AI Film Daily · Monday, October 26, 2026
AITVHOT
Hongguo Short Dramas discontinues its coin feature, as short drama platform competition shifts toward content revenue sharing
Hongguo Short Dramas announced it will discontinue its coin feature in phases, with coins expected to no longer be offered to new users starting November 1, a full discontinuation for all users by the end of the year, and the launch of rest reminder and sleep reminder mechanisms. Tencent's Green Bubble short drama mini program enters with up to 100% comprehensive incentives and revenue sharing based on average per-user watch time, while Hongguo guides toward premiumization by adjusting the revenue-sharing coefficients for animated dramas and offering cash rewards for high-quality single-title dramas. The article notes that producers still face uncertainties such as the high cost of trial and error in pursuing premium content and undisclosed per-unit revenue-sharing prices.
Tools and Workflows
comfyui_davcha_editor released: masking, preprocessing layers, and editable OpenPose inside the Load Image node
The author released the ComfyUI custom node comfyui_davcha_editor, which adds a full-screen editor to Load Image, supporting cropping, padding, rotation, soft-brush masking, and undo/redo; edits are saved in the workflow without modifying the original file.
Open-Source Local Video Tool Kinoloom Released, Supporting 8GB VRAM and Latent-Space Long-Take Stitching
The author has open-sourced Kinoloom, a local video generation tool that runs on ComfyUI. It supports video models such as LTX 2.5, MiniMax H3, and Wan 2.2, as well as image models such as Qwen image 2.1, and can generate videos on consumer-grade GPUs with 8GB of VRAM.
Tips and Opinions
Author generates 4K video with MiniMax H3 in ComfyUI on 6GB of VRAM
The author built a MiniMax H3 workflow in ComfyUI, combining SelfLift progressive resolution sampling with a DLSS 5 upscaling node to output 2K or 4K video on an RTX 3060 with 6GB of VRAM. In their 6GB VRAM environment, generating and upscaling to 4K took about 35 minutes, with parameters of 8 steps and 0.6 megapixels, all without additional model training; both the workflow and the DLSS5 DLL download links have been released.
MOSS-Image Locally Generates Storyboards and 絵コンテ — Japanese Text Renders Correctly Too (Prompt Included)
MOSS-Image in ComfyUI produces a 6-panel storyboard with Japanese descriptions and a table-based 絵コンテ in a single generation. All 18 Japanese descriptions across 3 イメージボード works rendered correctly, while 4 typos appeared across 2 pages of 絵コンテ. Single image generation takes approximately 18–40 seconds on an RTX 3060. The author provides region-separated Prompt writing techniques and a ComfyUI-MOSS-Storyboard custom node workflow.