Home Creators Posts Import Register Favorites Logout

Downloads

Content

Video : https://youtu.be/1tETo9M6OrQ

Hey everyone. New video is up, and this one is for anyone who's ever wanted real frame-by-frame control over an AI video - your camera, your character's pose, where every object lands.

The tool is SolarRenderer, a pair of LoRAs for MiniMax H3. You feed it a structure video - grey box blocks, a normal map, bounding boxes, even a stickman - and it renders that exact motion and camera into any world you want. In the video I turn a blocky rooftop jump into a modern-city Assassin's Creed style leap, with a female assassin diving off a tower onto an airbag in the plaza below. Same motion as the 3D blocks, every frame.

The fun part is how far the inputs stretch. A child's crayon drawing becomes a cartoon. A stickman becomes Robin Hood. Bounding boxes become a street with buses and pedestrians. And with the four-step LoRA, all of it samples in four steps - I paired it with FastH3-Omni and the new Singularity V2 for the action scenes and it runs fast.

One thing I show in the video that surprised me: the first frame alone can't carry the whole clip. When the 3D camera turns to an angle the first frame doesn't show, the render falls back to raw grey blocks - unless your text prompt describes that new scene in detail. Once I wrote the post-turn description properly, the grey houses turned into a modern city street with people walking. The prompt is half the pipeline.

If you've been stuck at DWpose and depth maps and want the full 3D-animation-level control, try SolarRenderer.

For Patreon Supporter, Additional content and resources for your membership post:

https://www.patreon.com/aifuturetech/posts/solarrenderer-h3-173451022

- Benji

Resources:

- SolarRenderer project: https://enderfga.cn/SolarRenderer/

- Model weights: https://huggingface.co/Enderfga/SolarRenderer

- SolarRenderer caption skill: https://github.com/Enderfga/SolarRenderer/blob/main/skills/solarrenderer-caption/SKILL.md

- comfyui-SelfLift: https://github.com/facok/comfyui-SelfLift
(paper: https://arxiv.org/abs/2609.02036)

- FastH3-Omni-Comfy: https://huggingface.co/FastVideo/FastH3-Omni-Comfy
- MiniMax H3 Singularity V2: https://huggingface.co/WarmBloodAban/Minimax-h3_Singularity

Calliope - Local-first Agentic Idea-to-video Studio https://github.com/benjiyaya/Calliope

Files

Minimax H3 New VideoToVideo Animation Pipeline Using SolarRenderer + FastH3-Omni + Singularity V2

SolarRenderer turns 3D structure videos into finished cinematic clips on MiniMax H3, and this video builds the complete ComfyUI workflow around it: the control LoRA and four-step LoRA from Enderfga, run with FastH3-Omni and MiniMax H3 Singularity V2. I test grey box blocks, normal maps, bounding boxes, stickmen and a crayon drawing as motion sources, render an Assassin's Creed style rooftop jump in a modern city, and show exactly why descriptive prompts decide whether the camera work survives. This one is for ComfyUI users who already generate AI video and want real frame-by-frame control over motion, placement and camera. If you've used ControlNet, DWpose or depth maps before and want the next level up, the workflow is built for you. Everything runs on MiniMax H3 with int8 models, so the pipeline is practical on a single GPU. What makes SolarRenderer different from native ControlNet support: the LoRA pair locks the motion to your reference video far more tightly, and the four-step LoRA cuts sampling to four steps. I also cover the SelfLift progressive sampler for two-stage resolution sampling, the causal LoRAs for block-by-block streaming, RTX VFX frame interpolation and super resolution, and the Qwen-Image-2.1 plus DWpose trick for first-frame generation. The biggest lesson in the video: when your 3D camera turns to an angle the first frame can't show, your text prompt has to describe that scene or the render falls back to raw blocks. Resources: Resources for Freebies: https://www.patreon.com/aifuturetech/posts/minimax-h3-new-173450100/?utm_source=youtube&utm_medium=video&utm_campaign=202610 - SolarRenderer project: https://enderfga.cn/SolarRenderer/ - Model weights: https://huggingface.co/Enderfga/SolarRenderer - SolarRenderer caption skill: https://github.com/Enderfga/SolarRenderer/blob/main/skills/solarrenderer-caption/SKILL.md - comfyui-SelfLift: https://github.com/facok/comfyui-SelfLift (paper: https://arxiv.org/abs/2609.02036) - FastH3-Omni-Comfy: https://huggingface.co/FastVideo/FastH3-Omni-Comfy - MiniMax H3 Singularity V2: https://huggingface.co/WarmBloodAban/Minimax-h3_Singularity Calliope - Local-first Agentic Idea-to-video Studio https://github.com/benjiyaya/Calliope If You Like tutorial like this, You Can Support Our Work In Patreon: https://www.patreon.com/c/aifuturetech #SolarRenderer #ComfyUI #minimaxh3 #aianimation

Comments

No comments found for this post.