Aller au contenu

Répertoire des ressources

Trouvez ce dont vous avez besoin pour votre flux de travail.

Guides: techniques, setup, and troubleshooting

Recherchez 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 42 663

Flux de travailCivitai

【WAN2.2】KONTEXT to VIDEO — v1.2

Change of execution order between interpolation and upscaling, really independent and better optimized.

MultiCLIP ViT-L/14
Statut
PrésentéUnrated
Flux de travailCivitai

Inpaint Anyone or Anything Anywhere Doing Whatever Seamlessly With Krita, Kontext, and Nunchaku — v3.0

Taking advantage of a new node

MultiFLUX.1 Kontext [dev]
Statut
PrésentéUnrated
Flux de travailCivitai

multi-WAN-KR (WAN 2.2 I2V clip combine workflow) — v1.2.2

V1.2.2 adds automatic toggle for landscape/portrait derived from input image.

UpscalingWan 2.2
Statut
PrésentéUnrated
ModèleCivitai

WAN-L.O.V.E. Low VRAM Image-to-Video Fast All-In-One

WAN-L.O.V.E. is hybrid Wan L ow O verhead V RAM E fficiency Image-to-Video Fast (4-step) All-In-One model (full checkpoint: UNET, CLIP and VAE). All you need to encode source images is this model and, optionally,...

CheckpointWan Video 14B i2v 720p
Statut
PrésentéUnrated
Flux de travailCivitai

FluxKontextDev-Lora General workflow通用工作流 — v1.0

Workflow for FluxKontextDev-Lora, a general model for the Phantasm series

MultiFLUX.1
Statut
PrésentéUnrated
Pack de nœudSource externe

ComfyUI-42lux-Hildegard-Refiner

ComfyUI-42lux-Hildegard-Refiner Tile-based refinement nodes for ComfyUI, built around the Hildegard-Refiner reference-latent scheme. Designed for FLUX.2 Klein.

3 nodes@42lux
Statut
VérifiéUnrated
Flux de travailCivitai

SVI 2 PRO with First/Last Frame (Keyframes) // Video Continuation // 3-Stage Loop Automation — SVI2Pro+FLFVideoExtension

Video continuation with keyframes

Image to videoWan
Statut
PrésentéUnrated
Flux de travailCivitai

Flux with Skin_Detailer [ComfyUi] — Detail Daemon + NI

Update 26.11.24 This workflow eliminates the need for a face and skin detailer. The idea is to render directly at a significantly higher resolution and then correct any imperfections in the image using a simple...

MultiFLUX.1 [dev]
Statut
PrésentéUnrated
Flux de travailCivitai

Wan2.2 i2v gguf + lightx2v lora — i2v_v1

My simple 4steps workflow which I use to generate videos from image on my rx 6800xt graphics card.

Image to imageWan 2.2 I2V A14B
Statut
PrésentéUnrated
Flux de travailCivitai

LTX-2.3 I2V AudioSync Simple Workflow V4b (RTX-VSR)

v4: High-speed upscaling is now possible using " RTX Video Super Resolution " without compromising image quality.

MultiLTX-Video
Statut
PrésentéUnrated
ModèleCivitai

The Alleyways of Seoul (Scenic, background, NSFW samples)

Simple aesthetic gradient "trained" with 30 images of various alleyways in the Gangnam area. Make sure you have the aesthetic gradients plugin installed, then place the file in the extension folder.

AestheticGradientSD 1.5
Statut
PrésentéUnrated
Pack de nœudSource externe

ComfyUI_PromptQueue

ComfyUI custom node: batch prompt queue from multiline/text file with incremental per-run consumption and {p} templating.

5 nodes@cyan9977
Statut
VérifiéUnrated
Pack de nœudSource externe

ComfyUI-QwenPromptRewriter

Enhance your prompts using the Qwen LLM to align the behavior and capabilities of the Qwen-Image/Edit online version | 使用千问大模型对提示词进行重写, 以对齐 Qwen-Image/Edit 在线版的效果和能力

4 nodes@lihaoyun6
Statut
VérifiéUnrated
Pack de nœudSource externe

ComfyUI-Flux-Continuum

A modular workflow for FLUX inside of ComfyUI that brings order to the chaos of image generation pipelines.

30 nodes@robertvoy
Statut
VérifiéUnrated
Pack de nœudSource externe

ComfyUI-Wan-VACE-Prep

ComfyUI nodes designed to help make common video editing tasks with video generation models less complicated. Smooth transitions, extensions, outpainting. Primarily designed for Wan VACE, with some LTX-2 support.

12 nodes@stuttlepress
Statut
VérifiéUnrated
Pack de nœudSource externe

ComfyUI-ImageAutotone

A node for ComfyUI that takes an input image and clips the color channels independently to increase contrast and alter color cast. This is a reinterpretation of PhotoShop's "Auto Tone" algorithm.

1 node@SparknightLLC
Statut
VérifiéUnrated
Pack de nœudSource externe

face-upscaling-and-seamless-embedding

FUSE KSampler is a face-aware KSampler node for ComfyUI that provides seamless face upscaling and embedding capabilities using YOLO face detection and SAM (Segment Anything Model) for precise masking.

5 nodes@WASasquatch
Statut
VérifiéUnrated
ModèleCivitai

Dark Victorian Aesthetic

Bustles, big hats, crinolines, and corsets. An aesthetic gradient trained mostly on pictures of Victorian clothing that produces a dark, gothy look suitable for vampires and being out on the moor alone.

AestheticGradientSD 1.5
Statut
PrésentéUnrated
Pack de nœudSource externe

ComfyUI-Global-Memory-Trim

ComfyUI custom node for global native heap trimming on Linux/WSL2, with automatic per-node cleanup and manual memory trim/status utilities.

2 nodes@xmarre
Statut
VérifiéUnrated
Pack de nœudSource externe

ComfyUI-fp8_cublas

ComfyUI custom node that patches loaded models (Flux, SDXL, etc.) to run Linear layers in FP8 or MXFP8, unlocking tensor-core throughput on Ada Lovelace (RTX 4090) and Blackwell (RTX 5090) GPUs.

1 node@marduk191
Statut
VérifiéUnrated