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 41 745
Image glow
Create an image with a sampled, optionally tinted glow from an uploaded source image. For a first run, upload your image and run with the saved settings: Intensity 2, Radius 29, Glow tint #0a9299, screen blending and Threshold 100. These settings apply a teal-tinted effect rather than a neutral preview. Change intensity or radius and run again to compare. Set Intensity to 0 to preview the source without the effect. Intensity uses a unitless 0 to 100 scale and scales the glow before blending. Radius uses a 0 to 100 scale rather than direct pixel units: the sampling radius is 0.012 × Radius squared in pixels, so the saved value 29 gives about 10 pixels. Sampling includes slight spatial jitter. Radius 0 also disables the effect. Glow tint multiplies the sampled glow's colors. Enter an RGB hex color; #ffffff leaves those colors unchanged. The saved #0a9299 favors teal. Pure black #000000 skips the tint multiplication rather than suppressing the glow. Advanced controls choose brightness selection and blending. Threshold is an inverted 0 to 100 scale: low values favor bright samples, while high values include darker samples. The brightness selection has a soft transition. Choose the exact lowercase blend name add, screen, soft, overlay or lighten; enter it exactly if shown as a text field. Add sums the source and glow, screen combines their inverse values, and lighten keeps the larger value in each channel. Soft and overlay use tonal blends that can darken areas when the sampled glow is weak, so lowering intensity is not necessarily a fade back to the source in those modes. Intensity 0 disables every mode. Strong settings can clip colors to black or white. The active effect also adds a small deterministic dither. Output dimensions follow the source image. Uploaded transparency is not preserved because the image loader's separate alpha mask is unused. This output applies only glow; the other image adjustments in this family are separate tools.
Kling first and last frame video
Generate one video from a starting image, a motion prompt, and an optional ending image using Kling. Provider access is required; generation sends inputs to Kling and uses a paid provider call. The result is returned as a video preview. For a first run, upload the first and end frames, replace the example prompt to match your images, and keep the five-second, 1080p defaults. The end-frame stage starts enabled and needs an upload. To animate only the starting image, bypass the End frame stage; no end-frame upload is then needed. Describe subject motion, camera movement, desired appearance, and the transition in the motion prompt. The same field accepts desired and unwanted content; there is no separate negative prompt. Duration ranges from 3 to 15 seconds. Resolution offers 720p, 1080p, and 4k. Kling v3 Omni is the default model; Kling Video O1 is also selectable. Generate audio is supported only with Kling v3 Omni, so leave it off with Kling Video O1. Seed -1 randomizes each run; a fixed seed does not make provider results reproducible. The advanced Video output stage provides file-type and codec choices. Keep both on auto for the first run. This interface supports first-frame and first-to-last-frame generation. Storyboards remain disabled because editable segment prompts and durations are absent. Reference-image guidance is not connected in this Pipe.
Recraft V4 text to image
Generate one to six images from a written description using Recraft V4 or V4 Pro. No source image is required. The host environment must provide access to the Recraft API; prompts are sent to the provider, and generation incurs provider usage charges. For a first run, replace the example prompt with your subject, composition, lighting and desired style. Keep Recraft V4, Output size 1024x1024 and Image count 1. Leave Negative prompt blank unless you want to describe elements to discourage. Run the Pipe to receive the generated images. Select the model before setting Output size. These are separate controls: switching to V4 Pro does not automatically update the size. The source defaults are 1024x1024 for V4 and 2048x2048 for V4 Pro. Enter sizes as widthxheight in pixels. The complete model-specific size lists are not supplied, so other dimensions must be supported by the selected model or the provider may reject them. Image count ranges from one to six; model choice and image count affect provider usage cost. Leave Seed at -1 to randomize it each run. Seed controls whether the generation node re-runs; a fixed seed does not reproduce the same images because provider results are nondeterministic. This Pipe returns generated images through Sweet Tea's preview output. It does not expose palette or background-color controls: the source's color examples are disconnected from generation.
Grok video
Generate one short video using Grok from a text prompt, optionally guided by a starting image. For a first run, describe the scene, subject action and camera movement. Keep grok-imagine-video selected, leave Starting image disabled, and use the default six-second duration and 720p resolution. Run the Pipe to receive the video in Sweet Tea. To use a starting frame, enable Starting image and upload an image. This is optional for grok-imagine-video and required for grok-imagine-video-1.5. Describe how the pictured scene should develop. Selecting grok-imagine-video-1.5 requires a starting image even if your prompt is complete. Only that model supports 1080p; 480p and 720p are also available. Duration sets the video length from 1 to 15 seconds. Aspect ratio controls the video shape; choose a listed ratio or leave auto for automatic selection. Seed controls whether the provider request is rerun, rather than making the generated video reproducible. Leave it at -1 to randomize the rerun value each run; a fixed value does not guarantee identical results. Under Video output, leave File type and Codec at auto for automatic encoding selection, or choose an available format and codec. The output stage returns the video to Sweet Tea rather than saving it through the original SaveVideo node. Generation uses a paid Grok provider call and sends the prompt and any enabled starting image to the provider.
SwitchX Video Alpha Matte
Generate a separate automatic subject alpha matte video from a trimmed source clip with Beeble SwitchX. SwitchX performs the scene edit as part of this operation; this Pipe returns its matte video, while the edited color video is not included. For a first run, upload a source video, replace the example prompt with your desired scene edit, and keep 720p resolution, start time 0 and duration 5 seconds. Check that the segment contains no more than 240 frames at the source video's frame rate. Leave output file type, codec and CRF at their defaults. The reference image stage is disabled initially. To use it, enable the stage and upload an image to guide the background, lighting or costume. Supply a nonempty prompt of at most 2000 characters, an enabled reference image, or both. Disable the reference stage to use the prompt alone. Start time and duration are measured in seconds. Duration 0 selects the remaining clip, still subject to SwitchX's limits of 240 frames and approximately 2.77 megapixels per frame. Strict duration raises an error when the requested duration is unavailable instead of accepting a shorter segment. Output resolution selects the maximum processing resolution, rather than an exact width and height. Alpha mode remains fixed to Auto for automatic subject isolation. Fill produces no separate matte, and this graph provides no keyframe or custom matte inputs for Select or Custom operation. The returned matte is a separate video, not an edited color video with embedded transparency. Seed -1 randomizes the rerun seed on each run. Identical seeds do not guarantee identical SwitchX results. This workflow sends inputs to the Beeble provider and invokes its paid processing service.
HappyHorse reference-to-video
Create a short video from a character reference image and a scene reference image, guided by a motion prompt. Set resolution, aspect ratio, duration, seed, watermark, and output FPS; choose a HappyHorse 1.1 or 1.0 model. Video file type and codec are also selectable.
Quality Embeddings for Anime models
I made 2 basic quality embeddings as an alternative to the quality tags that are normally used with my checkpoints. They work of course also with any other IL/NAI-based anime checkpoint.
ElevenLabs voice isolation
Reduce background noise in a speech recording with ElevenLabs voice isolation and export the processed audio as an MP3. For a first run, upload your recording under Source audio, keep MP3 quality at V0, run the Pipe, and download the result. Advanced MP3 export settings also offer 128k and 320k; these change MP3 encoding rather than the isolation process. The entire uploaded recording is processed. This Pipe has no trim controls or adjustable isolation strength.
Product camera tour
Generate one silent product camera-tour video by joining three Kling clips between four Seedream-generated views. For a first run, upload a product photo in Source image and leave that stage enabled. Review the four required view prompts, then run with the default sizes, transition modes and encoding settings. The prompts request an opening close-up, a low wide view, a side view and a rear view against a white studio background. The closing prompt includes car-specific details; replace those for another product. Four images are generated internally, but the selected result is the combined video. For text-only generation, disable the Source image stage and explicitly describe the same subject and setting in all four prompts. The views are generated independently from those prompts, so subject consistency may decrease. Even with a reference, consistent appearance and camera-only movement are generation goals rather than guarantees. Edit each view's framing, camera position and setting to change the shot sequence. View seeds are independent; -1 requests randomization. Gemini compares each adjacent image pair and automatically supplies positive and negative motion prompts to Kling. Direct motion-prompt overrides are not exposed. Each transition has its own mode string in mode / duration / model_name format, guidance value from 0 to 1, and aspect ratio. Defaults use pro mode / 5s duration / kling-v2-5-turbo and 16:9 for all three clips. Use configurations supported by the source node; this draft does not enumerate additional mode strings. Planning seeds offer best-effort repeatability of Gemini responses. Keep all four generated images at matching dimensions because adjacent images are batched for planning. Custom width and height are in pixels and apply only when that view's size preset is Custom. When changing the video shape, set all three transition aspect ratios consistently and keep their resulting frame dimensions compatible. Mode changes must also preserve compatible clip dimensions and frame rates. The final assembly uses the first clip's frame rate for all frames, so differing clip frame rates can alter playback timing. Each view remains limited to one generated image to provide an unambiguous start and end frame. The clips are joined in opening-to-wide, wide-to-side, then side-to-rear order. Audio is not carried into the result. File type, codec and CRF control final encoding; auto and CRF -1 retain transport defaults. Image watermark toggles affect the generated keyframes used downstream. Automatic planning relies on Gemini returning a single line with the expected --no separator; a differently formatted response can prevent usable prompt extraction.
Four-reference portrait with Flux.2 Pro
Create one prompted group portrait from four character references with Flux.2 Pro. For a first run, upload one character image into each of the four required reference inputs, keep the supplied prompt and default settings, then run the tool. The prompt requests a softly lit editorial portrait with all four characters looking up toward an elevated camera. References reach the generator in the displayed order. Describe the composition, setting, lighting and style in the prompt, including which details from each reference should carry into the result. Rewrite the prompt to request other scenes or compositions using the same four references. Character fidelity and placement are guided by the references and prompt rather than guaranteed. Uploaded alpha masks are not used by this workflow. Width and height set output dimensions in pixels, each from 256 to 2048 in increments of 32. The default is 1920 × 1280; adjust both to choose the frame's aspect ratio. Prompt expansion is enabled by default and allows the provider to modify the prompt for more creative generation. Disable it to avoid automatic prompt expansion. Seed -1 selects a fresh random seed for each run. Set a fixed nonnegative seed to hold the noise seed constant while comparing changes to the prompt or other settings.
Anima anime image generator
Generate anime and stylized illustrations from text with the fixed Anima Preview 3 model. No uploaded image is required; the output is an image or a batch of images returned to Sweet Tea. For a first run, keep the supplied cyberpunk eye prompt or replace it with your subject, composition, lighting, and style. Use the negative prompt to describe unwanted traits. Keep the initial settings: 1024 × 1024 pixels, one image, 30 steps, CFG 4, sampler er_sde, scheduler simple, and denoise strength 1. Run the Pipe to receive the generated images; the output stage does not automatically save image files through ComfyUI SaveImage. Width and height are in pixels, in multiples of 8, and together determine the aspect ratio. Images per run sets the batch size. Larger dimensions and batches require more memory. Open Sampling for additional controls. Seed -1 randomizes each run; use a fixed seed when comparing changes while holding other settings constant. Steps set the number of denoising steps. CFG controls prompt guidance; excessive guidance can harm image quality. Sampler selects the sampling algorithm, and Scheduler selects its noise schedule. Denoise strength defaults to 1 for full generation; reducing it changes sampling strength and does not preserve an original image. The workflow uses anima-preview3-base.safetensors, qwen_3_06b_base.safetensors, and qwen_image_vae.safetensors, with Sweet Tea's image output node. These dependencies must be available in the execution environment. Model selection is fixed in this Pipe. This is text-only generation from an empty latent. References to preserving an original composition in the example prompt are text instructions, not image guidance or a guarantee of preservation. There are no reference-image, image-editing, or upscaling stages.
Video green screen
Replace a video's background with a solid green or blue chroma-key backdrop using Bria. Upload the video you want to process, leave Background shade on broadcast_green, and run. Download the resulting video and use your editor's chroma-key tools to remove the colored backdrop for compositing. Background shade offers broadcast_green (#00B140), chroma_green (#00FF00), and blue_screen (#0000FF). Choose a color that contrasts with the foreground. The output has a solid colored background; it is not a transparent video. Seed controls whether Bria processing reruns. Leave -1 to randomize on each run. A fixed seed does not make the provider's results reproducible. Under advanced Video output settings, leave File type and Codec on auto for a first run. Explicit container choices are MP4, MKV, and WebM; codec choices are H.264 and AV1. The supplied evidence does not establish support for every explicit pairing. Audio preservation is also not established by the supplied graph. Processing sends the video to Bria and uses a provider-priced API operation.
Lotus Depth
Upload a source image to generate a Lotus Depth map. Advanced controls let you choose the sampler and schedule, set the step count and denoise amount, and adjust initial sigma. Lotus conditioning is fixed; the default uses one inference step.
Veo video generation
Create one short video with Google Veo from a scene description, optionally guided by an uploaded image and with generated audio. For a first run, replace the example video prompt with your subject, action, setting, camera movement and visual style. Keep the default eight-second, landscape, 720p settings and leave Reference image bypassed for text-only generation. Audio generation is off by default. For image-guided generation, enable Reference image and upload an image. The image guides generation through Veo's optional image input; the prompt and output settings remain available in both modes. Choose 16:9 landscape or 9:16 portrait output and a duration of 4, 6 or 8 seconds. Use the negative prompt for unwanted content or visual traits. Enable Generate audio when wanted and describe intended sounds or speech in the video prompt. People generation lets you allow or block generation of people. Choose a Veo model and resolution. The available resolutions are 720p, 1080p and 4K; 4K is unavailable with Veo 3.1 Lite and Veo 3.0 models. Seed -1 selects a new random seed on each run. A fixed seed is a generation input and does not guarantee identical provider results. Video output contains optional file type and codec choices. Keep both on auto for a first run; these affect the returned video's encoding rather than its generated content. Generation uses an external, provider-priced Veo API. Your prompt and any enabled reference image are sent to the provider.
Love Potion
Do you have a problem with shy subjects in your images? Try this love potion to really break the ice.
Image relight
Create a relit version of an uploaded image using a lighting instruction, Qwen Image Edit, and a dedicated relighting LoRA. For a first run, upload an image and keep the default warm twilight instruction, denoise 1, relighting LoRA strength 1, and the sampling preset: 4 steps, CFG 1, Euler sampler, and simple scheduler. Run the Pipe to receive one edited image. To request another lighting setup, describe direction, time of day, color temperature, softness, and shadows. The relighting trigger is added automatically. The source image is resized before supplying both image conditioning and the initial latent. Output dimensions follow this preprocessing; there are no independent width or height controls. Lower denoise values retain more of the initial image's structure and can limit the lighting change. The default 1 allows a full denoising pass. Objects and details may change along with the light. Uploaded transparency is not preserved because only the loader's RGB image output is connected. Relighting LoRA strength controls the dedicated adapter independently of denoise; 0 removes its contribution while retaining the underlying image-edit model. The negative prompt describes unwanted attributes, but at CFG 1 it has no ordinary classifier-free exclusion effect. Increasing CFG enables its influence and changes sampling behavior. Leave it blank for the source preset. Use seed -1 for a new randomized run, or a fixed seed to compare instructions and settings with the same initial noise. Advanced controls also expose guidance normalization strength and mode, sampling shift, and Lightning adapter strength. Normalization before CFG can amplify the result; the source preset leaves it off. Start with the supplied values and evaluate changes together with CFG, steps, sampler, and scheduler. Removing or changing the Lightning adapter's influence changes the basis of the four-step preset. The workflow requires qwen_image_edit_2509_fp8_e4m3fn.safetensors, qwen_2.5_vl_7b_fp8_scaled.safetensors, qwen_image_vae.safetensors, Qwen-Image-Edit-2509-Relight.safetensors, and Qwen-Image-Edit-2509-Lightning-4steps-V1.0-bf16.safetensors. Installation sources are supplied, but the dependency records mark these artifacts MISSING_MODEL; this review does not establish that they are installed.
Autumn Style
This is a DreamArtist Textual Inversion Style Embedding trained on a single image of fall/autumn like colors. You can get amazing autumn/fall color effects in your images by calling Style-Autumn in the positive...
Krea 2 Turbo image generator
Create an image or batch of images from a text description using Krea 2 Turbo. No uploaded image is required. For a first run, replace the example image prompt, choose an aspect ratio, and keep the defaults: 1 target megapixel, one image, prompt refinement enabled, and Darkbrush disabled. Run the Pipe to receive the generated image batch in Sweet Tea. Prompt refinement uses the local text model with fixed prompt-expansion instructions. Turn it off to use your wording directly. Refinement can change the interpretation of a detailed prompt. Its token limit, sampling settings, seed, optional thinking mode, and model template are available under Refinement tuning. Thinking applies only if the model supports it. Sampling-specific controls apply when refinement sampling is on. Image sampling and prompt refinement have separate seeds. Use -1 for a new random seed each run. To repeat a setup, fix the image seed and either disable refinement or also fix its seed and settings. Enable Darkbrush to apply the fixed style LoRA and append the Style phrase to the direct or refined prompt. LoRA strength changes the model adjustment; the phrase separately changes text conditioning. Setting strength to zero still leaves the phrase appended. Disabling Darkbrush selects the base model and omits the phrase. This interface uses the fixed Darkbrush LoRA and does not select other style LoRAs. Aspect ratio and target megapixels jointly determine pixel dimensions. At the square default, 1 target megapixel is approximately 1024 × 1024. Increasing resolution or image count increases resource use. The selected output returns the whole image batch through Sweet Tea's preview transport; it does not permanently save images through ComfyUI SaveImage. Image sampling starts from an empty latent with 8 steps, CFG 1, Euler sampling, the simple scheduler, and denoise 1 by default. Advanced Image sampling controls change this process. Lower denoise values do not preserve an uploaded image because this workflow has no image input. Negative conditioning is zeroed, so there is no independent negative prompt.
Illustration to realism
Reinterpret an uploaded illustration as a realistic photographic image using Qwen Image Edit and the Anything2Real adapter. Upload an illustration and keep the default editing instruction for a first run, or describe the photographic lighting, materials, setting, and features you want retained. Begin with Denoise at 1, Realism strength at 1, and the supplied 8 steps, CFG 1, Euler sampler, and beta scheduler. The source image supplies both visual conditioning and the initial latent. This is a generative reinterpretation, so details and identity can change. Lower Denoise to retain more of the original structure, potentially leaving more of its illustrated appearance. Realism strength scales the Anything2Real adapter; setting it to 0 or bypassing the Realism adapter stage keeps prompt-driven image editing active without that adapter's influence. Use Seed -1 for a new random variation each run, or a fixed seed to compare changes with the same starting noise. Negative prompt can be left blank. At CFG 1, ordinary negative-prompt guidance has no effect; increasing CFG makes positive-versus-negative guidance meaningful. Steps, CFG, Sampler, and Scheduler remain independent tuning choices; start with the supplied settings rather than assuming larger values improve the result. Advanced settings expose Lightning strength, guidance normalization, and sampling shift. Lightning strength defaults to 1 for the supplied eight-step adapter; 0 removes its influence without changing Steps automatically. Guidance normalization has its own strength and a before-guidance switch: off uses post-guidance attenuation, while on applies unclamped normalization before guidance combination and can amplify the prediction. Sampling shift defaults to 3 and changes the model's noise schedule independently of the Scheduler choice. Output shape derives from the uploaded image through latent encoding; there are no independent resize controls. Uploaded transparency is not preserved because only the loader's RGB image output is connected.
