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
20 affiché of 42 555
Regional Prompting with Regional LoRAs support — SDXL v1.0
ControlNet integration within regions can be tricky because ControlNet maps the reference image to the entire output image space, not to the mask space. This means that if the reference image contains a character in...
QWEN Image Edit 2511 Segment Inpaint, swap, local edit — v1.0
A workflow for segment editing, inpainting or swapping with Qwen 2511. 8192x4096 images can be very hard and slow to work with - but if you only need a single character it will probably be done within 20 seconds...
Klein I2I Fast Workflow - masked & unmasked w/ color match — v1.0
This is designed for Klein (or flux2), but the models & scheduler can be changed for other edit models.
LTX-2.3 FLV simple Workflow — v1.0
A simple (at least visually) Workflow for LTX-2.3 based on the official WF and RuneXX amazing work. Drop your image(s), select one or two passes and activate Sage Attention (optional) and type your prompt, length and...
Sunnypeak Commons - Jamie
Not much is known about Jamie, other than a limousine picks her up at least 3 times a week. She has a poodle named Dr. Pepper, and she likes to ride her motorcycle on Sundays. She seems to know all the important men...
Silicone Valley - Suzi
Suzi is a saltwater aquarium hobbyist and clownfish breeder. She enjoys Diana Ross albums and courtroom drama TV shows.
LtxApp360 - CUSTOM AUDIO DRIVEN 60 SECONDS VIDEO WITH 3 PROMPTS - i2v/t2v — v1.1
This version uses the newest ltx-2.3-22b-distilled-1.1.safetensors instead of the ltx-2.3-22b-dev-fp8.safetensors . It's heavier on VRAM but will get better results in almost the same generation time as version 1.0....
ZImageTurboPiD Upscale Decode Workflow — ZturbotoPiD
ZImageTurboPiDv2 +Color transfer from lora image as PiD tends to raise the gamma +Optional SageAttention +ModelSampling shift to PiD model Update your ComfyUI for PixelDiT support For models/text encoder INT8 Models
wan2.2_t2v_low_noise_14B_fp8_scaled
Wan 2.2 14B low noise Model
Anima Prompt Structure and Wildcard Workflow — v1.0
Moving to Anima from Illustrious has been daunting due to its reliance upon natural language descriptions to get quality results, whereas with Illustrious you relied upon tags with highly defined concepts as...
Wan 2.2 Daily Driver Workflow — v1.0
This workflow is the cleaned-up version of what I generally use when I'm rendering videos with Wan 2.2 or 2.1. It includes most of the options and settings that I most commonly use, so it's obviously tailored to work...
Basic Krea 2 Workflow
Important Update: The Fantastic Lora Loader is broken when using the latest version from the repository. Clone my fork of the repo here to fix it.
3D Asset to Futuristic Industrial Design Render — v1.0
3D Asset to Futuristic Industrial Design Render Transforms your 3D asset images into futuristic industrial design renders. By tweaking the lighting, materials, and composition, it gives your models a sleek, high-tech...
PixelWave
PixelWave FLUX.1-schnell 04 - Apache 2.0!
SDXL QR Code Art Generator — v2.0
Reduced the number of custom nodes
HS-Anima 4K Final Output Workflow — LoRA+Face Fix+Upscale
I will be offering 1,000 Patreon membership subscriptions to Civitai users, completely free of charge.
SDXL PONY ILLUSTRIOUS DMD2 Workflow By Stable Yogi — v2.0
DMD2 based Multi pass Workflow with VR2 Upscale extremely Fast and Detailed.
ComfyUI - Lossless Edit — FLUX Kontext Dev
Remove/edit any object with lossless quality - Flux Kontext Dev & Flow Assistor (ComfyUI)
Wan2.1 14B i2v (Native|GGUF) Self-Forcing(lightx2v) Single/Dual Sampling — 🟩v3 (SingleSamp)
Go here for Wan2.2 WF ≈➤ 🍥 Wan 2.2 (GGUF) [i2v / FFLF] + [t2v] Workflow
Vidu Q3 image to video
Animate a starting image into one short video, with optional generated dialogue and sound effects. Upload the required starting image and replace the example chase prompt with action and camera instructions suited to your image. For a first run, keep Vidu Q3 Pro, 720p and the supplied six-second duration. This Pipe uses the Vidu provider integration: configured provider authentication is required, the image and generation request are sent to the provider, and generation uses provider billing. The resulting video is returned to Sweet Tea's video preview output. The prompt may be empty and supports up to 2,000 characters. If you describe timed shots, keep their timing within the selected duration; changing Duration does not rewrite the prompt. Duration supports 1–16 seconds. Pro supports 720p, 1080p and 2K; Turbo supports 720p and 1080p. When switching from Pro at 2K to Turbo, also select a supported resolution. Generate audio is enabled by default. Describe desired dialogue and sound effects in the prompt, or disable it for silent video. Seed -1 randomizes each run; use a fixed seed when desired, without a guarantee of identical provider results.
