Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

In this setup, a Blender blockout provides the motion and composition while a reference image guides the environment, subject, and textures with MiniMax H3. With open weights, you can previs the final look locally for free or run it on Comfy Cloud. To try this workflow, link below 👇

ComfyUI

58,830 subscribers

34,344 views • 1 month ago •via X (Twitter)

Arts Science & Technology Education

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

SAM 3D Body is open-source, so it can be run locally or on Comfy Cloud. Extract motion from a recording → bring it into Blender → control the camera → use the result with Seedance 2.5 More control over body motion and camera movement. To try this workflows, links below 👇

SAM 3D Body is open-source, so it can be run locally or on Comfy Cloud. Extract motion from a recording → bring it into Blender → control the camera → use the result with Seedance 2.5 More control over body motion and camera movement. To try this workflows, links below 👇

ComfyUI

123,946 views • 1 month ago

$Seedance 2.5 tends to pick up more natural movement and follow 3D blockouts more closely—but sometimes the results are nearly 1:1 with MiniMax. MiniMax ran at a fraction of the credit cost in this Comfy Cloud test, or can be run locally for free. Both have their place. It comes down to the use case, the results you need, and how much room you have to iterate. To try this workflow, link below 👇$

Seedance 2.5 tends to pick up more natural movement and follow 3D blockouts more closely—but sometimes the results are nearly 1:1 with MiniMax. MiniMax ran at a fraction of the credit cost in this Comfy Cloud test, or can be run locally for free. Both have their place. It comes down to the use case, the results you need, and how much room you have to iterate. To try this workflow, link below 👇

ComfyUI

33,089 views • 1 month ago

Less than a minute to generate this shot with MiniMax H3 Max via Partner Nodes. It works quite well for fast video-to-video experiments, especially when starting with a basic blockout + reference images. The workflow also includes an option to upscale to 2K. To try this workflow, link below 👇

Less than a minute to generate this shot with MiniMax H3 Max via Partner Nodes. It works quite well for fast video-to-video experiments, especially when starting with a basic blockout + reference images. The workflow also includes an option to upscale to 2K. To try this workflow, link below 👇

ComfyUI

79,571 views • 21 days ago

SAM 3D Body turns video into motion capture, full-body 3D mesh from footage. Runs in ComfyUI, locally or on Comfy Cloud. Extract motion from a recording → bring it into Blender → control the camera → use the result with Seedance 2.5 More control over body motion and camera movement. To try this workflows, link below 👇

SAM 3D Body turns video into motion capture, full-body 3D mesh from footage. Runs in ComfyUI, locally or on Comfy Cloud. Extract motion from a recording → bring it into Blender → control the camera → use the result with Seedance 2.5 More control over body motion and camera movement. To try this workflows, link below 👇

ComfyUI

26,080 views • 1 month ago

Using Blender camera animation with Seedance 2.0 gives you a lot more control over your shots. By keyframing the camera in Blender, you can precisely define movement, rotation, and framing, then bring that motion into Seedance. It's a great workflow for previs-style blockouts or any shot where intentional camera movement matters. To try this workflow, link below 👇

Using Blender camera animation with Seedance 2.0 gives you a lot more control over your shots. By keyframing the camera in Blender, you can precisely define movement, rotation, and framing, then bring that motion into Seedance. It's a great workflow for previs-style blockouts or any shot where intentional camera movement matters. To try this workflow, link below 👇

ComfyUI

14,712 views • 3 months ago

Music video test in MiniMax H3. Five generated reference stills, one subject, four locations,j plus an audio track, all in a single context. It returned the location cuts already in the clip. To try this workflow, comment 'Comfy' and we'll send it to you! 🔗

Music video test in MiniMax H3. Five generated reference stills, one subject, four locations,j plus an audio track, all in a single context. It returned the location cuts already in the clip. To try this workflow, comment 'Comfy' and we'll send it to you! 🔗

ComfyUI

26,550 views • 2 months ago

MCode CLI + Blender + H3 = blockout to cinematic rescue Why MCode CLI fits this workflow: >Reads and edits your Blender scripts. >Runs builds, renders and checks in the terminal. >Automates workflows with `mcode exec`. >Resumes sessions for the next iteration. Set the poses and camera moves in Blender Give H3 the reference video and a prompt for the final look.

MCode CLI + Blender + H3 = blockout to cinematic rescue Why MCode CLI fits this workflow: >Reads and edits your Blender scripts. >Runs builds, renders and checks in the terminal. >Automates workflows with `mcode exec`. >Resumes sessions for the next iteration. Set the poses and camera moves in Blender Give H3 the reference video and a prompt for the final look.

Karan

35,851 views • 1 month ago

GPT-6 Astra + MiniMax H3 A workflow I've been experimenting with: First, used GPT-6 Astra with Blender to create the base video as a simple 3D previs. Then took that video into MiniMax H3 and used a character reference + prompt to replace the placeholder object, populate the environment and transform the whole scene into a polished 2D anime sequence. The useful part is that Blender already solves the camera path, timing, scale, blocking and environment geometry. So instead of asking the video model to figure out everything from scratch, you give it a moving blueprint and let it focus on the character, animation and final look. You can find the MiniMax H3 prompt below. Used a premade model from sketchfab for this experiment: "Day 5. Final:The Western Saloon" ( by Olyona Kuznetsova is licensed under Creative Commons Attribution.

GPT-6 Astra + MiniMax H3 A workflow I've been experimenting with: First, used GPT-6 Astra with Blender to create the base video as a simple 3D previs. Then took that video into MiniMax H3 and used a character reference + prompt to replace the placeholder object, populate the environment and transform the whole scene into a polished 2D anime sequence. The useful part is that Blender already solves the camera path, timing, scale, blocking and environment geometry. So instead of asking the video model to figure out everything from scratch, you give it a moving blueprint and let it focus on the character, animation and final look. You can find the MiniMax H3 prompt below. Used a premade model from sketchfab for this experiment: "Day 5. Final:The Western Saloon" ( by Olyona Kuznetsova is licensed under Creative Commons Attribution.

Kōda

23,085 views • 1 month ago

Player stats UI animation with GPT Image 2 and MiniMax H3. This model is amazing for UI animations. Give GPT Image 2 your character image and ask it to create a stats UI. Then use that UI as a reference for MiniMax H3. You can check the prompt in the replies.

Player stats UI animation with GPT Image 2 and MiniMax H3. This model is amazing for UI animations. Give GPT Image 2 your character image and ask it to create a stats UI. Then use that UI as a reference for MiniMax H3. You can check the prompt in the replies.

Kōda

42,858 views • 2 months ago

This ComfyUI workflow lets you draw lines and annotations to guide motion, define where actions should happen, and influence movement throughout a scene. An integrated LLM translates those annotations into prompt instructions, making it easier to direct motion visually instead of relying entirely on text prompts. The workflow works best with clear, intentional paths, while more complex routes with frequent direction changes can be harder to follow consistently. To try this workflow, link below 👇

This ComfyUI workflow lets you draw lines and annotations to guide motion, define where actions should happen, and influence movement throughout a scene. An integrated LLM translates those annotations into prompt instructions, making it easier to direct motion visually instead of relying entirely on text prompts. The workflow works best with clear, intentional paths, while more complex routes with frequent direction changes can be harder to follow consistently. To try this workflow, link below 👇

ComfyUI

44,590 views • 3 months ago

Turn one idea into a complete storyboard, then animate it in Seedance 2.0 using a reference image. This ComfyUI workflow uses LLMs to build storyboard scenes and prepare them for Seedance, making the jump from concept to animation much easier. Link below 👇

Turn one idea into a complete storyboard, then animate it in Seedance 2.0 using a reference image. This ComfyUI workflow uses LLMs to build storyboard scenes and prepare them for Seedance, making the jump from concept to animation much easier. Link below 👇

ComfyUI

74,592 views • 4 months ago

What used to take lights, props, and a full set can now be done inside an agent. This was created using a Glif agent with Kling 2.6 Motion Control and a Nano Banana reference image to lock the look. No physical setup needed. Glif has agents for different creative use cases, so you can pick what fits your workflow and move fast. Check the agents used for this below 👇

What used to take lights, props, and a full set can now be done inside an agent. This was created using a Glif agent with Kling 2.6 Motion Control and a Nano Banana reference image to lock the look. No physical setup needed. Glif has agents for different creative use cases, so you can pick what fits your workflow and move fast. Check the agents used for this below 👇

GLIF

12,858 views • 9 months ago

basically, you can generate this level quality of Ai-video locally on RTX 3090 MiniMax H3 runs on your own hardware for text-to-video, image-to-video, and reference-to-video with native stereo audio.

basically, you can generate this level quality of Ai-video locally on RTX 3090 MiniMax H3 runs on your own hardware for text-to-video, image-to-video, and reference-to-video with native stereo audio.

Md Ismail Šojal 🕷️

56,871 views • 1 month ago

MiniMax H3 Character Board Animation (Bottom Video) & Character Intro Animation (Top Video) First, we create our character board in GPT Image 2 or Seedream 5 using our character reference image. Then, we use that board as a reference in MiniMax H3 to turn it into an animated character board. Also, you can create another character animation with this board. You can find the prompts below.

MiniMax H3 Character Board Animation (Bottom Video) & Character Intro Animation (Top Video) First, we create our character board in GPT Image 2 or Seedream 5 using our character reference image. Then, we use that board as a reference in MiniMax H3 to turn it into an animated character board. Also, you can create another character animation with this board. You can find the prompts below.

Kōda

19,646 views • 1 month ago

> Prompt the scene. > Block it out in Blender. Animate the camera. > Bring it to life with Seedance 2.5. And now, your agent can run the whole workflow with WaveSpeed MCP. From 3D blockout to final video, without leaving your agent workflow.

> Prompt the scene. > Block it out in Blender. Animate the camera. > Bring it to life with Seedance 2.5. And now, your agent can run the whole workflow with WaveSpeed MCP. From 3D blockout to final video, without leaving your agent workflow.

WaveSpeedAI

42,747 views • 1 month ago

Tested MiniMax Design (H3)’s MiniMax H3 through early access by turning a single wireless-earbuds image into a complete product commercial. From the charging case opening and the earbuds lifting into frame to the close-up rotations and final hero shot, MiniMax H3 handled the sequence with smooth motion and strong product consistency. What stood out to me was how well it maintained the product’s design while adding controlled, commercial-style movement. This makes it especially useful for creating polished brand visuals from simple reference inputs. Explore Hailuo AI: #hailuoai #MiniMaxH3 #hailuo #H3

Marry claire

17,545 views • 2 months ago

You direct the look. The motion. The sound. MiniMax H3 is now available in Luma Agents. Generate up to 15 seconds of 2K video with native stereo sound, guided by text, image, video, and audio references. More creative range. One continuous workflow with Luma. Try it today →

You direct the look. The motion. The sound. MiniMax H3 is now available in Luma Agents. Generate up to 15 seconds of 2K video with native stereo sound, guided by text, image, video, and audio references. More creative range. One continuous workflow with Luma. Try it today →

Luma

19,645 views • 2 months ago

The new open-weights Hailuo AI (MiniMax) H3 is live on OpenRouter thanks to MiniMax (official)! H3 is a lightweight video model for text, image, audio, & video input, with native audio-visual output. Built for instruction-led edits, text/brand rendering, and video-2-video motion transfer.

OpenRouter

22,767 views • 2 months ago

What if the iPhone Duo launch ad looked like this? GPT Image 2.5 for key visuals. MiniMax H3 for motion, cinematography, and final video. Now they work together inside MiniMax Design — from a product idea to a polished ad in one creative workflow.

What if the iPhone Duo launch ad looked like this? GPT Image 2.5 for key visuals. MiniMax H3 for motion, cinematography, and final video. Now they work together inside MiniMax Design — from a product idea to a polished ad in one creative workflow.

Nayeem Sheikh

232,603 views • 1 month ago

Interactive Creature Encyclopedia with MiniMax Design (H3) MiniMax H3 Used one UI reference image and 8 creature images. #MiniMaxH3 handles these type of UI animations really well. You can check the prompt below.

Interactive Creature Encyclopedia with MiniMax Design (H3) MiniMax H3 Used one UI reference image and 8 creature images. #MiniMaxH3 handles these type of UI animations really well. You can check the prompt below.

Kōda

66,765 views • 2 months ago