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
16 affiché of 42 312
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.
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.
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.
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.
Wan 2.6 Reference-to-video
Generate one video featuring two referenced characters using Wan 2.6. Upload one reference video for each character. Both uploads are required and feed the same generation stage. Describe your scene and motion in the scene prompt, using character1 and character2 to identify the corresponding uploaded characters. English and Chinese prompts are supported. You can describe desired dialogue and sound, but exact delivery is not guaranteed. For a first run, replace the example battle prompt with your scene and keep the default 720p landscape size and 5-second duration. Choose multi for multiple shots with cuts or single for one continuous shot, and write matching shot instructions in your prompt. Available durations are 5 and 10 seconds; keep the requested actions and shots practical for the chosen duration. Use the negative prompt for unwanted elements, or leave it empty. Output size selects resolution and aspect ratio together. AI watermark requests the provider's watermark. Seed -1 randomizes each run; a fixed seed controls generation randomization. Advanced video output settings select the file container and codec; leave both on auto for the first run. The result is returned to Sweet Tea as one video. This tool exposes no FPS control. Generation sends the references and prompt to the Wan provider and uses a paid provider call.
Reskin a sprite and remove its background
Reimagine a sprite using an object description and a style reference, then remove the generated background. Upload both required images: the sprite whose composition and outline should guide the result, and an image showing the desired visual style. Replace the example object description with what you want to render, such as “copper gas lamp.” Gemini receives the sprite as image 1 and the style reference as image 2. For a first run, keep the supplied model, square aspect ratio, 1K resolution and random seed (-1). The default prompt requests the sprite's composition and outline, applies your object description and the reference style, and asks for a black background. Recraft background removal always processes the generated image before the result is returned. Outline preservation is a request to the model, not a guarantee of exact geometry or pixel alignment. Uploaded transparency is not carried through the reference-image paths. Choose either supplied Gemini model to change the generation model. Aspect ratio offers auto and the listed fixed ratios; auto follows the input image's aspect ratio, while another ratio can change framing. Resolution offers 1K, 2K and 4K; 2K and 4K use Gemini's native upscaler. Use -1 for a new random seed each run, or a fixed seed to request repeatability. Identical results are not guaranteed. For custom instructions, edit the advanced composition and style prompt fragments. The prompt joins composition instructions, object description and style instructions in that order without an added separator; preserve spaces or punctuation at their boundaries. The system instructions control Gemini's interpretation of the request. Editing these instructions does not bypass background removal; this interface has no removal bypass.
