the first reference's processing resolution. Second reference megapixels affects its conditioning resolution independently and does not determine output dimensions. Each reference has its own resize interpolation control. Turbo mode switches model adaptation and sampling budget together. Off uses the base model and Standard steps, initially 20. On uses the supplied Flux2TurboComfyv2 LoRA and Turbo steps, initially 8. Turbo strength affects only Turbo mode and defaults to 1. Enter step counts from 1 to 4096; only the active mode's step count is used. Guidance and sampler apply in both modes. Use seed -1 for fresh randomness each run, or a fixed seed to compare settings with the same initial noise. Image count sets the generated batch size. Larger resolutions and batches increase memory and processing requirements. Uploaded transparency is not retained through either reference path. The tool has one main prompt and no separate negative-prompt input.
HappyHorse image to video
Animate an uploaded first-frame image into one 3–15 second video using a motion prompt. The image determines the output aspect ratio. For a first run, upload your image, replace the example prompt with movement and camera directions appropriate to it, and keep HappyHorse 1.1, 720P resolution, and the 5-second duration. Prompts support English and Chinese. The uploaded image is required; the example prompt refers to a woman and horse and should be adapted to your subject. Choose 720P or 1080P output and a duration from 3 to 15 seconds in whole-second increments. HappyHorse 1.0 is also available. Seed -1 requests a fresh random seed each run; a fixed seed controls generation randomization. Enable Watermark to add the provider's AI-generated watermark. Generation sends the image and prompt to the HappyHorse partner API, requires configured API access, and uses provider-priced generation. The result is returned as one video for preview. Advanced video output settings offer automatic, MP4, MKV, or WebM file type and automatic, H.264, or AV1 codec selection; keep both on auto for the first run.
