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
19 affiché of 41 754
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.
Image restyle round-trip video
Create one silent round-trip video from an uploaded image and a description of its transformed appearance. Gemini generates the restyled image and separate motion prompts; Wan 2.2 generates the outward and return segments, which are concatenated in that order. First run: upload a source image, replace the Restyle prompt with the appearance you want, and leave the remaining defaults. The supplied prompt requests a back-facing anime illustration. With batch sizes of 1, the default 81 outward frames plus 81 return frames produce 162 frames, or 6.75 seconds at 24 FPS. The video size starts at a 1-megapixel source-image budget and follows that image's aspect ratio. Adjust the two frame counts independently using their supported increments of four from 1. Playback FPS changes how quickly the generated frames play; it does not generate more frames. Restyle aspect ratio affects the Gemini image, while Restyled image megapixels controls its separate resize budget. Neither sets the final video dimensions. For motion or camera changes, edit the advanced motion instructions. These tell Gemini how to write each segment's positive prompt. The comparison image always has the original on the left and the restyled image on the right: outward instructions should describe left to right, and return instructions right to left. Retain the request for prompt-only text. Negative prompts apply separately to each video segment. Image generation, each motion-prompt response, and each video segment have independent seeds. -1 randomizes. Fixed Gemini seeds request repeatability but do not guarantee identical responses. Holding a video seed steady alone does not hold the generated image or motion text steady. Keep batch sizes at 1 for one round trip. Larger batches feed all outward frames followed by all return frames into the same video; they do not create separate paired exports. The return segment is newly generated, not a reversed copy. Endpoint frames are not explicitly removed at the segment join or loop boundary, so a seamless loop is not guaranteed. Uploaded alpha transparency is not preserved, and no audio is connected. The source uses fixed high- and low-noise Wan 2.2 models with Lightx2v four-step LoRAs. Advanced sampling controls remain available independently. For the first run, retain the coordinated defaults: both stages use a four-step schedule, CFG 1, Euler/Simple, shift 5, and LoRA strength 1; initial sampling stops at step 2 and refinement resumes at step 2 without new noise. These controls form a coordinated setup rather than independent quality presets. Leave output container, codec, and compression quality on Auto initially. Final 10-bit output is optional, but both intermediate segment videos are fixed at 8-bit, so it cannot restore precision lost upstream and may have player compatibility limitations.
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.
PonyScores
Embedding created by merging score tokens " score9, score8up, score7up, score6up, score5up, score4up " for Pony based models.
Style Asian Less
This tool doesn't specifically race-swap asian to white-caucasian, it just removes asian so your prompts can be more effective with whatever other race or culture you're trying to portray. This is due mostly to heavy...
PixelDiT image generator
Generate one image from text using the fixed PixelDiT 1300M model, Gemma text encoder, and pixel-space decoding. No source image is required. For a first run, replace the positive prompt with your subject, setting, composition, lighting, and desired appearance. Keep or edit the prefilled negative prompt to describe features to discourage. Start with the square, 1-megapixel default and the supplied sampling settings: 30 steps, CFG 4, er_sde sampler, simple scheduler, and denoise 1. Run the Pipe to obtain the generated image. Aspect ratio sets the image shape; megapixels sets the approximate total pixel count in millions. Width and height are calculated together. A square image at 1 MP is approximately 1024 × 1024. Prompt text such as “8k” does not set actual output resolution. Larger images require more resources. Advanced sampling controls include seed, steps, CFG, sampler, scheduler, and denoise. Seed -1 requests fresh randomization on each run; a fixed nonnegative seed reuses the noise initialization. Steps set the sampling step count. CFG controls prompt guidance; excessive values can harm the result. Sampler selects the sampling algorithm, while scheduler sets the progression of noise levels. Changing these controls can change the generated appearance. Keep denoise at 1 for full generation from the empty latent. Lower values sample a shorter noise range. This is text-to-image generation: there is no uploaded image to edit or preserve. Image count is fixed at one, and model selection is fixed. The execution environment needs pixeldit_1300m_1024px_bf16.safetensors, gemma_2_2b_it_elm_bf16.safetensors, and the Sweet Tea output nodes.
Recraft Crisp Upscale
Upload a source image and run to receive the Recraft Crisp Upscale result. Prepare a file no larger than 5 MB, with width and height each no larger than 2048 pixels, as specified by the source template. This tool has one fixed upscaling mode and exposes no prompt, scale factor or enhancement settings. Uploaded transparency is not preserved because only the image loader's RGB output reaches the upscaler. The image is sent to Recraft for processing through a paid provider call.
Not Just Another Pretty Face
Any resemblance to actual persons, living or dead, is purely coincidental. This work is a product of fiction and any similarities to real individuals are entirely unintentional.
WanMove motion-guided image to video
Create a motion-guided video from an uploaded image, a scene-and-action prompt, and editable motion paths. For a first run, upload an image and replace the skiing example prompt with a description of its scene and desired action. Set path 1's start and end positions to guide the intended movement. Review paths 2 and 3 in Advanced: both are enabled by default, and each can be bypassed independently if unnecessary. Keep the initial 832 × 480 size, 81 frames and 16 FPS for an approximately five-second clip, and leave Turbo off to use the standard settings. The image is resized with Lanczos and center-cropped by default. The resized image supplies the start image and optional visual-reference encoding; its dimensions determine the video size. Use positive multiples of 16 when changing width or height. Uploaded transparency is not used, and the selected output has no connected audio. Each path creates a bundle of tracks. X runs from left (0) to right (1), and Y from top (0) to bottom (1) on that path's canvas. Curved path enables a Bezier control point defined by Curve X and Curve Y; the control point shapes the curve rather than specifying a required waypoint. Motion timing controls progression along the path. Track count sets the number of tracks, and Track spread sets their normalized spacing perpendicular to movement. Motion strength controls track-conditioning influence; paths guide generation rather than guaranteeing exact object trajectories. Video frame count and each path's frame count are independent. When changing length, update every enabled path to match. Video lengths follow 1 plus a multiple of 4, while path generators support at most 1024 frames. Frame rate changes playback duration, not the number of generated frames. Track canvases retain the source's 720 × 480 defaults, which differ from the 832 × 480 output. Canvas dimensions are independent controls: keep enabled path canvases consistent, and do not assume that changing output size updates them. Turbo mode selects the fixed Lightx2v LoRA together with its separate sampling settings. Standard defaults are 20 steps and CFG 6; Turbo defaults are 6 steps and CFG 1. LoRA strength affects only Turbo generation. The negative prompt applies in both modes; its supplied Chinese text lists unwanted artifacts and traits. Seed -1 randomizes the seed; use a fixed nonnegative seed to reuse it with otherwise matching settings. Sampler, scheduler, denoise and sampling shift remain available in Advanced. Keep Generation batch size at 1 for a single clip: the selected output assembles decoded images into one video rather than delivering separate files. Visual reference can be bypassed without removing the start image. Its center/none crop setting affects visual encoding and is separate from resize crop. Video encoding offers container, codec and CRF controls; auto container/codec and CRF -1 retain transport defaults. Bit depth defaults to 8; 10-bit may lack player support. The selected output is the generated video, without the source's disabled track-visualization diagnostic. The workflow uses fixed WanMove diffusion, UMT5 text-encoder, Wan 2.1 VAE, CLIP vision and Lightx2v LoRA assets identified in the source metadata. Those assets must be available to the runtime; this review does not establish execution results or generation speed.
Gemini image refinement and generation
Refine or edit an uploaded image with Gemini, or generate an image from a prompt, at a target resolution of 1K, 2K or 4K. For a first refinement run, upload a Source image, leave that stage enabled, and use the default prompt and 4K resolution. The prompt requests detail refinement while preserving text and composition. Replace it with specific editing instructions and describe what should remain unchanged. For text-only generation, bypass Source image and replace the editing prompt with a description of the image you want. Auto aspect ratio follows the reference image when supplied; choose an explicit ratio to specify the proportions when generating without a reference. Resolution selects the target output size; the source describes 2K and 4K as using Gemini's native upscaler. Model selects Gemini 3 Pro Image or Nano Banana 2 (Gemini 3.1 Flash Image). Seed -1 randomizes each run; a fixed seed requests best-effort repeatability, without guaranteeing identical results. System instructions set foundational behavior and default to prioritizing image creation. Response format requests IMAGE or IMAGE+TEXT, but this Pipe exposes only the generated image. Refinement is generative: text, textures and composition can change despite preservation instructions. Uploaded transparency is not preserved by the connected RGB image path. The generated image is returned through Sweet Tea's preview transport rather than a permanent SaveImage stage. Prompts and any reference image are sent to Gemini through a paid provider call.
Replace video background
Replace a video's background with a supplied image using Bria and receive one processed video. For a first run, upload the foreground video under Source video and a replacement image under Background image. Keep Background image enabled and leave File type and Codec on Auto, then run the Pipe. Background image is optional and bypassable. Bypassing it omits the replacement image; the supplied provider definition does not specify the resulting appearance. This Pipe has no replacement background video input. Uploaded image transparency is not carried through the connected RGB image output. Under Background replacement, Seed defaults to -1 to randomize on each run. Seed controls provider re-execution; results remain non-deterministic even with a fixed seed. Under Video output, File type offers Auto, MP4, MKV and WebM; Codec offers Auto, H.264 and AV1. Keep Auto for a first run, or choose a compatible container and codec together. The preserved hidden CRF control lacks documented semantics in the supplied evidence.
