Répertoire des ressources
Trouvez ce dont vous avez besoin pour votre flux de travail.
Guides: techniques, setup, and troubleshootingRecherchez Sweet Tea, Pipes, des flux de travail externes, des modèles, des packs de nœuds et des guides dans un catalogue unique lié aux preuves.
Commencez plutôt avec un flux de travail ↗Résultats de la recherche
Toutes les ressources
20 affiché of 41 716
Wan text to video
Generate a short video from an English or Chinese text prompt using Wan 2.5 or Wan 2.6, with optional generated audio. For a first run, keep the supplied detective scene, Wan 2.5 preview, 1080p landscape, and a 5-second duration, then run the Pipe. Replace the prompt to describe your subjects, setting, action, visual style, and camera movement. Audio generation and AI prompt enhancement are enabled by default. Choose Output size for resolution and aspect ratio. Use 5 or 10 seconds with Wan 2.5; select Wan 2.6 for 15 seconds. The negative prompt describes unwanted elements. Disable Enhance prompt to submit your wording without AI expansion, or disable Generate audio when you do not want automatic audio generation. Seed -1 randomizes each run; a fixed nonnegative seed controls generation randomness. Watermark requests an AI-generated watermark on the result. This Pipe accepts text only and has no connected soundtrack or voice-recording input. Generation uses a partner API and requires configured access and sufficient credits. Sweet Tea delivers the generated video. Under Video encoding, leave File type and Codec on Auto for the supplied encoding behavior, or select an available format and codec.
DALL·E 2 image creation and editing
Create one to eight square images with DALL·E 2. Write a prompt describing the desired result, choose an output size, and set the image count. Source image is enabled by default. Upload an image to edit; its RGB image and alpha-derived mask both feed the provider. Transparent regions supply the replacement mask, whose white areas are edited. This interface has no separate mask upload and does not promise transparent output. For a first text-only run, disable Source image, replace the example prompt, and generate one image at 1024×1024. Disabling Source image removes both image and mask conditioning while leaving generation active. The workflow uses a partner API node and requires an authenticated runtime with sufficient API credits. Seed is retained as a hidden runtime field because the provider documents it as unimplemented; it cannot reliably reproduce results.
Wan 2.1 image-to-video with optional end frame
Generate a silent video from a starting image and a text prompt using Wan 2.1 Fun InP 1.3B, optionally guiding the ending with a second image. For a first run, upload a start image and replace the example positive prompt with a description of your subject, scene, movement, and camera behavior. End frame is enabled by default: either upload an end image or bypass End frame to use the start image alone. The start image remains required in both modes because it also supplies visual conditioning. Images guide generation; an exact transition or exact endpoint match is not guaranteed. Begin with the supplied 480 × 768 dimensions, 81 frames, 16 playback FPS, and 20 sampling steps. This gives approximately 5.1 seconds of video. Width and height are pixels in multiples of 16; frame counts follow 4n + 1, such as 49, 81, or 121. Choose an input aspect ratio close to the output dimensions. Larger dimensions and more frames increase processing and memory requirements. FPS sets playback speed without adding or interpolating frames; duration is frame count divided by FPS. Keep Batch size at 1 initially: larger batches do not have separate clip output paths. The negative prompt describes unwanted appearance and motion; the supplied Chinese text discourages artifacts, poor anatomy, static imagery, and clutter. In Sampling, seed -1 chooses fresh random noise for each run; use a fixed seed to compare settings. Keep the supplied sampler, scheduler, guidance scale, and denoise fraction initially. Denoise is not a direct start-image preservation strength. Reference crop affects visual conditioning from the start image, independently of output dimensions. Skip-layer guidance is enabled by default and can be bypassed for comparison; its strength, start/end fractions, rescaling, and layer selections apply only when enabled. Noise schedule shift and the independent attention multipliers expose additional model tuning. Their effects are separate from playback timing; retain the packaged settings for the first run. Video playback also offers 8-bit or 10-bit depth. The supplied 8-bit setting favors compatibility; 10-bit supports smoother gradients but may be unsupported by some players or downstream tools. The output controls offer automatic encoding or an explicit file type (MP4, MKV, WebM) and codec (H.264, AV1). Automatic format and codec are the defaults. No audio input is connected, so the result is silent.
FLUX.1 Schnell text to image
Create images from text using the fixed FLUX.1 Schnell FP8 checkpoint. No source image is required. The runtime needs flux1-schnell-fp8.safetensors in its checkpoints directory. For a first run, replace the example prompt with your subject, setting and visual style. Keep 1024 × 1024 pixels, one image, four steps, CFG 1, Euler sampler, simple scheduler and denoise strength 1. Run the tool to receive the generated image batch through Sweet Tea's preview output; this graph does not permanently save files with SaveImage. Width and height must be multiples of 16. Adjust them together to choose the aspect ratio. Image count determines the number of images returned per run. Larger dimensions and batches require more memory. Seed -1 chooses fresh noise each run; a fixed seed lets you compare changes with the same starting noise. Advanced sampling controls expose steps, CFG, sampler, scheduler and denoise strength. Start with the source defaults. The optional negative prompt feeds negative conditioning but has no effect at CFG 1. Raising CFG allows that conditioning to influence sampling and is not a guaranteed improvement for this Schnell setup. This tool starts from an empty latent and supports text-to-image generation only. Lower denoise strength changes sampling of that empty latent; it does not provide image editing. The checkpoint is fixed, with no model-selection or source-image mode.
SDXL text to image with refinement
Generate one image or a batch from text using SDXL 1.0 Base followed by SDXL 1.0 Refiner. No source image is required. The fixed checkpoints sd_xl_base_1.0.safetensors and sd_xl_refiner_1.0.safetensors must be available to the runtime. For a first run, describe your scene in Positive prompt and copy that description into Refiner positive prompt. Enter unwanted features in both negative prompts, then run with the default 1024 × 1024 dimensions and Image count of 1. All four prompt fields are independent: editing a base prompt does not update its refiner counterpart. Keep their intent aligned, or deliberately change the refiner wording to emphasize finishing details. Width and Height are in pixels and use multiples of 8. Image count generates a batch using the same prompts. Larger dimensions and batches require more memory. In advanced settings, Seed controls the initial base noise: -1 selects a new seed each run, while a fixed seed lets you compare changes using the same initial noise. Guidance and sampler choices are independent for Base and Refiner. The default schedule has 25 total steps: Base performs the first 20, passes its partially denoised latent onward, and Refiner completes the remaining five without adding fresh noise. Refinement is integral to this output path and cannot be bypassed through this interface. Advanced schedule controls must be adjusted together. Keep Base schedule steps equal to Refiner schedule steps, use matching schedulers, and set Base handoff step equal to Refiner handoff step below the total schedule length. The schedule-step fields describe the full schedule for each stage, not how many steps that stage executes. Begin with the coordinated defaults before changing the schedule.
ACE Step 1.5 music generator
Describe the genre, instrumentation, vocals, and arrangement, then provide lyrics and musical settings. The saved example is a two-minute K-pop song. Output duration sets the audio length; conditioning duration separately tells the music encoder the intended length, so keep both values equal for ordinary use. Music seed controls conditioning variation, while Seed controls diffusion noise. Negative conditioning is automatically zeroed and has no separate negative prompt. The fixed Turbo model uses eight sampling steps by default and exports MP3 audio.
SAM3 object segmentation
Find objects by name in an uploaded image and return detection masks plus a companion image with detection-derived transparency. For a first run, upload an image, enter a short object description such as "guitar", and keep the detection threshold at 0.5, refinement passes at 2, and separate object masks disabled. The prompt selects objects in the source image; it does not generate new image content. Use a compatible SAM3 checkpoint installed in the runtime; the default is sam3.1_multiplex_fp16.safetensors. Keep prompts within the model's 32-token limit. Separate subjects with commas; append :N to limit detections for a subject, for example "eye:2, window panels:4". Raise the detection threshold to reject weaker matches, or lower it to include weaker matches. Refinement passes range from 0 to 5; zero uses raw detector masks, while additional passes apply SAM decoder refinement. By default, detections share one combined mask. Enable separate object masks for per-object results; output count then depends on detections. The companion image joins the original RGB image with the detection masks using ComfyUI's mask-to-alpha convention: detected regions become transparent. Uploaded transparency is unused, so this output does not preserve the source alpha or provide an isolated opaque object cutout. In the advanced Model section, choose a compatible SAM3 checkpoint from the runtime checkpoint selector. Other installed checkpoints may appear, but ordinary image-generation models are unsuitable. This graph supports text prompting; point prompts and bounding-box inputs are not connected.
Sonilo music generator
Generate music from a text description and save one MP3 with Sonilo. For a first run, keep the supplied ethereal, gentle music prompt, the 60-second duration and the default V0 MP3 quality, then run the Pipe. No media upload is required. To create another track, describe its musical style, instruments, mood and atmosphere in Music prompt, and set Duration from 1 to 360 seconds. Duration is a target rather than a guarantee of exact track length. Under advanced Audio quality, choose V0 variable bitrate or a fixed bitrate of 128k or 320k. This changes the saved MP3 encoding; the output format remains MP3. Generation sends your prompt to the Sonilo service and uses a provider-priced API call. Sonilo currently ignores the hidden seed, so repeated runs are not guaranteed to reproduce the same music.
Seedance text to video
Generate one video from a description of the scene, subject action and camera movement through the Seedance API. No source image is required. For a first run, use the supplied skier prompt or replace it with your own scene. Keep the default Seedance 1.0 Pro model, 720p resolution, 16:9 framing and five-second duration, then run the tool to receive the video. Choose aspect ratio, resolution and duration to shape the output. Duration is specified in whole seconds from 3 to 12. Fixed camera adds a stationary-camera instruction to the prompt but does not guarantee the effect; avoid requesting camera movement when it is enabled. For generated audio, select seedance-1-5-pro-251215 and enable Generate audio. Other listed models ignore that setting. The default model generates without audio. AI watermark requests the provider's “AI generated” watermark. Seed -1 selects a new random seed on each run; a fixed seed controls generation randomization. The advanced Video output section offers file type, codec and quality (CRF) controls. Leave their defaults for automatic output encoding. These settings affect the delivered video encoding, while the generation controls determine its content. This workflow requires an authenticated ComfyUI partner API account with sufficient credits. Generation sends the prompt and generation settings to the provider and uses a paid API call.
LTX image to video
Animate an uploaded starting image into a short, silent video using LTX-Video 2B v0.9.5. For a first run, upload an image and replace the fox example in the positive prompt with a description of your subject, intended movement and camera behavior. Keep the default 768 × 512 dimensions, 97 frames, image strength 0.15, 30 sampling steps, CFG 3 and Euler sampler. At 24 FPS playback, the returned clip lasts about 4.04 seconds. Leave batch size at 1 and output container, codec and CRF at their source defaults. Width and height use multiples of 32 with a minimum of 64 pixels. Frame counts are 9, 17, 25 and so on in increments of 8. Image strength controls starting-image conditioning. The negative prompt describes unwanted visual or motion characteristics. Larger dimensions and frame counts increase processing and memory requirements. Playback FPS changes how quickly the generated frames play and sets duration without adding frames. Conditioning FPS supplies a separate frame-rate cue during generation. Their source defaults are 24 and 25 FPS respectively; set them equal when you want the two settings aligned. Sampling controls include text guidance, initial noise, seed, steps, algorithm and the LTX schedule's base and maximum shifts. Keep their defaults for a first run. Seed -1 requests fresh sampling noise each run; use a fixed seed to compare changes with the same initial noise. Disabling initial noise removes that seed's effect on initial noise selection. Video playback settings offer 8-bit or 10-bit output. The source describes 10-bit as retaining smoother gradients, but player and encoder support varies. Video output settings select automatic encoding or an explicit MP4, MKV or WebM container and H.264 or AV1 codec. Use compatible container and codec choices; CRF interpretation depends on the codec. This graph returns one assembled video. Increasing latent batch size does not create separate video outputs. Only the image loader's IMAGE output is connected; its alpha mask is unused, so uploaded transparency is not preserved. There is no audio input or separate end-frame control.
LTX-2.3 image to video with audio
Animate a source image into one video with generated audio. Upload an image and replace the example prompt with directions for the scene, action, camera movement, dialogue and sounds. The tool generates video and audio together, performs fixed 2× spatial upscaling on the video latent, then refines both streams before returning the video with its soundtrack. For a first run, keep the requested 1280 × 720 size, nominal 5-second duration and 25 FPS. Leave Text-to-video mode and prompt enhancement disabled, and keep the sampling and encoding defaults. The image is center-cropped to the requested aspect ratio; Image fit can instead stretch it. It is then resized to a fixed 1,536-pixel longer edge and compressed before image conditioning. Uploaded alpha is not used as a transparency channel. Width and height also determine the initial half-resolution generation size. Use positive dimensions and duration, and a whole-number frame rate from 1 to 120. Requested frame count is duration × FPS + 1; keep this at or below the audio stage's 1,000-frame limit. Model alignment can affect actual dimensions and duration, so these settings are requests rather than exact output trimming. Image strength controls initial source-image conditioning. Refinement image strength separately controls conditioning reapplied after upscaling. Text-to-video mode bypasses both conditioning stages, so neither strength affects that mode. An uploaded image is still required because its processing path remains connected. If prompt enhancement is enabled, the image can still influence the expanded prompt in Text-to-video mode. Prompt enhancement expands your instructions before video prompt encoding. Leave it disabled to use your written prompt directly. Enhancement tuning and its text LoRA strength apply to expansion; temperature, token filters, penalties and the enhancement seed belong to sampled text generation. Thinking mode only applies if supported by the loaded text model. Initial generation and refinement have independent seeds, CFG guidance, samplers and noise schedules. Use -1 for randomized seeds; fix both generation seeds when comparing settings, and also fix the enhancement seed if using sampled expansion. Negative-prompt influence depends on each stage's CFG and can be limited at the default of 1. Keep the distilled LoRA strength and manual schedules at their supplied values for the first run. Advanced output settings choose bit depth, container, codec and CRF. Start with 8-bit assembly, automatic container and codec selection, and CRF -1. Explicit encoding choices must be compatible with each other and your player; 10-bit output can have compatibility limitations. Audio is generated from the prompt rather than supplied through an audio upload. The model, text encoder, audio decoder and spatial upscaler are fixed parts of this tool.
Wan 2.6 image to video
Animate a source image into a short Wan 2.6 video, with optional automatically generated audio. For a first run, upload the required source image and replace the sample car prompt with motion, camera movement, and visual style suited to your image. Prompts support English and Chinese. Adjust the car-specific negative prompt to describe unwanted features for your subject. Start with the default 720P resolution and 5-second duration, then run the Pipe to receive the video in Sweet Tea. Resolution choices are 480P, 720P, and 1080P. Duration choices are 5, 10, and 15 seconds. References to 4K and 60fps in the sample prompt are creative text, not output settings; this Pipe has no FPS control. Prompt enhancement is enabled by default and allows AI assistance to expand your prompt. Shot type selects single for one continuous shot or multi for multiple shots with cuts; this choice only takes effect while prompt enhancement is enabled. Generated audio is enabled by default. Turn it off when you do not want automatic audio. This Pipe does not accept an uploaded audio track. Seed -1 selects a fresh random seed each run; a nonnegative seed controls generation randomization. Watermark enables the provider's AI-generated watermark. Advanced video output settings let you choose file type and codec; both default to auto. Generation runs through the Wan partner API using the fixed wan2.6-i2v model. The source image uses LoadImage's RGB image output; uploaded transparency is not retained.
Negative Embedding for Deliberate
A negative prompt embedding for Deliberate V2. Use in your negative prompt to make the image look better. Do not use as a regular prompt.
Luma UNI-1 image edit
Edit an uploaded image with written instructions using Luma UNI-1. Upload a source image, replace the example grassland instruction with your desired changes, and describe any subjects or details you want to keep. For a first run, leave Model at uni-1-max, Style at auto and Web references off. Run the Pipe to receive an edited image preview. Choose uni-1 or uni-1-max as the editing model. Edit instructions must contain 1–6000 characters. Auto style follows your prompt. Manga applies a manga/anime aesthetic and requires a portrait aspect ratio of 2:3, 9:16, 1:2 or 1:3. There is no separate aspect-ratio control, so prepare a suitable portrait source before choosing manga. Enable Web references to let Luma search the web for visual references before generating. Leave Seed at -1 to randomize on each run. Seed controls re-execution, not reproducibility: even a fixed seed does not reproduce the same image. This Pipe sends the source image and editing request to the Luma partner API, requires configured provider access and uses provider-priced generation. It supplies one source image, with no additional reference-image or mask input. Uploaded alpha transparency is not preserved by the connected image path.
Nano Banana 2: Image edit
Edit one uploaded source image with written instructions using Nano Banana 2. Describe the changes you want and the details that should stay unchanged. For a first run, upload your image, replace the example instructions with edits suited to it, and keep aspect ratio at auto and resolution at 1K. Auto matches the source image's aspect ratio; select a specific ratio to request a different composition. The standard Nano Banana 2 model supports 1K, 2K and 4K output targets. Nano Banana 2 Lite supports only 1K, so set resolution to 1K before switching to Lite. Thinking level offers MINIMAL and HIGH. Temperature controls generation randomness, and nucleus sampling controls the breadth of sampling choices. Keep their existing defaults for a first run. Seed -1 randomizes each run; a fixed seed requests best-effort consistency, but identical results are not guaranteed, especially when other settings change. System instructions guide how the model interprets your request; the default directs it to produce an image. IMAGE requests image-only generation, while IMAGE+TEXT allows accompanying text. This Pipe delivers only the final image in either mode; generated text and intermediate thinking images are not connected to the output. The source loader supplies RGB image data without its alpha mask, so uploaded transparency is not preserved. Instructions to retain details express the desired edit rather than guaranteeing that those details remain identical.
Yoruichi Shihouin (Bleach) TI Embedding by Corneo
This is a textual inversion embedding for Yoruichi Shihouin from Bleach. Use corneoyoruichi to activate.
Recraft creative upscale
Upload an image to produce a Recraft creative upscale result. For your first run, choose a source image no larger than 5 MB, with width and height each no greater than 2048 pixels, then run the Pipe. The resulting image appears in Sweet Tea's output viewer; this workflow does not permanently save it through a SaveImage node. The image is sent to Recraft for a provider-priced upscale operation. This Pipe offers no prompt, scale factor, tuning controls or alternate modes. Uploaded transparency is not preserved because only the loader's RGB image output is connected.
Yor Forger - Thorn Princess version - TI Embedding by Corneo
This is a textual inversion embedding for Yor Forger / Yor Briar from Spy x Family in her Thorn Princess assassin outfit.
pony_negative for PianoMix
Even if you don't specify all the troublesome prompts, you can get a certain result by specifying one negative prompt.
Lens Text to Image
Create one image or a batch from a text prompt using the fixed Lens model, Lens text encoder, and Flux 2 VAE. No uploaded image is required. For a first run, describe your subject, composition, lighting, and style in Positive prompt, or use the supplied flower example. Leave Negative prompt empty unless you have specific exclusions. Keep the square, 2-megapixel output and supplied sampling defaults: 20 steps, CFG 5, Euler, and the simple schedule. Seed -1 chooses fresh starting noise on each run; use a nonnegative seed to select a fixed starting noise pattern. Increase Image count to generate multiple images together. Aspect ratio and Target megapixels jointly determine the output dimensions. Dimensions are aligned to multiples of eight and shared by the latent canvas and model sampling setup. Megapixels is an approximate pixel budget rather than a fixed width or height. Larger sizes and batches require more memory. CFG controls prompt guidance, including the influence of negative conditioning. Advanced controls select the sampling algorithm, distribute noise levels across the requested steps, and adjust CFG normalization and resolution-dependent sampling shifts. Pre-CFG normalization applies normalization before CFG combination without clamping and can amplify predictions; the default post-CFG mode only attenuates them. Base shift and Maximum shift work together with the selected output dimensions. Leave Add noise enabled and Denoise at 1 for ordinary text-to-image generation. Lower Denoise uses a shortened noise schedule on an empty latent canvas; it does not preserve or transform an existing image. Disabling Add noise removes the seeded starting-noise initialization, so the seed no longer controls that initialization. All generated images are returned through one batch image output using Sweet Tea's output transport. The workflow does not permanently save images through the original SaveImage node. The model stack and dimension plumbing are fixed; this Pipe does not accept an input image.
