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 42.678
SD3.5 Large blur-guided image generation
Generate new images from a prompt and an already preprocessed blur reference using SD3.5 Large and its blur ControlNet. Upload the required reference and describe the desired subject, appearance, materials, and details in the positive prompt. This tool does not blur or otherwise preprocess the upload. For a first run, replace the example prompt with your description, upload a reference with the intended composition, and choose output dimensions matching its aspect ratio. Width and height are in pixels and use multiples of 16. Start with one image and the defaults: 1024 × 1024, control strength 1, 30 steps, CFG 4, Euler sampler, Simple scheduler, and denoise fraction 1. Control strength determines the influence of the reference. Lower it for more freedom; set it to 0 for generation without reference guidance, while still supplying the required upload. Control start and end select the portion of sampling during which guidance applies: 0 is the beginning and 1 is the end. Keep start below end. Open Sampling for variation and tuning. Seed -1 selects a random seed each run; use a fixed seed when comparing settings with the same initial noise. CFG controls prompt guidance. Steps, sampler, scheduler, and denoise fraction change the sampling process. Keep denoise at 1 for the initial run. Image count generates a batch using the same prompt, reference, and dimensions; larger batches and dimensions require more memory. The checkpoint and blur ControlNet are fixed in this tool. Generation starts from an empty latent rather than an encoded copy of the upload, so this is not pixel-preserving restoration. Lowering denoise does not turn it into image-to-image restoration. There is no editable negative prompt: its text conditioning is zeroed internally before ControlNet is applied. Uploaded alpha is not used.
Seedance 2.0 text to video
Generate one video from a scene description, with optional generated audio. No uploaded media is required. For a first run, use the supplied five-second fantasy prompt with Seedance 2.0, 720p, 16:9 and Generate audio enabled. Alternatively, replace the prompt with your subject, setting, action, visual style and camera movement. Include desired sound when audio is enabled. This workflow calls the ByteDance provider API, requires runtime authentication and uses provider-priced generation. Choose Seedance 2.0, Seedance 2.0 Fast or Seedance 2.0 Mini. Resolution is a text field: enter a value supported by the selected model rather than assuming every resolution works with every model. Aspect ratio sets the frame shape; adaptive leaves that choice to the provider. Duration accepts 4–15 seconds. When changing it, update any duration or shot timestamps in the prompt as well. Prompt wording such as '8K' does not replace the Resolution control. Disable Generate audio for a silent result. Watermark requests a provider watermark. Seed defaults to -1 for randomization on each run. A fixed seed does not reproduce the same video; the source describes generation as non-deterministic regardless of seed. The generated video is returned as one preview result. Under advanced Video encoding, leave File type and Codec at auto for automatic selection, or choose a supported container and compatible codec. This output uses Sweet Tea's preview transport rather than the original SaveVideo stage.
fal.ai LTX Video
Describe a scene and its motion to generate a video through fal.ai's LTX Video 13B Distilled endpoint. This workflow accepts text only and returns the generated video. For a first run, enter a prompt describing the subject, setting, action, and camera movement. Keep the source defaults of 480p, 16:9, and 121 frames. The negative prompt provides a starting list of visual and motion defects to discourage. Resolution and aspect ratio set the video shape. Frame count sets its length in frames; this workflow does not expose FPS, so frame count is not a duration in seconds. Frame count must be entered as an integer, without units. Alternative shape values and frame counts must be supported by the provider. Seed defaults to randomization on each run. A fixed seed is available for exploring variations under otherwise similar settings, without a guarantee of identical provider results. Generation requires configured fal.ai access.
Amateur Snapshot Photo - [STYLE] [LORA] [FLUX]
Latest page update: Updated recommended workflow again to a version 2, which is slightly even better.
bad X (bad sdxl negative embedding)
This is a textual inversion based on SDXL 1.0 images with the refiner, tested and trained to enhance the effectiveness of the output of human figures. It is meant to correct mutation like symptoms of the face and...
Qwen-Image edge-guided generation
Upload a source image and describe the image you want to create. The Pipe resizes the upload to approximately the chosen megapixel count while retaining its aspect ratio, extracts Canny edges, and uses the encoded edge map as both reference conditioning and the sampler's starting latent. It returns the generated image and the edge-map preview. For a first run, keep the 1 MP size, default edge thresholds, full denoise, and standard mode. Replace the example positive prompt with your desired subject, appearance, and style. Inspect the edge preview: lower thresholds admit more edges, while higher thresholds suppress weaker details. Keep the low threshold below the high threshold. Enable Lightning mode to select the supplied four-step Lightning LoRA together with its separate steps and CFG settings. Standard mode defaults to 20 steps and CFG 2.5; Lightning defaults to 4 steps and CFG 1. Each mode retains its own tuning fields, and only the selected mode's fields affect a run. Denoise operates on the edge-map latent, not the original photograph. Lower values can leave more of that edge-map appearance in the result; this is not a control for preserving the source image's colors. Union LoRA strength adjusts the model adaptation used for reference guidance rather than guaranteeing an exact edge match. Keep Lightning strength at 1 initially. The resize stage can be disabled to work at the upload's native dimensions; megapixel and resampling settings then have no effect, and large uploads can substantially increase resource use. This graph implements Canny guidance only, despite the Union model supporting other control types. It does not use the upload's alpha mask.
Flux.1 Inpaint
Fill missing parts of images using Flux.1 Fill Inpainting.
Magnific reference style transfer
Create a restyled image from a source image, a visual style reference and a descriptive prompt. For a first run, upload both images and replace the fantasy example prompt with a description of your subject and intended appearance. Keep style strength 70, structure strength 41, faithful flavor, balanced engine and fixed generation enabled, then run the Pipe to view the resulting image. Style strength controls the reference style's influence from 0 to 100 percent. Structure strength controls retention of the original image's structure on a separate 0–100 scale. Adjust these independently to balance restyling with composition retention. Flavor selects the service's style-transfer treatment, while engine selects its processing engine. Both offer alternative treatments of the same inputs. Disable fixed generation to introduce more randomness across runs; enabling it does not guarantee identical results. Processing sends the images and prompt to the Magnific partner service through its API node, requires service authentication and uses provider-priced generation. Portrait enhancements are unavailable in this Pipe and remain disabled. Uploaded alpha masks are not connected, so source transparency is not preserved.
Gemini image refinement
Refine and upscale a reference image with Gemini, or generate a new image from a prompt. For a first run, upload a Source image, leave that stage enabled, and use the default prompt to request refined details, textures and materials while retaining composition and text. The default resolution is 4K. This is generative editing: exact text, details and composition may change. Uploaded transparency is not preserved because only the loader's IMAGE output is connected. Change Prompt to describe other edits and what should remain. Aspect ratio set to auto follows the reference image's proportions; an explicit ratio requests a different output shape. Resolution selects a target size tier of 1K, 2K or 4K rather than exact pixel dimensions. The 2K and 4K settings use Gemini's native upscaler, and dimensions also depend on aspect ratio. For text-to-image generation, bypass Source image and replace the refinement prompt with a complete description of the image you want. Choose an explicit aspect ratio to specify the output proportions. This Pipe accepts one reference image. Model selects the Gemini image model. Seed -1 requests a new random seed each run; a fixed seed requests best-effort repeatability, but identical results are not guaranteed. System instructions set foundational provider behavior alongside Prompt; the default directs Gemini to produce an image. Provider response format requests either IMAGE or IMAGE+TEXT, but only the image is connected to this Pipe's result. Generation uses the Gemini provider and sends the prompt and any reference image to that service through a paid provider call. The generated image is returned through Sweet Tea's preview transport; this workflow does not permanently save an image file.
Princess Style
This is a Style embedding which turns your image subjects into bonafide Princesses! Think pearls, tiaras, and ballgowns! Simply throw Style-Princess on to the end of your prompt (or the start, if the effect doesn't...
Z Image Turbo pixel-art image generator
Generate one image or a batch from text using the fixed Z Image Turbo model, with optional pixel-art styling. No uploaded image is required. For a first run, leave pixel-art style enabled, edit the pixel-art prompt, and keep the 1024 × 1024 size, batch size 1, LoRA strength 1 and four sampling steps. The source prompt begins with “Pixel art style, retro”; use that as a starting point when describing your own subject. Run the Pipe to receive the generated images. The style toggle switches both the model branch and the prompt. When disabled, the base model uses the separate unstyled prompt. Edit both prompts when comparing modes; changes to one do not update the other. LoRA strength affects only the enabled pixel-art branch. Width and height are output pixels and must be multiples of 16. Batch size controls how many images are returned. The output stage does not permanently save images to the ComfyUI output folder. Advanced sampling controls include seed, steps, guidance scale, sampler, scheduler and denoise fraction. Seed -1 randomizes each run; use a fixed seed to compare changes with otherwise unchanged settings. The source defaults are four steps, guidance 1, res_multistep sampling, the simple scheduler and denoise fraction 1. Negative conditioning is zeroed automatically, so there is no editable negative prompt. The optional sampling-shift stage starts bypassed, matching the source workflow. Enable it before adjusting its shift value; the source value is 3. While bypassed, shift has no effect. Generation starts from an empty latent and does not support image-to-image input. Reducing denoise fraction changes sampling but does not preserve an uploaded image. The model, text encoder, VAE and pixel-art LoRA are fixed by this Pipe.
Video to pose animation
Turn a source video into a rendered whole-body pose animation using SDPose. The output is one pose video, rather than an overlay on the original footage or a downloadable keypoint dataset. It uses the source frame rate and includes source audio when available. For a first run, upload a clip with one clearly visible person, keep the default 1024-pixel longer edge and drawing settings, and run the Pipe. The required checkpoint is sdpose_wholebody_fp16.safetensors. Frames are resized while preserving aspect ratio before pose extraction; Longer edge sets both detection resolution and rendered frame dimensions. Use Draw body, Draw hands, Draw face, Draw feet and Draw head to choose the rendered features. These switches change visualization, not what the model extracts. Confidence threshold controls which keypoints are drawn: higher values suppress uncertain points, while lower values include more points. Line width and Face point size are measured in output pixels; Face point size applies when Draw face is enabled. Resampling method controls frame resizing before detection. Area is suited to downscaling and Lanczos to upscaling. Processing batch size controls how many frames the extractor processes together; lower it if memory is limited. It does not change video duration. Frame rate is inherited from the source and cannot be independently adjusted here. This workflow supplies no bounding boxes, which the extractor requires for multi-person detection. Use single-person footage rather than expecting reliable multi-person capture. Advanced output controls select the container, codec, encoding quality and video bit depth. Keep File type and Codec on automatic, Quality (CRF) at -1 and Bit depth at 8 for a first run. Explicit container and codec choices must be compatible. The 10-bit option requires compatible encoding and playback and does not improve pose detection.
OmniGen2: Text to Image
Generate a single image or a batch from text with OmniGen2. No uploaded image is required; the diffusion model, Qwen text encoder, and VAE are fixed by this workflow. For a first run, enter the subject, composition, lighting, and style in Positive prompt. Negative prompt describes unwanted features. Leave the sampling defaults in place and generate one 1024 × 1024 image. Width and height are measured in pixels and must be multiples of 16; together they determine the aspect ratio. Images per run sets the batch size. Larger dimensions and batches increase memory use. Advanced settings expose guidance, seed, and sampling controls. Guidance defaults to 5. Guidance mode selects the source dual guider's regular or nested combination. Negative prompt feeds both its secondary and negative branches; there is no separate secondary prompt. Secondary guidance defaults to 2 and is not an independent negative-prompt strength in regular mode. Seed -1 chooses new random noise for each run. Use a fixed nonnegative seed when comparing settings. Sampling defaults are 20 steps, Euler sampler, and the simple scheduler. Steps sets the sampling step count, Sampler chooses the sampling algorithm, and Scheduler sets the distribution of noise levels. Denoise selects the fraction of the schedule used and defaults to 1 for the full schedule. Sampling begins from an empty latent. Lowering Denoise does not enable image editing, and this tool has no reference-image input. All decoded images in the batch are returned through Sweet Tea's preview output. The workflow requires omnigen2_fp16.safetensors, qwen_2.5_vl_fp16.safetensors, and ae.safetensors; model selection is not exposed.
Seedance image to video
Animate a starting image into one video using a motion prompt and ByteDance Seedance. Upload the image to use as the first frame, then describe the subject's action and desired camera movement. Generation sends the image and prompt to the ByteDance API and requires configured API access and sufficient credits. The result is returned through Sweet Tea's video output. For a first run, replace the example prompt to match your image and keep Seedance 1.0 Pro, 480p, adaptive aspect ratio and a duration of 5 seconds. Duration accepts whole seconds from 3 to 12. Resolution and aspect ratio set the requested output shape. Choose among the available Seedance models. Generate audio applies only to seedance-1-5-pro-251215; other models ignore it. Fixed camera adds a stationary-camera instruction to the prompt without guaranteeing the effect, so keep your motion prompt consistent with that request. Seed -1 randomizes each run; a specified seed controls generation randomness. AI watermark requests an “AI generated” mark on the video. Advanced Video output settings select the returned file container and codec. Leave both on auto and Quality (CRF) on -1 for default output encoding, or choose from the exposed encoding controls.
HiDream E1 image editor
Generate an edited image from an uploaded source and a written instruction using HiDream E1. The source supplies visual conditioning, and the instruction describes the requested transformation. The generated image is returned as a Pipe preview using the fixed HiDream E1 model, associated text encoders and VAE. For a first run, upload your image, replace the example instruction with the change you want, and keep 768 × 768 pixels, 28 steps, text guidance 5, image guidance 2 and regular guidance combination. Use positive width and height values divisible by 8. Center fitting crops the source to the chosen aspect ratio before resizing; disabled fitting retains the full image but can stretch it when aspect ratios differ. Resize method selects the interpolation used for this preprocessing. Text guidance and image guidance control separate conditioning contributions. In regular mode, text guidance scales the difference between instruction-conditioned and image-conditioned predictions, while image guidance scales the difference between image-conditioned and negative predictions. Nested mode changes how the two guidance values combine. The negative prompt describes unwanted content or qualities and supplies text to both the image-conditioned branch and the separate negative branch. Advanced controls include seed, steps, sampler, scheduler and denoise. Seed -1 selects a new random seed each run; use a fixed seed to compare settings with consistent initial sampling noise. Steps sets sampling iterations, sampler selects the algorithm, and scheduler sets the distribution of noise levels. Denoise selects the fraction of the noise schedule used. Sampling starts from an empty latent rather than the encoded source, so reducing denoise is not a conventional source-preservation strength control. This is a whole-image generative edit with no supplied editing mask and no guarantee that untouched details remain identical. Uploaded transparency is not preserved through the connected RGB image path.
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.
