Ressourcenverzeichnis
Finden Sie, was Sie für Ihren Workflow benötigen.
Guides: techniques, setup, and troubleshootingDurchsuchen Sie Sweet Tea, Pipes, externe Workflows, Modelle, Knotenpakete und Anleitungen in einem faktenbasierten Katalog.
Beginnen Sie stattdessen mit einem Workflow ↗Suchergebnisse
Alle Ressourcen
20 angezeigt of 41.764
Topaz video enhancement
Enhance an uploaded video to 1080p or 4K, optionally add frame interpolation, and receive one processed video. For a first run, upload your source video and keep Starlight (Astra) Fast, FullHD (1080p), interpolation Disabled, and compression Low. Leave the advanced output settings at their defaults. Configured Comfy partner API access is required: the video is sent to the Topaz partner API for provider-priced processing. Choose an enhancement model and target resolution to enhance the video. Resolution applies only when enhancement is enabled. Select apo-8 to enable interpolation; choose Disabled for the enhancement model if you want interpolation alone. Keep at least one operation enabled. Model-specific creativity, scene prompts, sharpness, and realism controls are not exposed. Interpolation frame rate and slow-motion controls are also not exposed; these settings rely on the node's schema defaults. Compression level controls the Topaz CQP processing setting. Advanced video output controls separately select the final container, codec, and CRF encoding quality. Available containers are auto, mp4, mkv, and webm; available codecs are auto, h264, and av1. Choose compatible container and codec settings for your playback software.
Seedance first and last frame video
Generate a prompted video transition between two uploaded images, with optional audio on Seedance 1.5 Pro. Both first and last frame images are required. This Pipe sends the images and prompt to ByteDance Seedance through a paid provider call and returns one generated video to Sweet Tea. For a first run, upload both images, replace the capybara example prompt with motion, transformation, and camera instructions suited to them, and keep the default Seedance 1.5 Pro model, 720p resolution, adaptive aspect ratio, and five-second duration. The example describes six shots and six seconds of audio; adapt its scope and timing to your requested clip. Duration sets the requested length from 3 to 12 seconds in whole-second increments. Resolution offers 480p, 720p, and 1080p. Aspect ratio offers adaptive sizing or a fixed frame proportion. Consider both endpoint compositions when choosing a fixed ratio. Model selection offers Seedance 1.5 Pro, 1.0 Pro, and 1.0 Lite. Generate audio is enabled by default and applies only to Seedance 1.5 Pro; describe desired music, sounds, or ambience in the prompt. Other available models ignore that control. Fix camera adds a provider instruction for a stationary camera, but the effect is not guaranteed. Avoid conflicting camera movement instructions when enabling it. Seed -1 requests a new random seed each run; a fixed seed controls generation randomization. Watermark optionally requests an AI-generated label. The image inputs use RGB image data; uploaded transparency is not carried through this workflow. The output is returned through Sweet Tea's video preview transport rather than the original local SaveVideo stage.
Z-Image-Turbo: Text to image
Generate images from a text prompt with the fixed Z-Image-Turbo model. No uploaded image is required. For a first run, replace the example prompt with a description of your subject, composition, setting, lighting and visual style. Keep 1024 × 1024 pixels, one image and eight sampling steps, then run the tool to receive the generated image. The workflow uses z_image_turbo_bf16.safetensors, qwen_3_4b.safetensors and ae.safetensors; these model files must be available to the runtime. Set width and height together to choose the aspect ratio. Both dimensions must be multiples of 16. Image count generates a batch from the same prompt. Larger dimensions and batches increase memory use and runtime. In advanced sampling settings, seed -1 selects a new random seed on each run. Use a fixed seed to compare changes under the same configuration. The source defaults are eight steps, guidance scale 1, res_multistep sampler and simple scheduler. Sampler, scheduler, steps and sampling shift affect the sampling process and interact; sampling shift defaults to 3. More steps do not guarantee a better image. Denoise amount defaults to 1. This tool starts from an empty latent, so reducing denoise changes the sampling range rather than preserving an existing image. Negative conditioning is zeroed internally, with no editable negative prompt. The model, text encoder and VAE are fixed; this tool provides text-to-image generation and batch generation, with no image-to-image mode.
Flux Fill outpaint
Generate an expanded image with prompt-guided surroundings using Flux Fill. For a first run, upload the image to extend and replace the example scene prompt with a description of the complete scene, lighting, style, and surroundings you want to add. Keep the other defaults and run the Pipe. It returns one image. The default canvas adds 400 pixels on the left, right, and bottom, with no extension above. Choose each extension in pixels, in increments of 8. Set a side to zero to leave that edge unextended. The padded canvas width is the source width plus the left and right extensions; its height is the source height plus the top and bottom extensions. Boundary feathering sets the width in pixels of the soft mask transition into the original image near extended edges. Advanced controls include Flux guidance for prompt influence and the separate sampler CFG, which defaults to 1. Sampling defaults are 20 steps, Euler, the normal scheduler, and denoise 1. Denoise controls sampling strength; lower values retain more of the initial latent and may leave added regions insufficiently filled. Seed -1 chooses a new random variation each run; use a fixed seed when comparing settings. Use sampling mask is disabled by default. Enable it to restrict sampling using the padding mask and its feathered boundary. This mode can substantially change results and may not work well with the model. Differential mask strength controls differential diffusion's mask handling when masked sampling is enabled, from 0 for no effect to 1 for the full effect. There is no final compositing step that restores the original pixels, so the original area can change; masked sampling does not promise exact pixel preservation. The mask comes from canvas padding, not uploaded transparency. This Pipe does not accept a painted inpainting mask or preserve uploaded alpha. Negative conditioning is automatically zeroed, so there is no negative-prompt field.
HappyHorse text to video
Create one video from an English or Chinese scene description using the HappyHorse API. Describe the subject, action, setting, camera movement and visual style; no uploaded media is required. For a first run, keep the supplied horse scene or write your own prompt, then use the default HappyHorse 1.0 model, 5-second duration, 16:9 aspect ratio and 720P resolution. Match the amount of action in your prompt to the chosen duration. Run the Pipe to receive one video. Choose HappyHorse 1.0 or 1.1. Both expose durations of 3–15 whole seconds, 720P or 1080P resolution, and aspect ratios of 16:9, 9:16, 1:1, 4:3 or 3:4. Model, resolution and duration affect provider generation cost. Generation sends your prompt to the provider and uses a paid API call. Seed -1 randomizes each run. A fixed seed supplies a specific generation seed without guaranteeing identical provider results. Enable Watermark to request an AI-generated watermark on the result. Advanced Video output settings offer automatic container and codec selection or explicit MP4, MKV or WebM containers and H.264 or AV1 codecs. Keep File type and Codec on auto and Quality (CRF) at its supplied -1 default for the first run. These settings configure output encoding; they do not change the scene requested from HappyHorse.
7 Dirty Words negative prompt
This is a negative embedding trained on the output you get from entering George Carlin's "7 dirty words" in the positive prompt. It was trained mostly on output from various anime models, so it's likely to work...
Kling two-shot storyboard
Generate one Kling video containing two consecutive storyboard shots, with optional first-frame guidance and native audio. For a first run, replace both shot prompts with your subjects, action, setting and camera movement. Set each shot's duration in seconds; the defaults request two seconds followed by three seconds. Each prompt supports up to 512 characters, and each shot duration supports 1–15 seconds. These controls request the segments and their combined duration; the example prompts describe a boxing sequence. Upload a start image and leave Start image enabled for image-to-video generation. An upload is required while that stage is enabled. For text-to-video generation, bypass Start image; no upload is required. Aspect ratio offers landscape 16:9, portrait 9:16 or square 1:1 in text mode and is ignored when a start image is supplied. Kling V3 is selected by default and supports 720p, 1080p and 4k, with optional native audio. You can also choose Kling 3.0 Turbo, but select 720p or 1080p before running it. Turbo always generates native audio and ignores the audio toggle. This tool supplies exactly two storyboard segments; other segment counts and ordinary single-prompt generation are not configured here. Leave Seed at -1 for a fresh run. A fixed seed does not make the provider's output reproducible. Generation uses authenticated Kling API access, sends prompts and any supplied start image to the provider, and incurs provider charges. The result is returned as one video. Advanced Video output controls offer file type and codec selection; leave both at auto for automatic selection, or choose a compatible explicit combination.
Corneo's Marin Kitagawa TI Embedding
This is a Textual Inversion Embedding of Marin Kitagawa from My Dress-Up Darling (sono bisque doll wa koi wo suru).
Audio-guided human video
Generate one human-focused video from source audio and positive and negative prompts, optionally guided by a reference image. The uploaded audio supplies HuMo conditioning and is also included as the soundtrack. For a first run, upload the desired audio excerpt and describe the person, clothing, setting, framing, and action in Positive prompt. Retain or edit Negative prompt to specify unwanted visual features; its supplied default is in Chinese. Upload a reference image to guide appearance and composition, or bypass Reference image to use audio and prompts alone. The reference stage starts enabled, so explicitly bypass it when no image is supplied. Start with 640 × 640 pixels, 97 frames, 25 FPS, and latent batch size 1. The generated frames represent approximately 3.88 seconds of playback. Prepare an audio excerpt appropriate for that span before uploading: this interface provides no verified audio trimming or time-stretching controls. Width and height use multiples of 16. Frame count follows 1 plus a multiple of 4, such as 97, 101, or 105. Frame count controls the number of generated frames; frame rate controls their playback duration. Changing frame rate does not change audio encoding or stretch the soundtrack. Optional 10-bit video can retain smoother gradients, but downstream codec and player support varies; the default is 8-bit. Advanced sampling exposes seed, steps, CFG, sampler, scheduler, denoise fraction, and sampling shift. Seed -1 randomizes each run; a fixed seed reuses sampling noise. The supplied preset uses six steps, CFG 1, uni_pc, simple scheduling, denoise 1, and shift 8. The fixed Lightx2v step-distillation adapter starts at strength 1; its strength is not a dedicated motion control. Keep these settings initially. The model, text encoder, audio encoder, and VAE remain fixed. The result is one video with the uploaded audio, with automatic file type and codec by default. Advanced Video output settings expose container and codec choices. Larger latent batches still enter the same video assembly rather than producing separate clip outputs. There is no separate image or audio output.
SeedVR2 video restore and upscale
Restore and resize an uploaded video with the fixed SeedVR2 3B Int8 model. The default run processes the full clip at 2× its source width and height with one sampling step. No text prompt is required: conditioning comes from the video itself. The full clip or selected segment supplies the output frame rate, audio when present, and bit depth to video assembly; final encoding also depends on the output settings. For a first run, upload a short video and keep the defaults. Enable Trim video to process a segment. Start time and Duration are in seconds; Duration 0 continues to the end. Require full duration raises an error if the requested duration cannot be provided. Segment settings apply only when trimming is enabled. Scale factor changes both dimensions while preserving aspect ratio: 2 doubles width and height, 1 retains the source dimensions, and values below 1 reduce them. A factor of 2 produces approximately four times as many pixels per frame. Resampling method controls interpolation before restoration; the source recommends lanczos for upscaling, area for downscaling, and nearest-exact for pixel art. Color matching optionally brings restored colors closer to the resized source. lab transfers color in CIELAB space, wavelet transfers low-frequency color, adain matches global channel statistics, and none skips color transfer. Enable Temporal chunking to sample automatically sized latent chunks, then merge them before decoding. Chunk overlap is measured in latent frames, rather than seconds or source video frames; overlapping chunks are crossfaded during merging, while 0 uses plain concatenation. It applies only when chunking is enabled. Chunk sizing is automatic; manual chunk size is not available in this Pipe. Chunking addresses sampling memory, while VAE encoding and decoding have their own spatial tile and temporal window controls. Long clips and large output dimensions can still require substantial memory; use a shorter segment when needed. Denoise 1, one sampling step, CFG 1, euler, and simple are the source restoration defaults. Lower Denoise values change the sampling schedule and may reduce changes; test on a short segment. Other sampling settings depart from the source setup and are experimental. Seed -1 selects a new random seed each run; use a fixed seed when comparing settings. Video file type and Codec default to automatic selection. If choosing them explicitly, use a compatible container and codec supported by your intended player. Quality (CRF) -1 keeps automatic selection; lower nonnegative values request higher encoding quality and generally larger files, with the effective range depending on the codec.
Portrait lighting transfer
Generate a relit portrait or subject image with Qwen Image Edit and the Light Migration LoRA. For a first run, upload the required subject image and a lighting reference, keep the default relighting instruction, and leave Lightning mode off. Start with standard steps 20, standard CFG 4, Light Migration strength 1 and denoise 1. Run the Pipe to receive one edited image. Add subject details you want retained to the positive prompt; the negative prompt can remain blank. For text-directed lighting, bypass the Lighting reference stage and replace the default instruction with a direct description of the desired illumination and colors. Leaving the upload empty alone does not select this mode. The subject image remains required. Lightning mode adds the supplied Qwen Image Edit 2509 four-step Lightning LoRA and switches steps and CFG together. Its defaults are four steps and CFG 1. Standard steps and CFG have no effect while Lightning mode is on; Lightning steps, CFG and LoRA strength have no effect while it is off. Light Migration strength applies in both modes. The required model files must be available, including the four-step Lightning LoRA when using that mode. Denoise ranges from 0 to 1 and controls regeneration of the initial subject latent. Lower values retain more source structure but may weaken the lighting change. Light Migration strength controls the lighting LoRA's model influence, rather than an exact percentage of transferred lighting. Use seed -1 for a fresh random seed or a fixed seed to compare edits with otherwise unchanged settings. Advanced controls include separate steps and CFG for each mode, Lightning LoRA strength, sampler, scheduler, guidance normalization and sampling shift. The source sampler and scheduler defaults are Euler and Simple. Steps must be 1–10000 and CFG 0–100, matching the downstream sampler. Guidance normalization and sampling shift apply in both modes; normalization before CFG can amplify guidance. The subject is automatically scaled before generation, so output dimensions may differ from the upload. There is no independent output-size control. This is generative editing: identity, edges and fine details may change. Uploaded transparency is not preserved.
Style Rust Magic
This is a textual inversion that I made inspired by The Last of Us, created with Dream Artist on a single image that I generated. I was trying to do a post-apocalyptic feel. It adds a lot of gadgets, rusted...
Wan 2.2 5B video generation
Generate a silent video with Wan 2.2 5B from a scene and motion description, optionally using an uploaded image to condition the opening. For a first run, leave Source image bypassed and replace the positive prompt with your scene, subject movement, visual style, and camera movement. Keep the supplied negative prompt and default 1280 × 704 dimensions, 121 frames, 24 FPS, and 20 sampling steps. These settings produce approximately five seconds of video. Seed -1 selects fresh random noise each run; use a fixed seed when comparing changes. To animate an image, enable Source image and upload an opening image. Describe the desired movement and continuation in the positive prompt. The upload connects to the opening-image input, rather than supplying a video for editing. Uploaded transparency is not preserved through the connected RGB image path. Width and height are measured in pixels and use multiples of 32. Frame counts use 4n + 1, such as 49, 81, or 121. Increasing dimensions or frame count increases generation work. FPS controls playback speed: with a fixed frame count, increasing FPS shortens the video rather than generating additional frames. Keep batch size at 1 for one sequence; larger batches still feed one video output and do not provide separate video files. The negative prompt discourages unwanted content and artifacts. Advanced Sampling and Noise schedule controls change the denoising process; begin with their supplied defaults and denoise 1. Lower denoise is not a direct opening-image fidelity control. Use 8-bit video for broader playback compatibility. The 10-bit option requires compatible encoding and players. Advanced Video output controls select container, codec, and compression quality. Start with automatic file type and codec and quality -1; explicit encoding choices must be compatible. Encoding quality affects compression, not generated scene content. The output has no audio, even when the prompt describes music or sounds.
SCG Embedding Toolkit for Version 1.5 Models - A collection of tools and helpers from my personal kit
Over the last 6 months, I've created quite the collection of helper and tool embeds for doing things like fixing faces, pushing realism, creating anime scenes, making subjects smile, or cry, or face the camera,...
SoCalGuitarist Cinema768 Embeddings - Digital / Analog / Classic B&W - Easy movie scenes for 2.X Models!
These are another batch of high quality SD model 2.X embeddings that I am excited to release to the stable diffusion community! My new Cinema768 embeddings deliver easy cinematic lighting, color grading and...
bad_pictures
A very versatile negative embedding that helps generate high quality images. Higher chances of producing normal looking hands in realistic images.
Flux 2 Klein four-step text to image
Create images from a text description using the fixed distilled Flux 2 Klein 4B model. For a first run, replace the example Positive prompt with your subject, setting, composition, lighting and desired visual style. No uploaded image is required. Keep the source defaults: 1024 × 1024 pixels, one image, four steps, CFG 1 and Euler sampling. Run the Pipe to receive the generated image in Sweet Tea. Width and height set both the image canvas and the resolution used by the sampling schedule. Enter positive multiples of 16, at least 16 pixels. Together they determine the aspect ratio. Images per run generates a batch with the same prompt and dimensions; larger dimensions and batches require more memory. Seed -1 selects fresh random starting noise each run. Use a fixed nonnegative seed to compare changes with the same starting noise. Advanced controls expose steps, CFG and sampler. Steps set the sampling iteration count; additional steps add computation and do not guarantee better results. Keep four steps and Euler for the source setup. Changing the sampler can change results and interact with the step count. CFG adjusts positive conditioning relative to zeroed conditioning. Keep 1 for the source setup; higher values change that guidance. This branch has no editable negative prompt. This Pipe generates only the distilled-model branch's images. The separate Klein Base model with editable negative prompting belongs to the sibling tool and is not a selectable mode here. The runtime requires flux-2-klein-4b.safetensors in diffusion_models, qwen_3_4b.safetensors in text_encoders, and flux2-vae.safetensors in vae. These model dependencies are fixed. The output transport returns images to Sweet Tea without permanently saving them through ComfyUI.
Kling motion transfer
Animate a character image using movement and expressions from a reference video, returning one generated video. For a first run, upload a character image and a 3–10 second motion reference video. Keep Orientation source set to video, replace the example Scene prompt with your character, setting and desired details, then run the Pipe. With video orientation, movement, expressions, camera motion and character orientation follow the reference video; supported reference duration is 3–30 seconds. With image orientation, movement and expressions still follow the video, character orientation follows the image, and camera details come from your prompt; supported reference duration is 3–10 seconds. Keep reference audio determines whether the motion video's original sound is retained and is enabled by default. Generation mode offers pro and std, while Model version offers kling-v3 and kling-v2-6. Defaults are pro and kling-v3; the supplied source does not establish quality or performance differences between these choices. Advanced Video output settings let you choose a file type and codec; both default to automatic selection. The CRF encoding control defaults to -1, and its codec-dependent behavior is not documented in the supplied evidence. Generation uses the Kling provider and transfers the reference media for a provider-priced request. Uploaded image transparency is not preserved because only the loader's IMAGE output is connected.
Styled logo rotation
Generate a styled logo animation from a logo image and a material or matcap reference. The material reference is resized and padded to the logo's dimensions, then both images guide generation of a styled first frame. Gemini 2.5 Flash Image generates the last frame from that first frame, and Seedance animates between the two generated endpoints. For a first run, upload both required images and keep the default prompts and five-second duration. These request a studio-lit logo, a matching back view, and a 180-degree rotation. Prepare the logo's background before uploading: uploaded transparency is not carried through the connected RGB image inputs. In the styling prompt, image 1 is the logo and image 2 is the material reference. In the last-frame prompt, image 1 is the generated styled first frame. To change the movement, edit the last-frame and motion prompts together so the destination view agrees with the requested motion. Fixed camera adds a stationary-camera instruction; the default motion prompt also explicitly requests a static camera. If you want camera movement, disable Fixed camera and revise that prompt. First-frame model selects gemini-3-pro-image-preview or Nano Banana 2 (Gemini 3.1 Flash Image). First-frame shape and resolution govern the initial image; the last frame defaults to matching its shape. Video shape and resolution govern the final clip independently. Duration is 3–12 seconds. Generate audio applies only to the Seedance 1.5 Pro model. AI watermark requests a watermark from the video service. Reference preparation offers white or black padding and a resampling method. Video export offers container and codec choices; keep their Auto defaults for a first run. Both endpoint images are generated on every run; uploaded endpoint frames are not supported. Each generation stage has its own seed: -1 randomizes that stage. Fixing only the video seed does not fix the generated endpoints. Fixed Gemini seeds request best-effort repeatability rather than deterministic results. Geometry, lettering, material consistency, and camera stability are not guaranteed. The selected result is the video; model text responses are not connected to an output.
Color Palettes
Easy one-click color palette for your images. No need to argue with the AI if an orange is a color or a fruit, everything is setup for you automatically.
