Répertoire des ressources
Trouvez ce dont vous avez besoin pour votre flux de travail.
Guides: techniques, setup, and troubleshootingRecherchez Sweet Tea, Pipes, des flux de travail externes, des modèles, des packs de nœuds et des guides dans un catalogue unique lié aux preuves.
Commencez plutôt avec un flux de travail ↗Résultats de la recherche
Toutes les ressources
19 affiché of 42 605
Wan 2.1 edge-guided video
Generate a silent video guided by source-video edges, a start image, and a text prompt using Wan 2.1 Fun Control. For a first run, upload a source video and a start image, then replace the positive prompt example with your desired subject, action, and style. The source video supplies frame-by-frame Canny contours. The start image supplies both initial-frame and visual conditioning. The negative prompt lists unwanted appearance or motion; its packaged default is in Chinese. Keep 960 × 544 pixels, 77 frames, 16 FPS, batch size 1, full denoise, and the packaged sampling settings initially. This gives approximately 4.8 seconds of video. Dimensions use multiples of 16 and frame counts follow 1 + 4n. Choose a source clip with enough frames for the requested sequence. There are no source trimming or frame-rate conversion controls. Low and high edge thresholds determine which contours guide generation. Lower thresholds include weaker edges; higher thresholds favor stronger contours. Keep the low threshold below the high threshold. Reference crop changes framing for visual conditioning only, independently of the initial-frame input. Frames determines the generated sequence length. FPS determines playback speed and duration without generating additional frames. Source FPS and source audio are not connected to output playback. The only selected output is the generated video; no separate edge preview is returned. Leave file type and codec on auto for a first run. Manual choices must be compatible with each other and your playback software. The optional 10-bit setting also requires compatible encoding and playback. Advanced sampling controls include seed, steps, prompt guidance, sampler, scheduler, denoise, and schedule shift. Seed -1 requests fresh random noise; a fixed seed lets you compare settings with the same starting noise. Keep denoise 1 and batch size 1 for normal use; batch variants have no separate video output branches. Skip-layer guidance exposes independent double-block and single-block layer lists, strength, rescaling, and a sampling-progress interval expressed as fractions from 0 to 1. Keep its start below its end. Attention adjustments independently scale structural and temporal self-attention and cross-attention. Either adjustment stage can be bypassed while preserving the model path; its controls apply only while enabled. The model, text encoder, vision encoder, and VAE remain fixed to the packaged Wan 2.1 Fun Control setup.
Capybara video edit
Generate a prompt-directed video variation from an uploaded clip using Capybara. Selected source frames are resized and supplied to video conditioning and, by default, a visual encoder; the generated frames become the output video. For a first run, upload a video with at least 121 frames, replace the example edit instruction with the change you want, and keep 960 × 960 pixels, 121 output frames, 24 FPS and batch size 1. The resulting playback duration is approximately 5.04 seconds. Describe both the desired change and any subject or action you want retained. The advanced negative prompt lists unwanted visual features. Width and height control both generation and source-frame resizing. Use positive multiples of 16. Source crop defaults to center, which crops to the output aspect ratio while preserving proportions; disabled stretches the frames to fit. Source resampling selects the resizing interpolation. Source start frame is the zero-based beginning of the selected visual reference range. Source frame count and output frame count are independent; keep both at 121 initially and keep the selected range within the uploaded clip. Use output frame counts of 4n + 1, such as 81 or 121. Output FPS is set independently of the uploaded video's frame rate. Source audio is attached unchanged: selecting later frames or changing output duration can cause audio synchronization differences. Visual guidance is an optional stage. Its crop control affects visual encoding of the already resized frames. Bypass Visual guidance to omit that encoding while retaining the source-frame conditioning connection. Advanced generation controls include seed, prompt guidance strength, steps, sampler, scheduler, sampling shift and denoise. The defaults are randomized seed (-1), guidance strength 6, 20 steps, Euler, simple scheduler, shift 7 and denoise 1. A fixed nonnegative seed reuses the initial noise. Sampling shift changes model sampling rather than source timing; denoise controls the fraction of the noise schedule and is not a calibrated video-edit strength. Keep batch size 1 for one clip because every decoded frame feeds the same video assembly path, rather than separate video outputs. Playback settings include 8- or 10-bit assembly; some players may not support 10-bit video. Video output offers automatic or explicit file type, codec and CRF settings. Start with auto file type, auto codec and CRF -1; explicit container and codec choices must be compatible. This is generative editing. Exact source-frame correspondence, subject preservation and source-motion preservation are not guaranteed.
Wan 2.2 camera video — Standard
Generate a silent camera-conditioned video from a scene prompt and an optional starting image with Wan 2.2 14B Fun Camera. For a first run, upload a starting frame with Source image enabled, replace the rover example under Scene and action, and keep the 720 × 720 dimensions, 81 frames and 16 FPS. Choose Static or a pan, zoom or rotation under Camera movement. Leave output container and codec on auto. The default clip is about 5.1 seconds long. To generate from text without a starting image, explicitly bypass Source image; an empty upload alone is not the mode switch. Describe subject action in the prompt and choose camera motion separately. Camera speed applies to moving presets. Width and height are pixel dimensions in increments of 16; frame counts follow 1, 5, 9 and so on. Frame rate controls playback speed and duration, while frame count controls how many frames are generated. Advanced camera intrinsic parameters use the source's 0–1 scales, not millimeters. Advanced settings include unwanted-content text, seed and independent prompt guidance for initial generation and refinement. Seed -1 selects new random variation; use a fixed nonnegative seed when comparing settings. The supplied negative prompt is Chinese and excludes artifacts, poor anatomy, clutter and static imagery; adapt it to your scene. The standard profile uses a high-noise stage followed by low-noise refinement, without the sibling four-step profile's acceleration LoRAs. Both samplers use a total schedule of 20 steps: the initial stage stops at 10 and refinement starts at 10. These are independent controls, not automatically synchronized. When changing the schedule, keep both total-step settings matched, keep the handoff boundaries matched and within the total schedule, and coordinate the noise schedulers. Refinement continues the initial latent without adding new noise. Separate model sampling shifts are also available. Keep latent batch size at 1 for one clip; this graph has a single video assembly and output path and does not expose separate clip downloads for larger batches. Output settings control container, codec and encoding CRF; -1 leaves CRF automatic. Video assembly supports 8-bit and 10-bit, with possible player or encoder compatibility limits for 10-bit. No audio is connected. Uploaded transparency is not preserved through the starting-image path because only the loader's image output is used. Camera choices condition generated motion rather than guaranteeing exact physical camera tracking.
Kling reference-guided video transformation
Transform a source video using a reference image and written editing instructions, returning one generated video. Upload both a source video and a reference image. Both uploads are required: this workflow always supplies the image to Kling and has no video-only mode. For a first run, choose a video showing the subject you want to change and an image showing the desired character or appearance. Replace or adapt the example prompt, which asks for a dancing person to become a rabbit while retaining the movement, background and camera sequence. Describe the changes, how to use the reference image, and what should remain consistent. Include unwanted content in the same prompt; there is no separate negative prompt. Choose landscape 16:9, portrait 9:16 or square 1:1, a generated duration of 3–10 seconds, and 720p or 1080p resolution. Keep original sound requests retention of the source audio. Model selection offers kling-video-o1 and kling-v3-omni. Motion, likeness, scene consistency and sound retention are requests rather than guarantees. Leave Seed at -1 to randomize it on each run. The provider uses the seed to control re-running; even a fixed seed does not make the generated video reproducible. Advanced video output settings offer file type and codec selection; both default to auto. Generation sends the supplied media and prompt to Kling and uses a paid provider call.
Beyond Negative Embedding
The Beyond Negative Embedding v4 is designed to improve image quality by enhancing resolution and sharpness while reducing disfigurement in generated images. Ideal for use with the SD 1.5 base model.
Create a HeyGen avatar from a prompt
Create a HeyGen avatar from a text description and save its returned avatar ID as a TXT record. For your first run, enter the required Avatar description with the appearance, clothing and visual style you want, then run the Pipe. The description is sent to HeyGen's prompt-based avatar creation node. The returned avatar ID is previewed and saved with the label “HeyGen Avatar ID:” using the filename prefix HeyGen/avatar_id. Keep the ID for later avatar-video jobs. This Pipe supports text-prompt creation only. There is no photo upload or selectable image-reference mode. The selected output is an avatar ID text record; this Pipe does not generate an avatar video.
EasyNegative
Original Hugging Face Repository Counterfeit-V3 (which has 2.5 and 2.5 as well) on Civitai - If you like this embedding, please consider taking the time to give the repository a like and browsing their other work on...
LTX-2.3: Text to video with audio
Create one video with generated audio from a scene prompt using LTX-2.3. Describe the scene, actions over time, camera movement, visual details, and desired sounds or dialogue. This graph accepts no image, video or audio uploads. For a first run, replace the example scene prompt and retain the defaults: requested size 1280 × 720, duration 5 seconds, 25 FPS, Enhance prompt enabled, Text-only mode enabled, and automatic output format and codec. The workflow generates video and audio together at half the requested spatial dimensions, applies fixed 2× video latent upscaling, then refines both and returns the combined result. Refinement runs every time. Enhance prompt chooses a generated rewrite as the video conditioning text. Disable it to encode your original wording directly. Advanced enhancement controls include sampled or unsampled text generation, token budget, sampling filters, template selection and text encoder LoRA strength. Temperature and the enhancement seed are relevant to sampled rewriting. Thinking mode is available only if the loaded text model supports it. Width and height request the final spatial size; latent alignment may affect realized dimensions. The initial latent receives half each dimension and has a source minimum of 64 pixels with a 32-pixel step. For aligned custom sizes, use final dimensions of at least 128 pixels in multiples of 64. Swap width and height for portrait framing. The retained 1280 × 720 default is preserved; arbitrary dimensions are not guaranteed to produce an exact requested size. Duration is positive whole seconds. Requested frame count is duration × FPS + 1. Use 1–120 FPS and keep the requested frame count at or below the audio latent's source limit of 1000. Video latent length has an eight-frame step, so frame alignment can affect the realized duration; for aligned custom timing, make duration × FPS a multiple of eight. Frame rate also controls video conditioning, generated audio timing and final playback. Text-only mode bypasses solid-color first-frame conditioning in both stages. Turn it off to use the chosen solid color, independently adjustable initial and refinement conditioning strengths, and conditioning compression. Color is a packed RGB integer: 0 is black and 16777215 is white. This mode uses a generated color image rather than an uploaded reference. Initial generation and refinement have independent seeds, CFG values, samplers and comma-separated noise schedules. The distilled LoRA strength affects both stages. Keep the supplied LoRA strength, Euler samplers and schedules for the first run. Negative conditioning is supplied to both stages, but ordinary classifier-free negative guidance has no effect at their default CFG of 1; increasing a stage's CFG makes its negative conditioning relevant. Generation, refinement and sampled prompt enhancement have separate seeds. Use -1 for fresh randomization, or fix every relevant seed when comparing settings. Advanced output controls select the video container, codec and encoding CRF. Keep their automatic settings and default CRF for the first run; the supplied evidence does not establish compatibility for every explicit container and codec pairing.
MiniMax H3 video with audio
Generate a widescreen video with accompanying audio from a text description using MiniMax H3. Describe the scene, action, visual style, camera movement, dialogue, sound effects, and music in the Scene and audio prompt. There is no image upload or separate negative prompt in this Pipe. For a first run, replace the example with a short scene suitable for the two-second duration default and retain the sampling defaults: 20 steps, res_multistep, simple scheduler, and denoise 1. The saved example describes five seconds; shorten its storyboard or increase Duration before using it. Prompt timestamps and camera directions describe your intent rather than guaranteeing exact cuts or timing. Duration is requested in seconds. At fixed 24 fps, the workflow rounds seconds × 24, applies a minimum of five frames, then snaps upward to a valid 17k+5 frame count. Two seconds produces 56 frames, about 2.33 seconds, so the delivered clip can be longer than requested. Output size is not adjustable here: the retained source resolution selector uses its saved 16:9, 0.4-megapixel settings. Advanced controls change generation: Seed -1 chooses fresh random starting noise each run; a fixed seed lets you compare changes with the same starting noise. Steps sets the sampling step count, Sampler selects the sampling method, Scheduler distributes noise levels across those steps, and Denoise selects the fraction of the noise schedule used. Lower denoise does not preserve an uploaded image because this Pipe has none. Video frames and audio are decoded from the same sampled result and delivered together as one video at 24 fps. Use the default 8-bit output for compatibility. The supported 10-bit option can retain smoother gradients but requires compatible encoding and playback. The configured MiniMax H3 diffusion model, Qwen3VL text encoder, video VAE, and audio VAE must be available in the execution environment. This Pipe does not expose model selection, image conditioning, end frames, or an audio-only output.
Stable Audio 3 audio creator
Create an MP3 audio clip from a written description using Stable Audio 3 Medium. No uploaded audio is required. Describe the sound source, instruments or materials, mood, rhythm, and production character you want. For a first run, keep the tropical-house example, Music category, Expand prompt enabled, and Duration at 150 seconds. Keep the source sampling settings: 8 steps, CFG 1, LCM sampler, simple scheduler, and Denoise 1. Run the tool and listen to the MP3 result. MP3 quality changes encoding and file size rather than the generated performance. Prompt expansion uses Qwen to elaborate your description. Category must be exactly Music, Instrument, SFX, or One-shot. Music requests an instrumental track; Instrument requests instrument-focused material; SFX describes effects or ambience; One-shot requests a short isolated sample. These are prompting modes, with no stem extraction or guaranteed seamless looping. Category does not change Duration automatically: set a shorter duration yourself for short effects or samples. Turn Expand prompt off to send your original description directly to audio conditioning. Category and expansion tuning then do not affect the selected conditioning. This selection does not promise that the runtime skips loading or executing every expansion dependency. Duration controls the empty audio latent in seconds. The connected latent node supports 1–1000 seconds. Use whole seconds because the expansion request converts Duration to an integer. Category templates contain their own length suggestions, so expanded wording can conflict with your requested duration; the latent duration remains controlled by Duration. Disable expansion when you want direct control over prompt wording. Text requests do not guarantee exact BPM or event timing. Audio seed and Prompt seed control separate random stages. Use -1 for fresh randomization. To compare audio settings with consistent wording, disable expansion or fix Prompt seed and retain the same expansion settings. Prompt sampling off disables text sampling; temperature and token-sampling controls apply to sampled expansion. Expansion length limit is measured in text tokens, not audio seconds. Thinking mode depends on model support, and generated text has no separate reasoning-text cleanup stage before audio conditioning. Negative prompt describes unwanted sounds. At the default CFG of 1, it does not contribute a positive-versus-negative guidance difference. Higher CFG changes that guidance behavior. Retain Denoise 1 for the first run because generation starts from an empty latent. Audio batch controls the number of latents generated together; larger batches require more memory. The runtime must provide the fixed source models: stable_audio_3_medium.safetensors in checkpoints and t5gemma_b_b_ul2.safetensors in text_encoders, supplied by https://huggingface.co/Comfy-Org/stable-audio-3; and qwen3.5_2b_bf16.safetensors in text_encoders, supplied by https://huggingface.co/Comfy-Org/Qwen3.5. These source dependencies are retained even though the supplied catalog has not resolved them.
Generate a background-removal mask
Generate a segmentation mask from an uploaded image with BiRefNet. The mask is returned as a separate output for compositing or downstream image processing.
Renaissance Style
A Textual Inversion Style Embedding trained on a beautiful late-medieval town archway scene. You can expect to get chaotic red brick/stone and wooden buildings, with floral accents, and a golden hue in your images by...
Wan 2.7 image to video
Animate an uploaded first-frame image into a 2–15 second video with prompted motion and automatically generated background music or sound effects. The uploaded image determines the video's aspect ratio. For a first run, upload your starting image, replace the example motion and scene prompt to match it, and keep 720P resolution and the 10-second duration. Describe the action, camera movement and atmosphere you want. The main prompt supports English and Chinese. The negative prompt describes unwanted visual features; its supplied Chinese default discourages artifacts, distorted anatomy, static scenes and unwanted text. Choose 720P or 1080P and a duration from 2 to 15 seconds in whole-second increments. Prompt enhancement is enabled by default and uses AI assistance to expand your instructions; disable it to submit your wording directly. Leave seed at -1 for randomization on each run, or enter a nonnegative seed to control generation variation. Enable watermark if you want an AI-generated watermark on the result. Under advanced video output settings, leave file type and codec at auto for automatic selection, or choose a container and video codec explicitly. This tool uses a remote API and requires configured provider access. It accepts one starting image. End-frame and audio uploads are not connected, so this tool does not offer an uploaded ending frame or uploaded audio to drive generation.
Wan 2.2 image to video
Generate one silent video from a starting image and a motion prompt using Wan 2.2's paired 14B image-to-video models. For a first run, upload an image, replace the example prompt with the subject's action and camera movement, and keep 640 × 640, 5 seconds, 16 FPS, batch size 1, and Fast mode off. Choose width and height in multiples of 16 to suit the image's composition. An upload is needed while the Source image stage is enabled. Disable that stage to generate without starting-image conditioning, and describe the subject and scene in the prompt as well as their motion. This mode retains the same image-to-video model pair. Uploaded transparency is not preserved by the connected RGB image output. Fast mode selects both Lightx2v acceleration LoRAs and the fast sampling controls. Defaults change from 20 steps, CFG 3.5, and handoff step 10 to 4 steps, CFG 1, and handoff step 2. Only the selected mode's steps, guidance, and handoff apply. Keep total steps between 1 and 10000, guidance between 0 and 100, and each handoff greater than zero and below its total steps. The two LoRA strengths apply only in fast mode. Both stages have independent sampler, scheduler, and noise-schedule shift controls; the supplied recipe uses matching Euler samplers, simple schedulers, and shifts of 5. Duration controls generation length. The graph requests floor(duration × FPS + 1) frames and uses the same FPS for playback. Use a positive duration and 1–120 FPS; choose duration × FPS as a multiple of four for the model's 4n + 1 frame convention. Defaults request 81 frames at 16 FPS, approximately five seconds. Increasing resolution, duration, or FPS increases generation work. Keep batch size 1 for one clip; larger batches still pass through a single video-assembly branch rather than separate clip outputs. Use seed -1 for a new random seed each run or a fixed seed to compare changes with the same initial noise. Advanced controls include a negative prompt for unwanted traits; its influence depends on guidance. The tool returns one video through Sweet Tea, using automatic container and codec selection by default. Available containers are mp4, mkv, and webm; explicit codecs are h264 and av1. Keep automatic selection unless you need a particular compatible combination. Eight-bit output is the default; 10-bit output requires compatible encoding and playback. The graph has no audio input, end-frame conditioning, or upscaling stage.
Z-Image realistic image generator
Write a scene prompt. The realism-focused negative prompt is editable; CFG and seed are also available. Leave seed at -1 to randomize it. Output size is fixed at 1280 × 1920.
All-in-One. Z-Image, Ernie, Klein, t2i, i2i, controlNet, inpaint, outpaint, LLM, WAN, Qwen image, SDXL, Chroma — v6.3
!!Please update Timesaver and RES6LYF nodes!!
Glorious Style
This is a DreamArtist Textual Inversion Style Embedding trained on a single image of glorious, imposing castles, towers, and ivy covered ruins. You can get stunning backdrops in your images by calling Style-Glorious...
Runway image generation
Generate images with Runway from a text prompt and an optional reference image. For a first run, leave Reference image disabled, replace the example portrait prompt with your desired subject, composition, lighting, and style, and keep Output format at 1024:1024 for a square image. Run the Pipe to view the generated images. To use reference guidance, enable Reference image and upload one image. The upload feeds the generator's optional reference-image input; keep the prompt focused on the desired result. Disable Reference image to return to text-only generation. This workflow exposes no reference-strength or exact-editing control. Output format controls the generation format. Use a value supported by the Runway node; 1024:1024 is the supplied square default. Generation uses the Runway partner API and requires configured API access and sufficient account credits. The prompt and enabled reference image are sent to the provider. Generated images are returned for preview through Sweet Tea's output transport; this graph does not permanently save them through SaveImage.
Flux Kontext image editing
Produce one image with Flux.1 Kontext dev using an uploaded image and written instructions. Use it for subject changes, background edits, style changes, or a new composition inspired by the reference. For a first run, upload a Source image, leave Second reference disabled, and replace the supplied swan portrait prompt with your own Edit instructions. Describe the desired change and anything that should remain unchanged. For example: “Change the background to a garden while keeping the subject's pose and clothing unchanged.” Keep the source defaults of Flux guidance 2.5, Denoise 1 and 20 Steps initially. For two references, enable Second reference and upload another image. The images are joined into one canvas before scaling and encoding. Explain each image's intended role in the instructions. In Reference layout, choose the second image's position, whether to match its adjoining dimension to the source, and an optional gap in pixels. Spacing color matters only when the gap is greater than zero. These layout controls apply only when the second reference is enabled. Output dimensions follow the reference canvas after automatic Kontext scaling; there are no independent width or height controls. Adding a second reference or changing its layout can change the output proportions. The encoded canvas supplies both the starting image and reference conditioning. Denoise ranges from 0 to 1: the default 1 allows full regeneration with reference conditioning, while lower values retain more of the starting canvas and can constrain the requested changes. Seed -1 selects a fresh random seed each run. Use a fixed seed to compare settings with the same starting noise. Steps controls the number of sampling steps; Sampler chooses the sampling algorithm and Scheduler chooses its noise schedule. The source defaults are 20, euler and simple. Flux guidance controls the model's prompt guidance. Sampling also exposes an independent Classifier-free guidance scale, retained at its source default of 1. There is no editable negative prompt; negative conditioning is zeroed internally. Uploaded transparency is not preserved because only the image loaders' RGB outputs are connected. Requests to preserve details are instructions to the model, rather than masked protection of particular pixels.
