Encontre o que você precisa para seu fluxo de trabalho.

🌀 Visual Regional Prompting – Overlapping Regions, Brushes & LLLite Control

Visual Regional Prompting for ComfyUI

Vidu Q2 two-subject video

Generate one video featuring two reference subjects, with prompt-directed action, camera movement and optional generated audio. Upload one reference image for each subject; both uploads are required. Refer to the first as @subject1 and the second as @subject2 in the prompt. This interface supplies one image per subject. The references guide appearance rather than defining exact start or end frames. For a first run, upload both references, adapt the example prompt to their appearance, and keep the 5-second, 16:9, 720p defaults. Describe the setting, each subject's actions and the camera movement. Keep the requested action appropriate to the selected duration. Duration supports 1–10 seconds. Choose 720p or 1080p resolution and landscape, portrait or square framing through Aspect ratio. Movement selects auto, small, medium or large motion amplitude for objects in the frame; specify camera direction in the prompt. Generate audio is enabled by default. Include speech and sound directions in the prompt to request generated speech and background music, or disable it for video without generated audio. Seed -1 randomizes each run; a specified seed requests a particular generation variation. This tool uses the paid Vidu Q2 partner service and sends reference images and generation instructions to the provider. It returns one video for preview in Sweet Tea.

Topaz creative upscale

Upload an image to produce one enhanced image at a scale-based size with Topaz Reimagine. For a first run, keep the 4× scale and creativity of 3; leave the enhancement prompt empty or describe details and appearance to guide the result. Scale multiplies the source width and height, approximately preserving its aspect ratio. Values below 1 request a smaller image. Keep each calculated dimension within 32,000 pixels. The sizing branch supplies dimensions; Topaz receives the original image directly. Processing sends the image to Topaz's external service. Creativity controls reinterpretation on a 1–9 scale; inspect details that must remain faithful to the source. Subject detection offers All, Foreground, and Background modes. Enhance faces enables additional face treatment; Face creativity and Face sharpness apply when it is enabled. Preserve face identity and Preserve colors request retention of facial identity and original colors. Crop to fill crops instead of letterboxing when output and source aspect ratios differ. Scale-based sizing normally preserves the source aspect ratio, so this setting usually has little effect. The model is fixed to Reimagine, and independent width and height overrides are unavailable. Uploaded transparency is not retained through the connected RGB image path.

Topaz video enhancement

Enhance an uploaded video to 1080p or 4K, optionally add frame interpolation, and receive one processed video. For a first run, upload your source video and keep Starlight (Astra) Fast, FullHD (1080p), interpolation Disabled, and compression Low. Leave the advanced output settings at their defaults. Configured Comfy partner API access is required: the video is sent to the Topaz partner API for provider-priced processing. Choose an enhancement model and target resolution to enhance the video. Resolution applies only when enhancement is enabled. Select apo-8 to enable interpolation; choose Disabled for the enhancement model if you want interpolation alone. Keep at least one operation enabled. Model-specific creativity, scene prompts, sharpness, and realism controls are not exposed. Interpolation frame rate and slow-motion controls are also not exposed; these settings rely on the node's schema defaults. Compression level controls the Topaz CQP processing setting. Advanced video output controls separately select the final container, codec, and CRF encoding quality. Available containers are auto, mp4, mkv, and webm; available codecs are auto, h264, and av1. Choose compatible container and codec settings for your playback software.

Vidu Q3 text to video

Generate one short video from a text description of the scene, action, camera movement and visual style, with optional generated sound. No uploaded media is required. This uses the Vidu partner API, requires authenticated provider access and makes a paid provider call; your prompt is sent to the provider. For a first run, use the included neon street-chase prompt with Pro, six seconds, 16:9 framing, 720p resolution and sound enabled. Replace the prompt to create your own scene. Keep it within 2000 characters and align any requested shot timings with the selected duration. Choose Pro or Turbo, one of five aspect ratios, 720p or 1080p resolution, and a duration of 1–16 whole seconds. Enable sound when describing desired dialogue or sound effects; disable it for silent video. Prompt details express the desired result and do not guarantee exact shot timing or dialogue. Leave seed at -1 for a fresh random seed each run, or enter a fixed seed. The generated video is returned for preview with automatic format and codec selection.

Sd3 Medium Backup

stabilityai-nc-research-community

Siglip2 So400m Patch14 224 Vision

> Note: This is a stripped-down copy of google/siglip2-so400m-patch14-224 containing only the vision tower. It encodes images / video frames into the shared embedding space and is meant to be loaded on its own at...

Seedance 2.0 text to video

Generate one video from a text prompt with a selectable Seedance 2.0 model and optional generated audio. No uploaded media is required. Configured ByteDance provider access is required; generation sends the prompt to the provider and uses a paid API. For a first run, keep Mini, 720p, 16:9, five seconds, and audio enabled. Use the supplied space-battle prompt or replace it with your subject, setting, action, camera movement, and visual style. Describe desired sound when audio is enabled. The example's '8K' wording is a style instruction; the Resolution field controls output resolution. Choose Seedance 2.0, Fast, or Mini, then check the resolution. Resolution is entered as text and must be supported by the selected provider model; this interface does not enumerate model-specific choices. Duration accepts 4–15 seconds in whole-second increments. Update prompt timing when changing duration. Aspect ratio controls frame shape, with an adaptive provider option also available. Disable Generate audio when audio is unwanted. Watermark requests a provider watermark and is disabled by default; remove the example's 'no watermark' instruction if enabling it. Seed -1 randomizes each run. A fixed seed does not guarantee reproducible results; the source uses it to control whether generation re-runs. The generated video is returned through Sweet Tea's video output. Advanced Video encoding controls provide file type, codec, and CRF settings. Keep file type and codec on auto and CRF at -1 for a first run. These settings configure output encoding, while the generation controls determine the video's content and dimensions.

ComfyUI-Inpaint-CropAndStitch

ComfyUI nodes to crop before sampling and stitch back after sampling that speed up inpainting

comfyui-minimax-h3-audio-T8

ComfyUI-Hunyuan3DWrapper

ComfyUI-Detail-Daemon

A port of muerrilla's sd-webui-Detail-Daemon as a node for ComfyUI, to adjust sigmas that control detail.

ComfyUI-QwenVL

ComfyUI-QwenVL custom node: Integrates the Qwen-VL series, including Qwen2.5-VL, Qwen3-VL, Qwen3.5-VL, Qwen3.6-VL (MoE), and Qwen3.8-VL, with GGUF support for advanced multimodal AI in text generation, image...

sdxl_prompt_styler

Custom prompt styler node for SDXL in ComfyUI

ComfyUI-FlashVSR_Ultra_Fast

Real-Time Diffusion-Based Streaming Video Super-Resolution / 基于Diffusion架构的实时视频流超分模型

Comfyui-zhenzhen

https://ai.t8star.org/register?aff=dP7j Comfyui的各种平价API调用节点,支持seedance2.0(满血版,支持真人,不排队)

z-tipo-extension

A sd-webui extension for utilizing DanTagGen to "upsample prompts".

ComfyUI-DyPE

ComfyUI DyPE+SEGA, enabling artifact-free 4K+ image generation: Z-Image, Qwen, Flux, Krea2

ComfyUI-Distributed

ComfyUI extension that enables multi-GPU processing locally, remotely and in the cloud