Skip to content

Creative Directions

ComfyUI & Workflows Latest

ComfyUI Ecosystem and Reusable Workflows: Nodes, process templates, batch production methods, and creator engineering practices.

199 picksLast 30 days 99 itemsCollected 1,541 items

updated

Pick archive · page 10

Sep 26Sat181–199
  1. 卡尔的AI沃茨 · 公众号公开订阅66

    Hands-on with LibTV 1.5's five new features: bringing a full film crew into the AI short-drama workflow

    LibTV 1.5 has launched, with the Agent upgraded to TV Director and five new capabilities: original and adapted scripts, a character styling room, director's direction, 3D-BOX, and creative opening titles. The author tested it with a period short drama: TV Director can plan a 50-episode outline and per-episode scripts in one go, and scripts support manual editing like a document or box-selecting to hand to the Agent for revision; the character styling room can sculpt faces to adjust features, hairstyles, body types, and clothing, and batch-replace related assets on the canvas.

    Why it matters: The author tests LibTV 1.5's script, character, storyboard and 3D previsualization workflow with a complete period-costume short drama, so readers can judge whether this workflow can replace existing production stages.

  2. NerdyRodent · YouTube 创作视频75

    Qwen Image 2.1 running locally in ComfyUI

    Nerdy Rodent releases a tutorial on how to run Qwen Image 2.1 locally in ComfyUI. Besides text-to-image, the model also supports image editing with up to 10 reference images, for face swapping, head swapping, background swapping, multi-character composition and natural-language style changes; the INT8 model file is under 8GB.

    Why it matters: Demonstrates the text-to-image, image-to-image, inpainting and upscaling workflows of Qwen Image 2.1 in local ComfyUI, which can be used to evaluate a local image generation setup.

Sep 25Fri
  1. GitHub:AI视频开源项目发现78

    SeeCut: Open-Sourced Auto-Editing Skill for Digital Human Voiceover, Built for Coding Agents

    YeJe-cpu open-sourced SeeCut on GitHub, a skill for coding agents like Claude Code that automatically edits digital human or real-person voiceover footage into vertical short videos with motion effects, and can optionally push the result as a layered CapCut draft for fine-tuning.

    Why it matters: The author open-sourced a reusable voiceover editing skill covering the full workflow from digital human voiceover to CapCut draft delivery.

  2. GitHub:AI视频开源项目发现65

    BridgeMind Open-Sources Desktop App BridgeClip, Cutting Long Videos into Subtitled Short Clips

    BridgeMind released the open-source desktop app BridgeClip, which can find complete clips from podcasts, livestreams, and interviews, then edit and export subtitled vertical 9:16 or horizontal 16:9 short videos. Video rendering is done locally, AI processing uses the user's own OpenRouter key, and it supports macOS, Windows, and Linux, with the installer bundling Python, FFmpeg, and yt-dlp.

    Why it matters: The open-source desktop tool chains long-video clipping, subtitling, and publishing into a single local rendering pipeline, enabling creators to evaluate how to repurpose their own assets.

Sep 23Wed
  1. Wireflow · AI短剧与视频制作教程66

    How to Create AI Song Ads on a Single Wireflow Canvas Without CapCut

    Wireflow publishes a tutorial on how to complete an 80-second AI music ad on a single canvas — from script, song, and word-level timeline to stills, motion, subtitles, and end credits — without ever exporting to CapCut or Premiere.

    Why it matters: A complete breakdown of the eight steps to produce an 80-second AI music ad, from writing lyrics to rendering, along with the actual cost of approximately 6,100 credits and a record of pitfalls encountered.

Sep 18Fri
  1. Theoretically Media65

    Theoretically Studio 4.0 Released: A Reusable AI Filmmaking Template

    Theoretically Media released Theoretically Studio 4.0, a reusable AI filmmaking template. The author used it to remake an old film made with Veo 2 in 2025, taking about a day and a half, using Seedance 2.5, GPT-6 Astra, and Runway's MCP connection during the process.

    Why it matters: The author remade an old film in a day and a half and publicly released a reusable AI production template and local dashboard, suitable as a reference for creators who want to build workflows.

  2. fal 官方博客62

    fal Details H3 Max: Built on the fal Inference and Training Platform

    fal's official blog explains how H3 Max completes the journey from post-training to distribution across its three-layer platform: Compute, Serverless, and Model API. H3 Max generates a 5-second video in under 3 seconds and ranked first in quality, prompt understanding, and aesthetics in fal's human preference evaluation; independent benchmarks from Artificial Analysis and Design Arena also ranked it first.

    Why it matters: fal officially breaks down the three-layer platform that takes H3 Max from training to launch, offering a look at the inference and scaling mechanisms behind low-latency video generation.

Sep 10Thu
Aug 25Tue
  1. Hugging Face Blog62

    Gradio launches gr.Workflow: turning AI pipelines into a drag-and-drop canvas with auto-generated APIs

    Gradio's built-in gr.Workflow describes AI pipelines as graphs of typed nodes, offering a drag-and-drop canvas where each node can run and intermediate results are visible; the same graph is also a REST API and can be deployed to Hugging Face Spaces with one click.

    Why it matters: Gradio turns multi-step AI pipelines into a visual graph and automatically exposes REST interfaces, giving teams a basis to assess migration costs against their existing production workflows.

Jul 23Thu
  1. Hugging Face Blog62

    Diffusers natively supports Nunchaku 4-bit diffusion inference

    A Hugging Face blog post explains that Diffusers now natively supports Nunchaku's 4-bit diffusion inference; loading a quantized checkpoint only requires calling from_pretrained(), with no local CUDA compilation needed.

    Why it matters: Nunchaku's 4-bit quantized inference is now natively integrated into Diffusers, allowing creators to evaluate the trade-off between VRAM usage and speed for image generation on consumer-grade GPUs.

Jul 23Wed
  1. Hugging Face Blog62

    Hugging Face Releases a Fast Inference Optimization for Flux LoRA

    Hugging Face releases a LoRA inference optimization for Flux.1-Dev, combining Flash Attention 3, torch.compile, and FP8 quantization to achieve a 2.23× speedup on H100.

    Why it matters: Provides a complete optimization recipe for Flux LoRA inference, including real-world data for hot-swapping and consumer-grade GPUs, which can be directly applied to your own image generation pipeline.

Jun 19Thu
  1. Hugging Face Blog62

    Hugging Face Tutorial: Fine-Tuning FLUX.1-dev with QLoRA on Consumer Hardware

    Hugging Face publishes a tutorial demonstrating how to fine-tune FLUX.1-dev on a single GPU using QLoRA and diffusers, with peak VRAM around 9GB. On an RTX 4090 at 512x768 resolution with LoRA rank 4, training for 700 steps takes approximately 41 minutes, whereas standard BF16 LoRA requires 26GB of VRAM.

    Why it matters: Hugging Face officially provides the complete workflow and measured VRAM data for fine-tuning FLUX.1-dev on single-GPU consumer hardware, which can be adapted for your own style training.

Jan 27Mon
  1. Hugging Face Blog60

    The Diffusers Team Surveys the State of Open-Source Video Generation Models and Optimization Approaches

    The Hugging Face Diffusers team publishes an article surveying the state of open-source video generation models and introducing how Diffusers supports these models. The article lists open-source models such as CogVideoX, Mochi-1, HunyuanVideo, Allegro, and LTX-Video, noting that high resource requirements, generalization ability, and latency are the main limitations.

    Why it matters: The Diffusers team systematically surveys the state of open-source video models and provides an optimization combination that reduces HunyuanVideo's VRAM usage to approximately 6.5GB.

Jan 14Sun
Jan 2Tue
  1. Hugging Face Blog62

    Hugging Face Releases Advanced Training Script for SDXL Dreambooth LoRA

    Hugging Face releases an advanced training script for SDXL Dreambooth LoRA, integrating Pivotal Tuning and the Prodigy optimizer into diffusers, along with reusable training parameters.

    Why it matters: Hugging Face officially integrates Pivotal Tuning and the Prodigy optimizer into diffusers training scripts, providing directly reusable parameters and experimental comparisons.

Jul 17Mon
  1. Hugging Face Blog60

    Hugging Face builds an AI WebTV video stream with Zeroscope and MusicGen

    Hugging Face released an experimental AI WebTV demo that uses the open-source text-to-video model Zeroscope and the music generation model MusicGen to automatically generate and stream short videos.

    Why it matters: It breaks down the complete pipeline for building an automatically generated video stream with Zeroscope, MusicGen, and FILM, and includes failure cases and prompt suggestions.

Mar 24Fri
  1. Hugging Face Blog62

    Train your own ControlNet with diffusers

    Hugging Face released a tutorial explaining how to train ControlNet with diffusers, walking through a three-step process using the face pose model Uncanny Faces as an example.

    Why it matters: Using the face pose ControlNet as an example, it walks through the full process of conditioning planning, dataset construction, and the diffusers training script, and provides low-VRAM parameter configurations.

Mar 3Fri
  1. Hugging Face Blog62

    Diffusers integrates ControlNet: a tutorial on using StableDiffusionControlNetPipeline

    Hugging Face integrated ControlNet into Diffusers and introduced StableDiffusionControlNetPipeline, which can control Stable Diffusion generation using spatial conditions such as depth maps, segmentation maps, scribbles, and keypoints.

    Why it matters: The official Diffusers documentation provides the complete way to integrate ControlNet, including reusable code for Canny, OpenPose, and multi-condition combinations.

Jan 26Thu
  1. Hugging Face Blog73

    Hugging Face explains how to efficiently fine-tune Stable Diffusion with LoRA

    Hugging Face published a blog post on how to efficiently fine-tune Stable Diffusion with LoRA, and LoRA training support is now available in diffusers, covering both Dreambooth and full fine-tuning approaches.

    Why it matters: The official diffusers documentation provides LoRA fine-tuning and inference scripts and notes that weights can be reduced to about 3 MB, making it easy for creators to evaluate a low-cost customization workflow.