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
20 angezeigt of 42.662
Magazine packaging presentation: mechanisms and practical controls
Create a magazine-in-packaging image through two generative stages, with independent cover and presentation settings.
LTX-Video text to video
Generate a silent video from a scene description using the fixed LTX-Video 2B v0.9 model and T5 text encoder. No source image or video is required. Describe subjects, actions, camera framing or movement, lighting and visual style in the positive prompt. Use the optional negative prompt to describe unwanted qualities. For a first run, replace the example positive prompt, then keep 768 × 512 pixels, 97 frames, batch size 1, 30 steps, prompt guidance (CFG) 3 and the Euler sampler. Keep Add noise enabled and output container, codec and quality on their automatic defaults. Run the Pipe to receive one video without audio. At the default playback rate of 24 FPS, 97 frames produce approximately 4.04 seconds of video. Use dimensions in multiples of 32 and frame counts of 8n + 1, such as 49, 97 or 145. Width and height determine the aspect ratio. Increasing dimensions, frame count or batch size increases resource use. Batch size above 1 generates multiple samples whose decoded frames enter the same video creation node; it does not provide separate video outputs. Playback FPS controls how quickly the returned frames play and therefore the clip duration. Conditioning FPS supplies the intended motion rate to the model. These independent fields default to 24 and 25 respectively; set both to the same value for matching generation and playback timing. Changing playback FPS does not generate or interpolate additional frames. Seed -1 randomizes each run. A fixed seed reuses the starting noise with unchanged settings. Steps, prompt guidance and sampler control sampling; maximum shift and base shift adjust the latent-dependent noise schedule rather than playback timing. Retain their supplied defaults for an initial run. Disabling Add noise skips starting-noise initialization, but this workflow still uses an empty latent rather than a source video. Video playback offers 8-bit and 10-bit output. The 10-bit option can retain smoother gradients, but some players and downstream nodes may not support it. Under Video output, choose automatic encoding or select a container and codec compatible with your intended player. Leave quality (CRF) at -1 for automatic quality selection. This Pipe has no image upload, audio input, interpolation or separate batch-output branches.
VideoFlow - LTX 2.3 All-in-One T2V / I2V / A2V / Stable Character Voice, Wan 2.2/2.1 I2V workflow — LTX 2.3 All-in-One v3.0
Text-to-Video Support with a pre-configured set of LoRAs for creating photorealistic videos.
Google Nano Banana 2
Generate an image with Google's Nano Banana 2 Comfy Partner Node and return it through PreviewImage without a duplicate ComfyUI save.
Civitai Grok Text to Video
Generate a native MP4 with Civitai Grok and transport the original bitstream through SweetTeaPreviewVideo without transcoding or duplicate saves.
Civitai GPT Image 1
Generate an image with Civitai GPT Image 1 and return it through PreviewImage without creating a duplicate ComfyUI output save.
fal.ai Nano Banana Image
Generate an image through fal.ai's async API, retain the provider request ID and cost estimate, and return it through PreviewImage without duplicate saves.
Civitai SDXL + LoRA Stack
Select an SDXL checkpoint and build a zero-to-many Civitai LoRA stack in Studio, then generate through Civitai and PreviewImage.
ByteDance Seedream Image
Generate images with ByteDance Seedream through Comfy Partner Nodes and return them through PreviewImage without duplicate saves.
Google Veo 3 Video
Generate native video with Google Veo 3 and transport the original bitstream through SweetTeaPreviewVideo without a duplicate ComfyUI save.
Anima Workflows — V7.0
(This is not an exhaustive changelog)
SeedVR2: one-step 4X video/image upscaling (and beyond) with BlockSwap and great temporal consistency — v1.0
Restore and upscale any video to 4X and beyond in a single step with ByteDance's revolutionary SeedVR2. Tutorial update for SeedVR2.5
Wan 2.2 - All in Wan I2V (I2V, F2LF, SVI with optional F2LF, NAG, LTX for V2A, Pulse of Motion, Lora Optimizer, CFG-Ctrl, 4 modes, ...) — v2.1
Some important bug fixes, including:
Video upscaler and Interpolator [RIFE VFI + Nvidia Video Super Resolution] — v1.0
First version release
Z-Image Turbo + Controlnet (with LoRA fix) + 4k Upscaling + Detail Daemon — v1.0
First release
Z Image Turbo Workflow by Stable_Yogi🔥 — ZImage Turbo V3.1
Fixed the Lora Loader to be more usable.
All MiniLM L6 v2
This is a sentence-transformers model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search.
All Mpnet Base v2
This is a sentence-transformers model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
[NEW]Krea2 & LTX2.3 & ideogram 4 WF in collection — LTX2.3REDMixKrea2
》 RED MOSS - 图片 - T2I -LCS-6STEPS v1 10/19 付费工作流-模型页面 ⚡
Azure ColdSnap
Azure Coldsnap is the anime and humanoid-focused counterpart to Azure Starfire . This model emphasizes clean composition , stable generation , and balanced background detailing avoiding cluttered or overly complex...
