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
19 angezeigt of 42.599
HappyHorse video edit
Edit a source video with text instructions and a reference image using HappyHorse 1.0, and return one edited video. For a first run, upload a 3–15 second source clip and a reference image. Adapt the example instruction to identify the subject in your clip and explain how the reference should be used. The instructions also support appearance changes or style transfer. Both uploads are required in this Pipe. Choose 720P or 1080P and the desired aspect ratio. The provider describes output duration as 3–15 seconds, matching the input within that range; clips longer than 15 seconds are truncated. This Pipe has no duration or FPS control. Use seed -1 for a new random seed each run, or enter a fixed seed to control generation variation. Enable Watermark to request the provider's AI-generated mark. Under Video output, leave file type and codec on auto for a first run, or choose the available container and codec settings. These affect encoding of the returned video. Execution requires configured access to the HappyHorse partner API. The source video, reference image and editing instructions are sent to the provider, and generation uses a provider-priced API call.
Resize image by scale
Upload an image and set the scale factor to resize both dimensions while keeping its aspect ratio. The default factor of 2 doubles its width and height; values below 1 reduce it. Run with the default Lanczos method for a first result. The resampling method changes how pixels are interpolated. Lanczos and bicubic suit smooth photographic resizing; nearest-exact keeps hard pixel edges. This is conventional resizing, so enlarging does not generate new scene detail. The source connects only the loader's image output, so uploaded transparency is not preserved.
Replace video background
Replace an uploaded video's background with a selected solid color using Bria, and return the processed video as a preview result. For a first run, upload your source video, leave Background color on Black, keep Seed at -1 and leave the advanced File type and Codec controls on auto. Run the Pipe to view the resulting video. Choose another background color to change the solid fill behind the foreground subject. Seed -1 requests a fresh re-run seed each run. A fixed seed does not make Bria's results reproducible: results remain non-deterministic regardless of seed. For explicit output encoding, enter auto, mp4, mkv or webm for File type, and auto, h264 or av1 for Codec. Explicit selections must be compatible with each other; keep both on auto unless you need a particular encoding. The Bria stage sends the uploaded video to an external provider and uses a paid provider operation. This Pipe offers solid backgrounds only, with no transparent-background mode. Audio preservation is not established by the supplied source evidence.
Moody Base + Turbo Image Generator
Generate an image or batch from text using the source's fixed Moody Base/Turbo checkpoint pair. A Base pass establishes composition, the latent is resized, Turbo refines it, and tiled diffusion produces the enlarged result. The Pipe returns only the finished image collection, without permanently saving images through the source SaveImage node. For a first run, replace the positive prompt with your subject, composition, lighting and style, and review the negative prompt. Keep the 640 × 960 starting size, refinement scale of 1.7, enlargement factor of 2 and supplied sampling defaults. No uploaded image is required. Final dimensions depend on both scale factors and latent-size rounding; final enlargement applies to the decoded Turbo result. Scale factors below 1 reduce dimensions. Larger dimensions, scales and image counts increase memory and processing requirements. The negative prompt affects the Base pass only. Turbo refinement, tiled enlargement and face refinement use zeroed negative conditioning. Enlargement normally reuses the main positive prompt. Enable Use separate enlargement prompt and edit Enlargement prompt to replace it for tiled redraw. Higher enlargement denoise permits more changes to existing details and content. Advanced sampling controls belong to separate stages. Base defaults use a 17-step schedule starting at 0 and stopping at 12, retaining noise for refinement. Turbo defaults use an 11-step schedule beginning at 5 and completing the schedule. These schedule lengths are not the number of iterations each pass executes. When changing them, review the corresponding start and end boundaries; keep the Turbo starting boundary below its schedule length. Each stage has its own seed. -1 randomizes that stage on each run; use explicit seeds for all active stages when retaining their random choices. Enlargement uses automatically calculated tile dimensions that depend on the decoded image size and enlargement factor. Tile batch size controls how many redraw tiles are processed together, separate from Image count, and can change results. Tile padding controls redraw context, while the automatic dimension formulas retain a fixed 96-pixel allowance. Seam repair starts at None. Select a repair mode before adjusting its denoise, blur or padding; Seam band width applies to Band Pass repair. Face refinement is optional and initially bypassed. Enable it to detect and redraw faces, then replace the portrait-specific Face prompt for your subject. Face denoise controls redraw strength. Detection threshold and minimum size determine which detections are accepted; crop context, region expansion and feathering control the processed regions and their blending. Detection may miss small or obscured faces. Face sampling and cycle controls apply only when this stage is enabled. Skin contrast finishing is optional and initially bypassed. Enable it to apply the fixed skin contrast model, then adjust Skin contrast strength. With Normal blending, 0 keeps the image before finishing and 1 uses the full finishing result; strength has no effect while finishing is bypassed. Other blend modes can alter the image even with finishing bypassed because they combine two identical inputs differently. The source's manual mask detailer and native editor bridge remain hidden and bypassed. This Pipe does not provide a live paint-mask session or portable manual mask refinement. Optional finishing stages process the generated image and still run the upstream generation and enlargement stages. Model selections are fixed to the source's Moody checkpoints; stock Z-Image catalog entries do not establish that those specific files are installed.
NegativeMutation
Original Hugging Face Repository Simply uploaded by me, all credit goes to . If you like this embedding, please consider taking the time to give the repository a like and browsing their other work on HuggingFace.
SD 3.5 Image Generator
Generate images from text prompts using Stable Diffusion 3.5. Describe your subject and scene in the positive prompt, and use the negative prompt for elements to exclude. Set the image width, height and batch size. Advanced sampling controls include seed, steps, guidance, sampler, scheduler and denoise strength. The model is fixed.
LTX-2.3 first and last frame video
Generate a video with audio between two endpoint images, guided by a motion and audio prompt, using the fixed LTX-2.3 distilled model. For a first run, upload both a first frame and a last frame. Replace the example prompt with the action and camera movement connecting your images, and include desired music, sound effects, or dialogue in the same prompt. Keep the defaults of 1280 × 720, approximately 5 seconds, 25 FPS, and endpoint strengths of 0.7. Run the tool and review the returned video with generated audio. Both images are required; there is no exposed silent-output mode or audio upload. Width and height resize both images, and the first resized image determines the video canvas. Use matching aspect ratios and compatible compositions to reduce unwanted cropping. Each image has independent advanced fitting and resampling settings: center fitting preserves aspect ratio by cropping, while disabled fitting stretches to the requested dimensions. Area resampling suits downscaling, lanczos suits upscaling, and nearest-exact suits hard pixel edges. Uploaded transparency is not retained because only the loaders' RGB image outputs are connected. Endpoint strengths independently control each image's conditioning influence. The first guide is fixed at the beginning and the last guide at the end; these guide positions are not exposed controls. Endpoint guidance does not guarantee exact copied frames. Advanced preprocessing controls apply compression independently to each resized image before conditioning; both default to 25 on a 0–100 scale. Use positive dimensions of at least 64 pixels. The downstream latent schema declares a sizing step of 32, although the retained source height is 720; exact spatial alignment behavior is not established by the supplied evidence. Duration is requested in positive whole seconds. FPS controls generation conditioning, audio timing, and playback; use 1–120. The graph requests duration × FPS + 1 frames for video and audio, and this count must stay at or below the audio latent limit of 1000. Temporal alignment can change the final duration. Larger canvases and longer clips require more memory and computation. Keep CFG at 1 for the first run. At this value, negative conditioning does not contribute through standard classifier-free guidance. When changing CFG, review the negative prompt's scene-specific exclusions and replace them to suit your images. Seed -1 randomizes each run; a fixed seed reuses the initial generation noise. Ancestral noise defaults to zero; its separate noise scale becomes relevant when ancestral noise is enabled. The advanced sampling schedule contains nine comma-separated noise levels defining eight intervals. Editing it changes the sampling trajectory and interval count; there is no independent steps control. Keep the supplied distilled-model schedule for a first run. Advanced output settings offer 8-bit or 10-bit video, container selection, and codec selection. Use 8-bit and automatic container and codec selection initially. The source notes that 10-bit can retain smoother gradients, but some players and downstream tools may not support it. Explicit container and codec choices must be compatible. Encoding choices do not disable generated audio.
Clutter
Fill your background with a lot of stuff with a quick prompt. Gives any scene that "lived in" look and feel.
Seedream layer separation
Separate an uploaded image into requested visual layers with generated transparency. Upload a source image and describe which elements should belong together, such as a character, background, lettering, or decorative graphics. The connected image outputs are combined with their corresponding generated masks and returned as one image batch. For a first run, replace the example layer instruction with elements present in your image, keep output resolution at 1K, and leave Crop layers off. The instruction requests layer organization; it does not guarantee a fixed number of output images. Enable Crop layers to request cropped layers, or leave it off to request the uncropped layout for compositing. Output resolution offers auto, 1K, 1.5K, and 2K; independent width and height controls are unavailable. Prompt optimization offers the provider's standard and fast modes. Watermark enables the provider's watermark option. Seed -1 requests a fresh randomized seed on each run; a fixed seed is supplied to the provider without guaranteeing identical results. Transparency comes from the generated separation masks. The source image's alpha-mask output is not connected, so uploaded transparency is not preserved as an input mask. Results are returned through Sweet Tea's image output; this graph does not permanently save PNG files.
Grok image edit
Edit a source image with a written instruction using Grok. For a first run, upload one source image, describe the changes you want and the features to retain, and keep the supplied defaults: grok-imagine-image, 1K resolution, one result and request seed -1. The example instruction requests anime styling while retaining identity. The output returns the edited images. Model selects among grok-imagine-image, grok-imagine-image-quality and grok-imagine-image-pro. Resolution selects a 1K or 2K output request. Image count requests 1 to 10 edited results from the same reference and instruction. Request seed controls whether the editing request reruns. Keep -1 for randomization or change a nonnegative seed to trigger another request. Results remain nondeterministic even with a fixed seed. Aspect ratio remains automatic. The source allows manual aspect ratios only with multiple connected reference images, while this tool connects one. Increasing image count changes the number of results, not the number of references. A source image is required; this tool has no text-only mode, mask-based editing input or denoise-strength control. Uploaded alpha transparency is not preserved because only the loader's RGB image output is connected.
Minimax H3 INT8/INT6/INT4 ConvRot
Minimax H3 INT8 / INT6 / INT4 ConvRot
Inzaniak's Lazy Textual Inversions
You can now get all my LoRAs in one single package if you subscribe to my Patreon (including those not on CivitAI):
Amazing Embeddings - fcNegative + fcPortrait suite
fcNeg is a Negative Embedding. You just install it in the embedding folder and then type fcNeg in the negative prompt. I don't know why it shows two trigger words. Ignore "fcneg-neg"
FLUX image upscale
Enlarge an uploaded image using the workflow's fixed FLUX/Dev and AnimeSharp upscale preset. For your first run, upload a source image and run the Pipe. The image passes through the Ultimate Upscale stage, and the saved upscaled image is returned as the result. The preset selects the FLUX/Dev fp8 bundle and 4x-AnimeSharp.pth. This interface offers only the source-image upload: there is no editable prompt, seed override, model selector, LoRA selector or optional processing mode. Processing settings remain at their source values. The upscaler's filename does not establish the final enlargement factor, and the supplied evidence does not establish an exact output size. No separate face-detailing stage is exposed. Running requires ComfyUI-UmeAiRT-Toolkit and the preset's model assets. The supplied dependency records leave the toolkit, FLUX/Dev bundle and AnimeSharp asset unresolved; automatic installation is not established.
SwitchX Video Edit
Create one edited video clip using SwitchX, guided by a prompt and optional reference image. For a first run, upload a source video, replace the example prompt with your desired look, and keep auto editing mode and 720p resolution. Start time defaults to 0 seconds and duration to 5 seconds. Shorten the duration if needed to stay within the 240-frame limit at your source video's frame rate. Enter auto to isolate the main subject automatically and edit the surrounding scene while preserving unmasked source pixels. Enter fill to regenerate the whole frame while preserving geometry; the subject's original pixels are not preserved, so this mode can change the subject's look or costume. Select and custom require first-frame keyframe or per-frame matte inputs unavailable in this Pipe; use auto or fill. The reference-image stage is disabled by default. Enable it and upload an image to guide the background, lighting or costume. Disable it for prompt-only editing. Provide a nonempty prompt or an enabled reference image; at least one is required. Prompts are limited to 2,000 characters. Start time and duration are in seconds. Duration 0 selects the remaining video, still subject to SwitchX's limits of 240 frames and approximately 2.77 megapixels per frame. Five seconds may exceed the frame limit for some videos. Enable strict duration to raise an error when the requested duration cannot be extracted; otherwise a shorter available clip is allowed. Enter 720p or 1080p for the maximum output resolution. Seed -1 randomizes on each run. Seed controls provider re-running rather than reproducibility; results remain nondeterministic with a fixed seed. The advanced video-output section provides file type and codec choices; keep both automatic for the first run. This Pipe returns the edited video, not SwitchX's separate alpha video. SwitchX uses an external Beeble provider call with provider billing.
Anima illustration with upscale and finishing
Generate an Anima illustration from prompts and return an enlarged, finished image batch. For a first run, describe your subject, scene, composition, and style in Positive prompt. The two additional prompt fields append optional details. Leave Negative prompt empty unless you want to specify unwanted content or visual traits. No uploaded image is needed. Choose the initial Size preset, Image count, and Enlargement factor. The default 832 × 1216 portrait preset and 2× enlargement produce 1664 × 2432 images. The factor multiplies both width and height. Leave the sampling defaults unchanged for a first run. Advanced generation controls provide the initial seed, steps, prompt guidance, sampler, scheduler, and denoise. Keep Generation denoise at 1 for the active empty-latent generation path. Generation and tile seeds are independent; -1 requests fresh randomization for that stage on each run. Fix both seeds when comparing changes without deliberately randomizing either stage. Finishing first applies the configured model upscaler, resizes to the chosen enlargement factor, and refines the enlarged image with tiled diffusion. Tile denoise controls how much is redrawn. Tile steps, scheduler, and sampler use the connected custom sampling nodes; the retained fallback fields are not the operative controls. Tile dimensions follow the original generated image dimensions. Tile padding supplies surrounding context in pixels, and Tile mask blur softens blending boundaries in pixels. Noise cleanup and Blur cleanup run after tiled refinement. Their strength choices range from Light to Maximum. Each cleanup stage can be bypassed independently. Strong cleanup can remove texture, so compare a lower strength or a bypassed stage if the result loses detail. Color correction offers Auto, Preset, Manual, and Colorize modes. Choose Preset to use Color preset and Preset variation; choose Manual for direct tonal tuning. Tint applies only in Manual mode. White balance shifts between cooler blue and warmer orange, while Green–magenta balance is a separate adjustment. Skin-tone preservation requires AI analysis. For Colorize mode, choose a colorization method; Force colorization overrides content detection that would otherwise skip art or anime. Sepia blend applies to vintage colorization. Bypass Color correction to return the preceding cleanup result. No color-reference image is connected, and palette and histogram outputs are not returned. The source's hand, face, and eye refinement passes and their detection chains are bypassed, with no Pipe switch to enable them. Their retained settings do not affect runs or provide anatomy repair. The uploaded-image and custom-width/height branches are also disabled; normal runs use the size preset. No LoRA entries are configured. The Pipe returns one final image collection through Sweet Tea's preview output rather than permanently saving through the original Image Saver. Larger batches, enlargement factors, and sampling workloads increase resource use.
CyberRealistic Negative - SDXL
Join The Tinkerer on Whop. Membership gets you early releases, private tools and a bunch of extra stuff.
ACE Step 1.5 music generator
Generate an MP3 music track from a music description and lyrics using ACE Step 1.5 XL Turbo. Describe the genre, instruments, mood, and vocal style, and supply lyrics with optional section markers. Adjust tempo, time signature, lyrics language, and musical key. Output duration and conditioning duration are independent controls in seconds; set them to match when changing track length. One shared seed controls conditioning and audio sampling; -1 selects randomization. Audio code generation is enabled by default and can be toggled, with separate guidance and sampling controls. Additional controls expose batch size, audio sampling settings, sampling shift, and MP3 encoding quality.
Qwen Image canvas outpainting
Extend an uploaded image on selected sides with prompted scene continuation using Qwen Image and inpainting ControlNet. The output is a resized, composited image with an automatically created padding mask. For a first run, upload an image and replace the example scene continuation prompt with content that fits its subject, lighting and style. The defaults add 200 pixels on the left, top and bottom and none on the right, before resizing the padded canvas to a longest edge of 1536 pixels. Set at least one extension amount above zero. Keep Lightning enabled at strength 1, with 4 steps, CFG 1, denoise 1, Euler and Simple for the initial run. Seed -1 randomizes each run; use a fixed seed to compare settings. Each extension is measured in original-image pixels before resizing. The padded image and its padding mask share the longest-edge target and resize together, retaining aspect ratio. Use a positive target size. The original image is also resampled, so preservation outside the generated region refers to the resized working image rather than the original file's exact pixels. No separate mask upload is needed. The region is derived from directional padding; uploaded alpha and loader edit masks are unused, and output transparency is not preserved. Boundary feathering acts before resizing. Mask expansion then grows or contracts the region in resized-mask pixels: positive values create overlap into the original image, while negative values contract it. Tapered corners affect nonzero expansion. Blur radius controls the Gaussian neighborhood and sigma independently controls its spread. The processed mask guides ControlNet and the final blend; softened boundaries mix original and generated pixels. The padded canvas is encoded and sampled without a separate latent noise mask. Final compositing determines where the generated result is visible, retaining the resized source outside the processed mask. Denoise controls how much of the encoded padded canvas is changed during sampling; lower values retain more initial structure. Control strength adjusts image-and-mask guidance. Guidance start and end are sampling-progress fractions from 0 to 1; keep start below end. The default interval covers the full sampling process. A negative prompt can discourage unwanted content, but has little or no effect at CFG 1. Sampler, scheduler and model-specific sampling shift are independent controls; retain Euler, Simple and shift 3.1 for the first run. Lightning is an optional adapter and starts enabled. Its toggle does not update steps or CFG. When disabling it, manually use the source baseline of 20 steps and CFG 2.5; when enabling it again at strength 1, return to 4 steps and CFG 1. For replacing a selected region inside an existing canvas using an uploaded edit mask, use the separate masked inpainting tool.
