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 42.552
Z-Image Turbo edge-guided generation
Generate images from a prompt while following a reference image's Canny edges. Each run returns generated images and a preview of the reference edge map. For a first run, upload a reference with the composition and outlines you want, then enter a prompt describing the desired subject, appearance, lighting and style. Keep control strength at 1, image count at 1, and the source sampling setup: 8 steps, CFG 1, res_multistep sampler, simple scheduler and denoise amount 1. Seed -1 provides fresh randomization; use a fixed seed to compare changes with the same initial noise. Inspect the returned edge preview to understand the structural guidance. The normalized low and high Canny thresholds default to 0.1 and 0.32. Lower thresholds retain more faint detail; higher thresholds suppress weaker edges. Keep the low threshold below the high threshold. Control strength scales the edge guidance influence; reducing it toward 0 loosens that influence. Output dimensions are derived from the processed reference, with no independent width or height controls. Resize reference is bypassed by default. Enable it to choose a longest side in pixels, initially 1024, while retaining the reference aspect ratio. The resize method affects the image used for edge extraction. Resizing changes both the guidance map and the dimensions supplied to generation. Increase image count for a batch of variations; the edge preview remains one reference map. Advanced sampling controls include steps, CFG, sampler, scheduler, denoise amount and sampling shift. Their source defaults provide the initial setup, and changes affect sampling behavior. The reference is structural guidance, not an encoded starting image: its original colors, textures and transparency are not preserved. Lower denoise does not turn this into pixel-preserving image editing. Negative conditioning is zeroed internally, so there is no editable negative prompt. This Pipe implements Canny guidance only.
Corneo's Power (Chainsaw Man) TI Embedding
This is a textual inversion embedding for Power from Chainsaw Man. Chainsaw Man is an incredible series that you should try out if you haven't already.
Vidu Q2 start and end frame video
Generate a short video guided by a start image, an end image, and a description of the motion between them. For a first run, upload both endpoint images and replace the example prompt with the action, camera movement, and scene transition you want. Both images are required; there is no start-frame-only mode. Keep the defaults of Vidu Q2 Pro Fast, 5 seconds, 720p, and small movement initially. Prompts support up to 2000 characters. Duration supports 2–8 seconds in whole-second increments. Resolution offers 720p or 1080p. Movement amplitude sets object movement to small, medium, large, or automatic; describe camera movement in the prompt. Match the requested action to the selected duration. The model selector also offers Vidu Q2 Pro and Turbo. Seed -1 randomizes each run; a fixed seed controls generation randomization. The Pipe returns one generated video. 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 a first run. Generation sends the endpoint images and prompt to Vidu through a paid provider call. Endpoint images guide a generative transition rather than a deterministic blend.
ChronoEdit image editing
Create one prompt-guided edited image from an uploaded source using ChronoEdit 14B. The source supplies both visual conditioning and the starting frame. Internally, the workflow generates and decodes a five-frame sequence, then returns only the fifth image; it does not export a video. For a first run, upload the image to edit, replace the example advertising prompt with a description of your desired result, leave the output at 720 × 720 pixels, and keep fast mode off. The negative prompt discourages unwanted attributes; its supplied Chinese text can be edited or replaced with exclusions appropriate to your scene. Standard mode uses the supplied defaults of 20 steps and CFG 4. Fast mode selects the fixed ChronoEdit distillation LoRA and its separate defaults of 4 steps and CFG 1. Standard and fast step counts and guidance affect only their respective modes. LoRA strength affects only fast mode. The mode name describes this distilled configuration; actual runtime depends on the execution environment. Width and height set the output canvas in pixels, in multiples of 16. Changing the aspect ratio can change source framing. Reference crop controls only the visual-conditioning branch: none avoids a center crop, while center uses the middle of the source. It does not crop the separately connected starting-frame branch. In advanced Sampling, use seed -1 for a new random seed each run or a fixed seed to compare changes with the same sampling noise. Sampler, scheduler and denoise affect both modes. Denoise uses a fraction of the noise schedule and is not a direct source-preservation slider in this temporal setup. Keep the supplied sampling values for a first run. Advanced positional encoding and model sampling shift also affect both modes. They adjust model encoding and its noise schedule, rather than directly controlling canvas size, image translation or frame selection. The sequence length and selection of the fifth image remain fixed. The uploaded alpha mask is unused, so source transparency is not preserved. The output is a generated edit, and the source framing or details can change.
Z-Image: Text to image
Generate square images from text using the fixed Z-Image base model and Qwen text encoder. Generated images are returned through Sweet Tea's image preview output. For a first run, replace the example positive prompt with your subject, setting, composition, lighting and visual style. Leave the negative prompt empty unless you want to discourage specific elements. Keep image count at 1, steps at 25, prompt guidance (CFG) at 4, sampler at res_multistep, scheduler at simple and denoising strength at 1, then run the Pipe. No source image is required. The saved resolution setting is square at approximately 1 megapixel, around 1024 × 1024 pixels. Resolution and aspect ratio are fixed in this interface. Image count creates a batch of images; larger batches require more memory. Seed -1 randomizes each run. Use a fixed seed to compare prompt or sampling changes with the same initial noise. Steps control sampling work, and CFG controls prompt guidance; excessive guidance can harm the image. Sampler and scheduler offer alternative sampling behavior. Change one setting at a time when comparing results. Denoising strength ranges from 0 to 1. Keep 1 for the saved empty-latent generation setup; lower values shorten the noise schedule and do not provide image-to-image editing. Advanced noise schedule shift adjusts the model's schedule and starts at 3. The model, text encoder and VAE are fixed to z_image_bf16.safetensors, qwen_3_4b.safetensors and ae.safetensors. This Pipe provides text-to-image generation, with no image upload or selectable model mode. Its preview output does not perform the original workflow's permanent PNG-save operation.
Text-to-Image · Flux.1 Schnell Full: Text to Image
Generate images quickly with Flux.1 Schnell full version. Uses Apache2.0 license, requires only 4 steps to generate images while maintaining good image quality.
Wan 2.2 speech-driven video
Generate a speech-driven video from a reference image, a speech recording and a scene prompt. Separated vocals condition generation; the trimmed original recording supplies the soundtrack. Additional outputs preview the prepared reference, separated vocals and instruments. First run: upload both required files, replace the example positive prompt to match your reference and desired motion, and retain the source defaults: 960 × 528 fill/crop framing, 49 frames per chunk, 5 steps, CFG 1, uni_pc sampling, simple scheduling and 16 FPS. The negative prompt describes unwanted content and also feeds negative-attention guidance. Seeds of -1 randomize each run; use fixed seeds when you want to retain the noise choices. Width, height and framing prepare the reference and determine generation dimensions. Use positive dimensions divisible by 16. Stretch, crop and pad offer different ways to fit the reference; keep-proportion mode can change the resulting dimensions. Frames per chunk follows the 1 + 4n convention, such as 49. It does not choose the number of chunks: the graph generates an initial segment and one continuation, while five further source examples remain bypassed and are not selectable here. Advanced settings retain independent initial and continuation denoising, generation batch size, three stacked LoRA strengths, sampling shift and negative-attention guidance strength, mixing and clipping. Start with their authored defaults. Batch size 1 is the single-video recipe, not a chunk-count setting. The Lightning HIGH and LOW LoRAs are applied in series, followed by Lightx2v; they are not alternative model modes. FPS changes playback timing without generating more frames or retiming audio. The starting frame offset defaults to 2 and changes the final frame selection without trimming the soundtrack. Both controls can affect synchronization. Audio trimming remains fixed at source positions 0–6; the supplied evidence does not establish those positions' units or boundary behavior. Output duration is not automatically matched to the recording. The video output defaults to MP4 with NVENC H.264 and requires a compatible encoding runtime. Model and encoder selections retain the authored recipe. Uploaded transparency is not preserved through the RGB reference-image path.
Flux Klein crop inpaint
Replace a selected region with a Flux 2 Klein generated crop and blend it onto the original RGB image. First run: upload the image, provide a manual mask through the image input's mask workflow, and replace the example Edit instruction with your desired change. Leave Use mask enabled, Automatic mask disabled and Use native crop size enabled. Set Object to select to an object present in your image: SAM2's image output feeds the crop even in manual-mask mode. Run and inspect the edited image, processed mask and input crop preview. The processed mask preview is before cutoff and final feathering, not the final blending mask. For text-detected selection, keep Use mask enabled, enable Automatic mask and name the object to select. Detection threshold, blur, offset and inversion adjust this selection. Disable Use mask for whole-image image-to-image processing. Neither mask switch bypasses SAM2 processing. The crop supplies both the starting latent and a latent reference. Denoise controls change strength throughout that crop; the selected mask controls cropping and final compositing, not a diffusion noise mask. Crop padding adds surrounding context in source-image pixels. Mask coverage adjusts the resized mask, Mask cutoff thresholds it, and Composite edge applies final expansion and feathering. Inverting a processed or composite mask does not change the earlier crop selection. Native crop size uses the crop dimensions as resize targets, with processing dimensions subject to the resize stage's divisibility setting. Disabling it stretches the crop to a square whose width and height equal Sampling resolution in pixels; this is not a maximum-side limit. The graph resizes the generated image back to the crop dimensions but does not explicitly route a correspondingly restored processed mask into compositing. Inspect alignment in this mode. Large native crops can increase memory use. Advanced controls include seed, sampling algorithm, schedule, steps, Flux guidance and resolution-dependent sampling shifts. Seed -1 requests fresh randomization; a fixed seed reuses the noise choice. Desaturation reduces generated-crop saturation before blending, with a selectable grayscale conversion method. The source suggests 0.05–0.20 for saturation mismatch, but this does not guarantee brightness or color matching. Uploaded transparency is not preserved as output alpha.
Hamunaptra Style
This is a Style embedding which turns everything in your image towards an Ancient Egyptian style! Think Pyramids, the river Nile, and Pharaohs! Simply throw Style-Hamunaptra on to the end of your prompt (or the...
FLUX.2 Klein Base 9B text to image
Create an image or a batch of images from text using the fixed FLUX.2 Klein Base 9B model. Describe the subject, composition, lighting and style in the positive prompt; optionally list unwanted elements in the negative prompt. No uploaded image is required. For a first run, keep the 1024 × 1024 size, one image, 20 steps, CFG 5 and Euler sampler. The supplied motorcycle prompt is a ready-to-run example. Width and height jointly set the latent image size and the resolution-aware sampling schedule; use multiples of 16. Larger dimensions and batches increase memory requirements. Advanced controls let you tune guidance, steps, sampler and batch size. Higher CFG increases the influence of prompt conditioning and can change the visual balance; more steps increase sampling work without guaranteeing a better result. Seed -1 randomizes each run; use a fixed seed to reuse the initial noise while comparing other settings. The runtime requires flux-2-klein-base-9b-fp8.safetensors, qwen_3_8b_fp8mixed.safetensors and full_encoder_small_decoder.safetensors. The source graph uses the Base model with its supplied sampling settings; it does not provide an image-editing mode or a selectable distilled-model preset.
Recreate an image with realistic detail
The reference image supplies a generated scene description, rather than direct image conditioning. A style prefix and detail suffix surround that description, and the resulting positive prompt drives both Grok generation and Z-Image Turbo refinement. The default style is black and white photography. Refinement denoise controls how much the generated image changes. Before refinement, the image is resized to the chosen base megapixel count, enlarged fourfold with RealESRGAN, and reduced by half, producing approximately four times the base pixel count. Grok resolution affects the initial generation; base megapixels determines the final refinement size. The negative prompt affects only refinement and becomes useful when refinement CFG is increased above its default of 1.
HiDream O1 image studio
Create an image batch with HiDream O1 Image Dev by editing an uploaded reference or generating from a text description. For a first run, upload a source image, keep Image edit enabled, replace the example Positive prompt with your requested change, leave Refine prompt off, and run with the existing defaults. Results are returned through Sweet Tea's image output; this graph does not save files through ComfyUI SaveImage. An upload is required by this interface in both modes. With Image edit enabled, the original upload supplies reference conditioning. Output width and height follow the upload, rounded down to multiples of 32. Use dimensions of at least 64 pixels and keep the calculated canvas within 4096 pixels per dimension. To calculate a different edit canvas, enable the currently bypassed Resize edit output stage and set Edit megapixels, measured in millions of pixels. Aspect ratio follows the upload. This stage changes canvas sizing only; reference conditioning and prompt refinement still receive the original upload. Resize method affects the intermediate sizing copy, rather than directly filtering the generated result. Disable Image edit for text generation and describe the complete desired image in Positive prompt. Text width and Text height specify pixels, in multiples of 32 from 64 to 4096. Text batch count and Edit batch count independently select the number of results for their respective modes. Text mode does not use the upload as image-generator reference conditioning, but the interface still requires it. Refine prompt optionally uses Gemma 4 and the upload to expand your request into an English visual description, including in text mode. It may add interpretation or inferred details; leave it off when exact wording matters. Refinement tuning controls text sampling, its separate seed and the response token limit. Temperature and token filters apply when Sample refinement text is on. An insufficient token limit or malformed JSON response can prevent prompt extraction. Refinement thinking requests model-supported thinking behavior; false is the source configuration for JSON extraction. The starting image settings are 28 steps, normal scheduler, CFG 1 and Add noise enabled. CFG changes conditioning influence; at 1, conventional classifier-free negative guidance is inactive. Denoise changes the sampling schedule from an empty latent in both modes, rather than directly controlling preservation of uploaded pixels. Advanced Sampling noise tuning exposes the initial and final per-step noise multipliers and clipping threshold. Image Seed and Refinement seed control separate random processes: -1 randomizes each run, while fixed seeds help compare settings. This tool accepts one reference image. Uploaded alpha is not carried through the RGB reference path. Edit canvas dimensions are rounded rather than clamped, so check the resulting size when using a very small image or an extreme aspect ratio.
Grok Imagine image generator
Generate one or more images from a text prompt using Grok Imagine. Describe the subject, composition, lighting, style, and any desired text. No uploaded image is required. For a first run, use the supplied example or replace it with your own prompt. Keep grok-imagine-image-quality, the square 1:1 aspect ratio, 1K resolution, and one image, then run the Pipe. Returned images appear in Sweet Tea results; the output stage does not permanently save files. The model field selects the Grok Imagine model. Aspect ratio sets the width-to-height shape, while resolution selects a size tier supported by that model. Keep the supplied values unless you know another combination is supported; the supplied evidence does not enumerate alternative model, aspect-ratio, or resolution values. Number of images requests 1–10 results from the same prompt. Seed controls whether the provider node re-runs, rather than making images reproducible. Leave it at -1 to randomize on each run. A fixed seed does not guarantee the same image. Generation sends the prompt to the external Grok provider and uses a paid provider call.
Character camera views
Upload a character image and describe the camera view you want. This Pipe uses Qwen Image Edit 2511 with the multiple-angles LoRA to generate one image per run. The uploaded image supplies both reference conditioning and the initial image latent. For a first run, upload your image, keep the close-up instruction and leave Fast mode enabled. Replace the instruction to request another view. The eight source camera instructions are shown below; leading whitespace and trailing line breaks inside the code blocks reproduce the source strings. Close-up: ``` Turn the camera to a close-up. ``` 45 degrees right: ``` Rotate the camera 45 degrees to the right. ``` Aerial: ``` Turn the camera to an aerial view. ``` Wide-angle: ``` Turn the camera to a wide-angle lens. ``` Low-angle: ``` Turn the camera to a low-angle view. ``` 90 degrees right: ``` Rotate the camera 90 degrees to the right. ``` 90 degrees left: ``` Rotate the camera 90 degrees to the left. ``` 45 degrees left: ``` Rotate the camera 45 degrees to the left. ``` Fast mode coordinates the Lightning LoRA, Fast steps and Fast CFG through one source boolean. Its defaults are 4 steps and CFG 1. Disable Fast mode to use the model without Lightning and the independent Standard steps and Standard CFG defaults of 40 and 4. Each mode's tuning fields affect only that mode. Keep Euler and the simple scheduler for the source setup. Negative prompt guidance has little or no effect at CFG 1. Denoise defaults to 1 to allow substantial viewpoint changes. Reducing it retains more of the initial image structure but can prevent the requested camera change. Camera LoRA strength adjusts the multiple-angles adaptation in both modes; Lightning strength applies only in Fast mode. These are generated interpretations of a single image, not measured 3D rotations. Hidden surfaces and character details may be invented or changed, and requested degree values are instructions rather than geometric guarantees. The source automatically scales the input before generation and offers no independent output dimensions. Uploaded transparency is not preserved by this RGB-only path. Run again with another instruction to create additional views.
Color balance
Create a color-graded image by adjusting red, green and blue separately in shadows, midtones and highlights. For a first run, upload a source image and run with the saved settings to preview the source's stylized grade. These defaults include strong shadow and highlight shifts rather than a neutral starting point. To start without a color shift, set all nine color adjustments to 0, then adjust the tonal region you want to change and run again. Each adjustment uses a unitless -100 to 100 scale. Positive red, green or blue values add that channel; negative values shift toward cyan, magenta or yellow respectively. Tonal regions are weighted by the original image's HSL lightness and overlap, so they are not hard selections. The nine adjustments combine in one grade. In advanced controls, Preserve luminosity is enabled by default. It restores original HSL lightness after the shifted RGB values are clamped. Disable it to allow the color shifts to alter lightness too. This preserves HSL lightness, not every measure of perceived brightness; strong adjustments can clip colors. The result has the source image's dimensions. Uploaded transparency is not preserved because the image loader's separate alpha mask is not used. This tool applies only color balance; it does not combine the other adjustment tools in this family.
Style Sylva Magic
This is a Textual Inversion trained on one image with DreamArtist, my second publicly released inversion. :)
LTX-2 video with generated audio
Generate a video with accompanying generated audio from a text description. Describe subjects, appearance, actions over time, camera movement, and desired sounds, dialogue, or singing. No uploaded image or audio is required. The selected output combines the decoded imagery and audio into one video; MP4 is the default container. For a first run, keep the supplied puppet scene, 121 frames, both frame rates at 24, and the sampling defaults. This gives approximately five seconds. Replace Scene and sound with your own description when ready. Negative prompt lists unwanted characteristics and supplies conditioning to both sampling stages. Width and height are nominal output targets. The initial pass runs at half those dimensions, followed by a fixed 2× spatial latent upscale and a short distilled refinement pass. Internal quantization can change the final size, including the supplied 1280×720 target. For aligned dimensions, use multiples of 64, at least 128 pixels in each dimension. Use frame counts of 8n+1, such as 121, within the audio stage's supported range of 1–1000. Video FPS controls conditioning and playback; Audio FPS independently determines audio duration from the shared frame count. When changing frame rate, set both to the same integer from 1 to 120. Changing one does not update the other. Optional dolly-left camera guidance is disabled by default in both stages. Enable Initial camera guidance and Refinement camera guidance together to apply it across both passes, starting with their supplied strengths of 1. Their toggles and strengths are independent. A prompt requesting a stationary camera may compete with enabled dolly-left guidance. Advanced controls separate initial generation from refinement. Initial steps and schedule shifts affect the first pass. Refinement uses its own sampler, CFG, distilled adapter strength, and explicit noise-level sequence; Initial steps does not alter that sequence. Keep the supplied refinement settings for the first run. Each pass has its own seed: -1 randomizes on each run; set both seeds to fixed values when comparing settings. Generated speech, singing, and timing require review and may not match the prompt exactly. Video output exposes container, codec, and compression controls. Leave MP4, codec auto, and CRF -1 for the first run. Video precision selects 8-bit or 10-bit output; 10-bit requires compatible downstream encoding and playback. The fixed setup uses ltx-2-19b-dev-fp8.safetensors in checkpoints, gemma_3_12B_it_fp4_mixed.safetensors in text_encoders, ltx-2-19b-distilled-lora-384.safetensors in loras, and ltx-2-spatial-upscaler-x2-1.0.safetensors in latent_upscale_models. Optional camera guidance uses ltx-2-19b-lora-camera-control-dolly-left.safetensors in loras. All five assets are marked MISSING_MODEL in the supplied dependency evidence; local availability has not been established. The checkpoint, distilled adapter, and upscaler have supplied sources under https://huggingface.co/Lightricks/LTX-2/resolve/main/ using their filenames. The text encoder source is https://huggingface.co/Comfy-Org/ltx-2/resolve/main/split_files/text_encoders/gemma_3_12B_it_fp4_mixed.safetensors. The optional camera adapter source is https://huggingface.co/Lightricks/LTX-2-19b-LoRA-Camera-Control-Dolly-Left/resolve/main/ltx-2-19b-lora-camera-control-dolly-left.safetensors.
Mage-Flow image edit
Create edited images from one uploaded reference and written instructions using the fixed Mage-Flow-Edit model. Upload your source image, then describe what to keep and what to change. An instruction such as “Keep the subject and pose; replace the background with a grassy prairie” is a starting point. Preservation requests guide generation but do not guarantee unchanged pixels. For a first run, leave Resize reference enabled at 1 megapixel, Match reference size enabled, Number of results at 1, and sampling at 30 steps with instruction guidance 5. Leave Negative prompt blank unless you want to describe unwanted content or visual traits. Run the Pipe to receive the edited image results. Reference resizing retains the reference aspect ratio and aligns dimensions to multiples of 16. When Match reference size is enabled, output dimensions follow this processed reference, so Reference megapixels also affects output size. Turning Resize reference off passes the original image dimensions through. Turning Match reference size off uses Width and Height instead; reference preprocessing remains independent. Use positive manual dimensions divisible by 16. With resizing off and size matching on, use a source image whose dimensions are divisible by 16. Advanced controls include reference pixel area and interpolation, seed, sampling steps, instruction guidance, sampler, scheduler, and denoising amount. Seed -1 selects fresh randomization for each run; a fixed seed helps compare settings using the same sampling seed. The source sampling defaults are Euler, Simple, and denoising amount 1. Denoising amount acts on the edit encoder's latent output and is not established as a source-image preservation strength. This Pipe accepts one reference image and returns the requested number of edited images. It has no mask-based edit boundary, and uploaded transparency is not preserved: only the loader's IMAGE output is connected.
Style Swirl Magic
This is my fifth Textual Inversion, called Style-SwirlMagic. This model was trained on a single image using DreamArtist. As the name suggests, it adds magical swirls to images, making it a great tool for creating RPG...
