Directorio de recursos
Encuentra lo que necesita tu flujo.
Guides: techniques, setup, and troubleshootingBusca Pipes de Sweet Tea, flujos externos, modelos, paquetes de nodos y guías en un catálogo con evidencias.
Empieza con un flujo ↗Resultados de búsqueda
Todos los recursos
20 mostrados of 41.749
GPT Image generation and editing
Create one or more images using a text prompt, optionally guided by an uploaded reference image. For a first run, leave Reference image disabled, enter your prompt, and use the default square size, high quality, and one image. To edit an image, enable Reference image, upload it, and describe the changes in the prompt. Output size selects a preset or automatic sizing. Custom width and height apply only when Output size is Custom and Model is gpt-image-2; each dimension must be 1024–3840 pixels in multiples of 16. Quality affects generation time and cost, and Image count requests 1–8 results. Model offers the three source-supported GPT Image variants. Background requests automatic, opaque, or transparent output from the provider; the supplied graph does not establish preservation of output alpha. Uploaded reference transparency is discarded by the RGB input path, and this tool has no mask-based inpainting interface. Seed is not implemented by the provider backend and cannot reproduce a result. Runs require access to the ComfyUI partner API with authentication and sufficient credits.
Character motion transfer
Animate a reference character using motion poses from a source video, producing one animation assembled from five sequential generated segments. Provide a character reference image and a motion video file path accessible to the execution runtime. The image supplies appearance, reference pose and an automatic caption; the video supplies motion poses. Source audio and uploaded image transparency are not used. For a first run, use a reference showing the character's body clearly and a motion clip with one clearly visible performer. Edit both dancing prompt additions to describe your intended action. They surround the automatic reference-image caption, which remains part of the positive prompt. Keep the default six sampling steps, guidance settings, 81 frames per segment and five-frame overlap. The default output is a silent H.265 MP4. Width and height control both input resizes. The default requested portrait size is 450 by 800 pixels; actual dimensions are adjusted for divisibility by 16. Both inputs use aspect-preserving cropping, with independent reference and motion crop positions. Keep the character and relevant limbs inside each crop. Frame rate is shared between motion-source resampling and final playback. Enter a positive FPS value. Frame stride keeps every nth resampled source frame; values above 1 advance the action faster at the unchanged playback FPS. Skip initial frames selects a later starting action. Source frame limit caps loaded motion frames, with 0 meaning no cap; it does not change the number of generated segments. The graph always generates an initial segment and four continuations rather than automatically matching the full source duration. Keep frames per segment in the 4n+1 pattern, such as 81, and no greater than 256. Keep overlap below the segment length and no greater than 64. Provide enough sampled motion frames for the initial segment. Each continuation defaults to repeating the last available pose when its motion window runs out; its short-source behavior can instead require enough frames by selecting error. Reference strength and its sampling start/end fractions apply across all segments. Body, hand and face pose components can be enabled independently for the motion source and reference image. Pose strength, pose CFG and sampling start/end fractions are independent for each segment. Pose CFG has no effect while the corresponding sampler CFG is 1. The negative prompt is shared, and its influence depends on sampler CFG. Steps is shared by all five samplers. Seeds, CFG, schedule shift, scheduler and denoise are separate per-segment controls. Start with the source defaults and matching segment settings; earlier generated frames become context for later segments, so an early change can affect the remaining video. The fixed Lightx2v distillation LoRA is part of the six-step setup and has an adjustable strength. Advanced continuation context controls adjust the encoded generated-frame multiplier and noise augmentation for each later segment. Automatic caption controls affect the positive prompt used by every segment. Caption seed matters when caption sampling is enabled; the token limit is a ceiling, and lowering it can truncate the caption. Seed -1 requests fresh randomization for the caption or the corresponding video segment. Video output controls change encoding rather than generated motion. File type and codec are selectable; choose compatible combinations supported by the runtime. The source defaults are MP4, H.265, 10-bit yuv420p10le and sRGB. CRF defaults to 22; for codecs using CRF, lower values generally retain more detail and produce larger files. Bitrate is expressed in Mbps, with 0 leaving a positive bitrate unspecified. Keep pixel format and bit depth consistent with the codec. HDR encoding choices do not establish HDR detail in the generated frames.
ZIB + ZIT image generator and upscaler
Generate a final image batch from text using the fixed Moody ZIB composition model and Moody ZIT detail model, followed by tiled enlargement. No upload is required. For a first run, replace Positive prompt with your subject, composition, lighting and style. Keep the 640 × 960 starting canvas, Image count of 1 and supplied sampling settings. Leave Face detailing and Contrast finishing disabled. The example prompts favor cool, pale portrait styling; replace the tile and face examples when enabling those options for another subject. Detail enlargement defaults to 1.7× before the second diffusion pass. Final enlargement defaults to 2× during tiled refinement and supports 0.05–4 in increments of 0.05. Final dimensions are approximately the starting dimensions multiplied by both factors, subject to latent rounding. Factors below 1 reduce dimensions. Larger canvases, factors and image counts increase memory use and processing time. This Pipe always generates its starting image and has no uploaded-image input for standalone upscaling. Positive prompt guides both generation passes and normally tile refinement. Enable Use separate tile prompt to substitute Tile prompt for the tiled stage. Negative prompt affects only composition; later diffusion stages use zeroed negative conditioning. Tile denoise controls how strongly the enlarged image is repainted. Composition steps defines a full 17-step schedule, with Composition start step 0 and Composition stop step 12. The partial pass retains noise before latent enlargement. Detail steps defines a separate 11-step schedule starting at Detail start step 5; Detail stop step 999 allows it to finish. Start and stop indices belong to each stage's own schedule. Keep schedule lengths, boundaries and noise settings consistent when changing them. Latent resize method changes interpolation between these passes. Composition sampling shift affects the first model; Detail and tile sampling shift affects both subsequent stages. Composition, detail, tile and optional face sampling have independent seeds. -1 randomizes each active stage on each run. Fix all active stage seeds to reuse their randomization; other control changes can still change the result. Tile dimensions are calculated automatically from the detail-pass image dimensions and Final enlargement. The formulas retain a fixed 96-pixel term even if Tile padding changes, so preserve the padding default initially. Tiles per batch controls tile processing rather than output image count, and applies to redraw rather than seam correction. Seam correction starts at None; seam denoise, band width, blur and padding apply when a correction mode is selected. Tiled decoding controls VAE decoding separately from image redraw tiling. Enable Face detailing to detect and repaint faces after enlargement. Face prompt is independent of Positive prompt. Face denoise controls how strongly faces change and may affect identity or expression. Face crop sizing, detection, segmentation, noise masks, sampling and encoding/decoding controls apply only while this stage is enabled. Guide size works with its bounding-box or crop basis and maximum size. Keep Face inpainting model mode false for the fixed supplied model, and leave Face wildcard text empty unless using supported Impact Pack syntax. Enable Contrast finishing to apply the fixed 1× skin-contrast model, then adjust Contrast strength and Blend mode. With normal blending, strength 0 keeps the pre-finish image and 1 uses the finish. When finishing is disabled, normal blending leaves the image unchanged regardless of strength. Other blend modes can alter the image even while finishing is disabled. The model pair and source LoRA configurations are fixed. Manual masked detailing is unavailable because its mask depends on a live ComfyUI editor session rather than a portable Pipe input. The retained manual bridge and regional detailer remain bypassed without enable toggles; their archived settings do not affect the output. Only final images are returned.
Wan 2.1 camera-controlled image to video
Animate an uploaded still image into a prompt-guided video with selectable camera movement using Wan 2.1 Fun Camera 1.3B. For a first run, upload a source image, replace the landscape example prompt with a description of your scene and desired subject action, and choose a camera movement. Keep the remaining defaults initially: Zoom In, camera speed 1, 512 × 512 pixels, 81 frames, 16 FPS and generation batch size 1. These settings produce about 5.1 seconds of silent video. The source image supplies starting-frame conditioning and a separate visual reference; its alpha mask is not connected, so transparency is not preserved. Camera choices include Static, directional pans, zooms and clockwise or counterclockwise rotation. Camera speed changes camera conditioning. Width and height use multiples of 16; frame count follows 1, 5, 9 and so on. These shape controls drive both camera and video conditioning. Playback FPS changes duration without changing the generated frame count. Static camera conditioning still permits subject motion described by the prompt. Camera controls condition generation rather than guaranteeing an exact rendered trajectory. In advanced settings, edit the negative prompt to describe unwanted results. Image guidance can be bypassed while keeping the uploaded image connected as the starting frame. Reference crop applies only to image guidance and has no effect when that stage is bypassed. Camera focal-length and optical-center controls are available in Camera and video shape; their source uses a 0–1 scale. Sampling controls include seed, steps, prompt guidance, sampler, scheduler, denoising amount and sampling shift. Seed -1 selects random noise; use a fixed nonnegative seed to reuse the initial noise with the same settings. Denoising amount is not a direct image-preservation slider. The saved sampling settings are 20 steps, CFG 6, uni_pc, simple scheduler, denoising amount 1 and shift 8. Video playback and export expose FPS, 8- or 10-bit depth, container, codec and CRF. Start with automatic container and codec and CRF -1. Some players or downstream tools may not support 10-bit video. Generation batch size controls latent batching, not separate exported files; the selected output assembles decoded images into one video, so use 1 for a single clip. This tool has no connected audio input and returns the video output rather than an animated WebP or individual frame export.
Grok video extension
Continue an existing video with a prompted 2–10 second extension using Grok. For a first run, upload an MP4 clip lasting 2–15 seconds, replace the example space-scene prompt with what should happen next in your footage, and keep the default six-second extension. Describe the action, setting, and camera movement that should follow the clip’s ending. Extension length requests 2–10 seconds in whole-second increments; it does not set the source clip’s length or total output length. The Pipe returns the video supplied by Grok, with no separate concatenation stage. Advanced output encoding controls offer file type, codec, and CRF settings; keep their defaults for a first run. The Grok partner API requires runtime authentication. Leave Seed at -1 for randomization on each run. Seed is a rerun control, and a fixed value does not make Grok’s results reproducible.
Whole-body pose map
Create a rendered whole-body pose map from an image of one person using SDPose. Upload your source image, leave the longer edge at 1024 pixels and all drawing regions enabled, then run to view the output image. The input is resized with its aspect ratio preserved before pose extraction. Choose whether to draw the body, hands, face, feet and head. Head drawing is separate from facial keypoints. Line width changes the skeleton's thickness; face point size applies when Draw face is enabled. The confidence threshold ranges from 0 to 1: raising it omits less-confident keypoints, while lowering it can display more uncertain detections. These controls affect the rendered map rather than pose extraction. Longer edge sets the resized image's longer dimension in pixels; use a positive value. Resampling method selects interpolation before detection. Area is suited to downscaling and Lanczos to upscaling. Advanced settings expose the extractor's processing batch size, defaulting to 16; this does not request multiple output variations. This tool uses the fixed sdpose_wholebody_fp16.safetensors checkpoint and returns a pose visualization through the image preview output, without a separate keypoint-data output. The extractor requires bounding boxes for multi-person detection, and this workflow supplies none, so use a single-person image.
Gemini Omni Flash text to video
Generate a 3–10 second video with audio using Google's Gemini Omni Flash model. The source node specifies 720p output at 24 FPS. For a first run, keep the example video prompt, portrait aspect ratio (9:16), three-second duration and default advanced settings, then run the Pipe. No image, video or audio upload is required. To create your own clip, describe the scene, action, visual style, camera movement and desired sound. Use 9:16 for portrait or 16:9 for landscape. Enter duration as 3s through 10s in whole-second increments. These controls append instructions to the scene prompt rather than cropping or trimming the result; avoid conflicting duration or framing instructions in your prompt. Advanced generation settings expose temperature and top-p sampling controls. Seed -1 randomizes the request seed each run. Seed affects whether the generation node reruns, but results remain non-deterministic even when a seed is repeated. Advanced video output settings expose file type, codec and CRF for output transport. Keep their defaults for the first run; these settings do not change the generation model or scene instructions. Generation requires access to the ComfyUI partner API. The workflow sends the assembled prompt to the Gemini provider and makes a provider-priced generation call. This Pipe uses text input only and returns the generated video; the model's separate text output is not selected.
Wan image to video
Animate an uploaded image into one video using Wan 2.5 or Wan 2.6, with optional generated audio. Upload the image you want to animate and replace the example prompt with instructions matching its subjects and setting. Describe the scene, subject motion, and camera movement in English or Chinese. For a first run, keep Wan 2.5, 720P, and 5 seconds. The result appears in Sweet Tea's video output. Choose 480P, 720P, or 1080P and a duration of 5, 10, or 15 seconds. A 15-second video requires Wan 2.6. The negative prompt describes elements to avoid and may be left blank. AI prompt extension is enabled by default and lets the provider enhance your instructions; disable it to submit your wording without that enhancement. Generated audio is enabled by default and can be turned off. This Pipe has no uploaded audio input. Watermarking is optional and disabled by default. Use seed -1 to randomize each run, or enter a fixed generation seed; identical provider results are not guaranteed. Advanced video output controls select the file type and codec. Leave both on auto for the first run and choose compatible settings when changing them. Uploaded transparency is not preserved: only the loader's RGB image output feeds generation. Generation sends the image and prompt to the Wan API and uses a provider-priced generation call.
Video frame interpolation
Add intermediate frames to an uploaded video for smoother playback or slow motion, returning one video at the source frame dimensions. For a first run, upload a source video, keep Frame multiplier at 2 and Keep original speed enabled, and use the default film_net_fp16.safetensors interpolation model. Leave the advanced bit depth and encoding settings at their defaults. With Keep original speed enabled, output FPS is the source FPS multiplied by Frame multiplier, giving smoother playback at approximately the original duration. Disable it to retain the source FPS and play the additional frames as slow motion. The multiplier supports integers from 2 to 16; larger values create more frames and increase processing work. Output FPS is calculated automatically, and there is no resizing control. The advanced Interpolation model control selects from the source loader's available runtime models. Models must be available in the runtime's frame_interpolation folder; the default is film_net_fp16.safetensors. Source audio is passed through unchanged. It is not slowed or stretched, so slow-motion output may have mismatched audio and video durations. Advanced controls select 8-bit or 10-bit video, the output container (Auto, MP4, MKV or WebM), and codec (Auto, H.264 or AV1). Start with 8-bit and automatic format and codec selection. The source describes 10-bit as reducing gradient banding, but some players and downstream tools may not support it. Explicit container and codec choices must be supported together by the runtime and your playback software.
Wan 2.1 Camera Motion
Animate an uploaded image into a silent video using Wan 2.1 Fun Camera 14B, a scene prompt and explicit camera-motion conditioning. For a first run, upload your source image, replace the example jazz-bar prompt with a description of its scene, subject action, lighting and style, and choose a camera movement. Keep camera speed and sampling settings at their defaults. The default output is 512 × 512 pixels with 81 frames at 16 FPS, approximately 5.1 seconds. Use dimensions in multiples of 16 and frame counts of 4n + 1, such as 49, 81 or 121. Available movements are Static, directional pans, zoom in or out, and clockwise or counterclockwise rotation. Camera speed is a relative conditioning parameter, not a physical speed. Align camera instructions in your prompt with the chosen movement. Static requests a stationary camera; subjects can still move. Generated motion is model-guided and does not guarantee a geometric reconstruction of the scene. Frames determines how many frames are generated. FPS sets playback rate: raising FPS shortens playback without adding frames. Width, height and frame count are supplied by Camera and output shape. The uploaded image supplies both the starting image and visual-reference conditioning and is required in this graph. Reference crop changes only visual-reference encoding. Uploaded transparency is not retained through the RGB image path. Advanced controls include negative prompt, seed, sampling steps, prompt guidance, sampler, scheduler, sampling shift and denoise. Use seed -1 for a new random seed each run, or a fixed seed when comparing changes. Denoise is a sampling-schedule fraction rather than a direct image-preservation strength. Optional normalized focal and principal-point parameters adjust camera intrinsics; retain their defaults initially. Keep batch size at 1 for one clip: this Pipe has one assembled video output rather than separate outputs for each latent sample. Video playback and encoding controls provide FPS, 8-bit or 10-bit video, container, codec and CRF. Retain automatic container and codec selection for the first run. Ten-bit output requires compatible encoding and playback support. CRF changes encoding quality rather than generated content. No audio is connected, so the output is silent.
Bernini-R: Video Edit
Generate an edited video with consistent relighting using Bernini-R. Ideal for portrait and product relighting, e-commerce catalog photography, and creating consistent lighting across photo sets.
Kling reference image to video
Generate one video from a reference image and a motion prompt. Upload one image, then replace the example prompt with the desired action, scene and camera movement. For a first run, keep kling-v3-omni, five seconds, 16:9 framing and 720p resolution. Generated audio is enabled by default. Choose landscape (16:9), portrait (9:16) or square (1:1) framing, a duration from 3 to 15 seconds, and 720p, 1080p or 4k resolution. The Model control also offers kling-video-o1; turn Generate audio off when selecting it because generated audio is supported only by kling-v3-omni. Execution uses the ComfyUI partner API, sends the reference image and prompt to Kling, and incurs provider charges. Model, duration, resolution and audio choices affect the charge. The image guides the subject and appearance; this Pipe has no separate first-frame or end-frame input. Include desired content and things to avoid in the same prompt. Storyboard mode remains disabled because this interface has no editable segment prompts or durations. Seed defaults to -1 for randomization. It controls provider re-execution rather than reproducibility: results remain non-deterministic with a fixed seed. The Pipe returns one video for preview. Advanced Video output settings provide file type and codec choices, both defaulting to automatic selection.
Qwen Image Edit 2511 · Material replacement
Create an edited image that changes an object's material using written instructions and an optional material reference. For a first run, upload a furniture photo as Source image and a fur texture as Material reference. In Edit instructions, write: "Replace the leather upholstery in image 1 with the fur material shown in image 2." Adapt the surface and material to your uploads. Leave Lightning mode off and keep the sampling defaults: 40 steps, CFG 4, Euler, simple scheduler and denoise 1. Run the Pipe to receive the edited image. Source image is required and is image 1 in the prompt. Material reference is image 2 and is enabled by default: upload it or explicitly bypass its node. To edit using a text description alone, bypass Material reference and describe the desired material directly without mentioning image 2. The source is automatically scaled before conditioning and latent encoding; there is no independent output-size control. Denoise ranges from 0 to 1: lower values retain more source structure but may weaken the material change. Seed -1 requests fresh randomness each run; use a fixed seed to compare edits with the same sampling settings. Lightning mode enables the four-step LoRA and selects separate defaults of 4 steps and CFG 1. Only the selected mode's steps and CFG apply. Lightning LoRA strength applies only when Lightning mode is on. Denoise, seed, sampler and scheduler are shared by both modes. The negative prompt describes details to discourage; at CFG 1, including Lightning's default, negative conditioning has no guidance effect. Advanced settings also expose guidance normalization, noise schedule shift and independent positive and negative reference-latent methods. Normalization and shift affect both modes. Normalize before CFG changes normalization from post-CFG attenuation to pre-CFG rescaling that can amplify guidance. Keep normalization strength 1, Normalize before CFG off, shift 3.1 and both reference methods at index_timestep_zero for the first run. This is a generative edit without a region mask, so other areas may change and material matching is not guaranteed. Uploaded transparency is not preserved by the connected RGB image path.
Flux 1.1 Pro Ultra image generator
Create a single image with Flux 1.1 Pro Ultra. For a first run, edit the prompt, choose an aspect ratio, and leave reference image guidance disabled. The default produces a square image without an uploaded input. To guide generation with an existing image, enable Reference image and upload an image. Reference strength controls its influence: higher values make the result closer to the reference. This setting has no effect while Reference image is disabled. Enable Raw mode for less processed, more natural-looking images. Prompt expansion lets the provider modify the prompt for more creative generation; with it enabled, the same seed will not produce exactly the same result. Seed defaults to a new random value each run. This workflow uses a hosted API node and requires configured API access and sufficient credits. Output size is controlled by aspect ratio; the source does not expose explicit pixel dimensions.
Boogu image edit
Create edited images from one uploaded reference and a natural language instruction. Upload your source image, enter the change you want and run with the defaults: 1 megapixel, one variant, 25 steps and instruction guidance (CFG) 3.5. “Remove the hat” is an example instruction; choose wording appropriate to your image. The negative prompt can describe unwanted details, or remain empty. Output size sets a target pixel budget in millions while retaining the source aspect ratio. Bypass Output size to derive dimensions from the source image instead. This stage controls output dimensions; the original upload still feeds editing conditioning. Resampling method affects only the image used to derive dimensions. Variants sets the number of edited images returned in a batch. Larger dimensions and batches require more memory. Advanced controls include guidance, seed, sampling steps, sampler and scheduler. Seed -1 selects fresh randomness each run; use a fixed seed when comparing settings with Add noise enabled. Leave Add noise enabled and Noise schedule fraction at 1 for a first run. The workflow starts from an empty latent conditioned on your image and instruction, so lowering the schedule fraction does not directly preserve source pixels. Schedule adjustment changes the sampling configuration used to calculate noise levels; the sampler itself receives the original model. This is a generative editor without a connected editing mask. Instructions to retain details do not guarantee that all other content stays unchanged. Uploaded transparency is not retained because only LoadImage’s IMAGE output is connected. The fixed model files are boogu_image_edit_fp8_scaled.safetensors, qwen3vl_8b_fp8_scaled.safetensors and ae.safetensors. Supplied dependency evidence marks all three model files and the Sweet Tea output node pack as missing in the inspected environment; their source locations are supplied. The selected result is the decoded edited-image batch returned through Sweet Tea’s image output.
Wan 2.7 video edit
Edit a source video using text instructions and two reference images, and return one edited video. Upload the video and both reference images. Reference image 1 connects to image1; reference image 2 connects to image2. Use those names in your instructions to explain how each reference should affect the edit. Both image uploads are required by this saved Pipe. For a first run with the default instructions, upload a clip of two people playing chess, a bear as reference image 1 and a dog as reference image 2. For other footage, rewrite the instructions to describe the changes and details to retain. Requests to preserve the scene or movement guide the model; they do not guarantee unchanged pixels or motion. Start with the defaults: 720P, 16:9 and duration auto. Choose 720P or 1080P and the aspect ratio for your intended output. Duration auto matches the input video duration; choosing 2–10 seconds truncates from the beginning of the source video. Audio mode auto lets the model decide whether to regenerate audio based on your instructions. Include desired sounds in the instructions when using auto. Choose origin to preserve the input audio; requests for new sounds should then not be expected to take effect. Seed -1 randomizes each run. A nonnegative seed controls generation variation. Enable Watermark to request the provider's AI-generated watermark. Under Video encoding, leave file type and codec on auto for automatic selection. Supported file types are mp4, mkv and webm; supported codecs are h264 and av1. This Pipe uses the Wan 2.7 partner API and requires configured provider access. Uploaded video, reference images and instructions are sent to the provider, and generation uses a provider-priced API call.
Gender Slider
Don't let the Model or Lora push a gender on you. Male, female, and every point in between. You decide. This isn't to push any agenda, just giving you the tools to get the image you want, despite the biases that...
Bad-Hands-5
Check my EXCLUSIVE models on Mage.Space : AniMage PXL • AniReal PXL • Lucid Dream • AniMage SD1.5 • Realistic Portrait SDXL - Pony : AniVerse PXL • AniMerge PXL • AniToon PXL • AniMics PXL • AniVerse XL SD1.5 :...
Bria: Remove image background
Remove an uploaded image’s background using Bria RMBG 2.0 and preview the resulting image in Sweet Tea. For a first run, upload your source image and run the Pipe with the default settings. No prompt or sampling setup is required. The workflow uses a ComfyUI partner API node and requires the corresponding authenticated service access. Advanced controls let you enable the provider’s moderation mode, which is disabled by default, and control provider re-runs with the re-run seed. Leave the seed at -1 to request a fresh run each time. The seed does not make results reproducible; provider results are non-deterministic. Existing uploaded transparency is not preserved through the source connection: only the loader’s image output is sent to Bria, and its separate alpha mask is not connected. The selected output returns an image preview rather than permanently saving an image through the workflow.
Bridal Style
This is a Style which brings out a beautiful bridal aesthetic. Simply call Style-Bridal in your prompt and your female characters will be ready for their wedding day!
