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

ComfyUI-Spectrum-LTX

Feature-level Spectrum acceleration for native ComfyUI LTXV / LTXAV models

MiniMax H3 Frame Rate Adjustment (Ac)

AnimaTagCompleter

An extension (custom node) for ComfyUI that suggests tags from booru sources. The extension is primarily designed for the Anima model.

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.

Text to video with SDXL and SVD

Generate a starting image from text with SDXL, then animate it into a short, silent video with SVD XT. For a first run, keep the supplied settings and example prompts, or replace the positive prompt with your subject, setting and desired appearance. Use the negative prompt for unwanted image features. Run the Pipe to receive the video. No image upload is required or exposed: the starting image is generated within this workflow. The selected output is video, without an independent still-image output or audio. The default video is 1024 × 576 pixels with 25 frames at 10 playback FPS, giving a 2.5-second clip. Change frame count and playback FPS together to control duration. Conditioning FPS defaults to 6 and influences SVD generation independently of playback FPS. Motion bucket and starting image noise are additional SVD conditioning controls; they do not specify an exact motion trajectory. Positive and negative prompts affect only the SDXL image stage. SVD animates that generated image and does not receive text conditioning directly. Starting image dimensions and video dimensions are independent; both default to 1024 × 576. Starting image dimensions are available in advanced settings. Image and video sampling have independent seeds, steps, guidance, samplers, schedulers and denoising amounts. Seed -1 randomizes that stage. Fix both seeds when comparing runs with the same starting image and animation noise. Video guidance varies linearly between the minimum guidance setting and the video sampler's maximum CFG; keep minimum at or below maximum for that relationship. Retain the default denoising amounts of 1 for the first run. Advanced playback settings include 8-bit or 10-bit video. The source notes possible player and downstream compatibility limitations for 10-bit. Video output settings offer automatic selection or explicit container and codec choices, plus a separate encoding CRF setting. These encoding controls do not change the generation prompts or sampling guidance. The workflow uses sd_xl_base_1.0.safetensors and svd_xt.safetensors from the source's Stability AI model references, loaded from the checkpoints directory, plus Sweet Tea's video output node. Those models must be available to the runtime. The selected graph always includes both image generation and video generation; it has no upload mode or bypassable stages.

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.