OpenBlender

Integrated AI assistant inside Blender.

1. Enable the Chat panel in addon Preferences
2. Configure your LLM provider (OpenRouter or LM Studio)
3. Click the floating chat button in the Blender UI

Vision / Keyframe Analysis

The AI chat supports vision-capable models (e.g. Kimi k2.5, GPT-4o, Claude) for analysing images directly inside Blender.

Video Prompt from Keyframes:

1. Generate or assign your three keyframe images (First, Middle, Last) via the IMG to VID or Remix panel
2. Open the floating chat and type: generate a video prompt from keyframes images
3. The AI calls get_vid_keyframe_images, receives the three images, analyses the visual sequence, and writes a detailed motion prompt describing scene content, transitions, mood, lighting, and optionally sound design

Requires a vision-capable model. The keyframe images are sent as base64 JPEG (max 512px) to stay within context limits.

Batch Generation

Request multiple images at once for keyframe sequences:

• "Generate 3 continuous keyframes of Batman — first, middle, and end frames"
• "Create 5 variations of a mountain landscape"

The AI generates coherent, continuous prompts showing temporal progression and calls the generation tool once per image. Each frame logically follows the previous with evolving poses, camera movement, and lighting. All prompts are automatically enhanced with cinematic detail.

Note: The AI triggers each image sequentially and will confirm after all requested images have been sent to ComfyUI.

Automatic Prompt Enhancement

All generation requests are automatically enhanced without you needing to write detailed prompts:

• Subject specifics: appearance, pose, action, costume, expression
• Camera work: angle, lens, motion, depth of field
• Lighting: key light quality, fill, rim, time of day, atmosphere
• Environment: location, weather, background elements
• Style: cinematic look, color grading, technical quality

Example — You say: "Batman" → AI generates: "Batman in tactical armored suit on rain-soaked Gotham rooftop, low-angle heroic shot with 35mm lens, dramatic rim lighting through storm clouds, volumetric fog, wet cape reflecting neon signs, cinematic color grading, 8k photorealistic"

Generate images from your viewport.

🎯 Manual Mode

1. Set mode to "Run" in sidebar
2. Adjust parameters → click "Generate"

⚡ On-Change Mode

1. Set mode to "Run (on change)" → click "Start"
2. Modify viewport — generation triggers when inputs are released

⚙️ Parameters

Output: Images appear in Image Editor as Result, Result_001, Result_002…

Generate videos from three keyframe images.

1. Click "First Frame" → start view
2. Click "Middle Frame" → transition view
3. Click "Last Frame" → end view
4. Set Frame Count and Megapixels
5. Click "Generate Video"

All three keyframes required. You can re-click any to replace. Video auto-adds to video sequencer if the scene is selected. Show example

AI Video Prompt Generation

Once your three keyframes are set, ask the AI Chat to "generate a video prompt from keyframes images". The AI will visually analyse the First → Middle → Last sequence and write a cinematic motion prompt describing transitions, mood, lighting, and sound design context.

Generate videos from text, image, or video inputs using LTX 2.3.

🖊️ Text to Video

1. Open the OpenBlender sidebar panel (image editor) (N key → OpenBlender tab)
2. Select the TXT to VID pannel
3. Enter a text prompt describing the scene and motion
4. Click "Generate"

🎞️ IC-LoRA Depth Control

The IC-LoRA depth model gives LTX 2.3 structural guidance for consistent motion across frames. It is downloaded via Blender Preferences → Download Models → LTX 2.3.

Convert 2D images to 3D GLB models via Trellis2.

1. Import an image
2. Click "Start"
3. 3D model imports into Blender as GLB, with textures

Requires Trellis2 nodes in ComfyUI (installed via Blender Preferences → Install Nodes). Models are downloaded via Download Models → IMG to 3D.

Transform images from inside the Image Editor side panel.

1. Open any image in the Image Editor
2. Press N → find the OpenBlender tab in the sidebar
3. Set your Prompt, Megapixels, Steps, and Denoise strength
4. Click "Generate Remix"
5. Result appears as Remix.001, Remix.002… in the Image Editor

📤 Send to IMG to 3D

Click "Send to IMG to 3D" to push the currently displayed image to the IMG to 3D input.

🎬 Send to IMG to VID Frame

Use "Send to First / Middle / Last Frame" to assign the current Image Editor image directly to an IMG to VID keyframe slot.

🤖 MCP / AI Chat

Remix is also available via the MCP server and AI Chat using the trigger_remix tool. Agents can transform any displayed image remotely with a text prompt.

📸 Image Capture

Request the current state as an image:

• "Send me the current image" → Agent calls capture_image_editor
• "Show me the viewport" → Agent calls capture_viewport

Both return base64 JPEG images that the agent can display in the chat.

Generate 360° equirectangular HDRI environment maps from text prompts using FLUX.2-Klein + Klein 9B HDRI LoRA.

1. Set viewport shading to Material Preview or Rendered so the environment is visible
2. In Properties → World, ensure a World data block exists — click "New" if the slot is empty
3. Open the OpenBlender sidebar panel (N key → OpenBlender tab)
4. Enter a Prompt describing the environment
5. Set Megapixels and Steps
6. Click "Generate HDRI"
7. The generated panorama is automatically applied to the scene World as an environment texture

The required models are downloaded from Blender Preferences → Add-ons → OpenBlender → Download Models → TXT to HDRI.

Generate a humanoid dummy rig with motion from a text prompt using HY-Motion. The output is a generic animated skeleton — not a character with specific appearance or textures.

1. In Blender, open the sidebar (N) → OpenBlender tab → TXT to RIG panel
2. Enter a text prompt describing the motion (e.g. "walking forward", "jumping", "waving hand")
3. Click "Generate" — HY-Motion runs in ComfyUI and produces an animated GLB
4. The humanoid dummy rig is automatically imported into the scene

Tips

• Prompts should describe motion only — HY-Motion outputs a generic humanoid skeleton regardless of character description
• Use it as an animation base: retarget the motion onto your own character rig
• The AI Chat can trigger generation via the trigger_txt_to_rig MCP tool
• Models are downloaded from Blender Preferences

Add LoRA models to your generation workflows.

1. Open your IMG to IMG or IMG to VID workflow in ComfyUI WebUI
2. Add your LoRA node(s) to the workflow graph
3. Save the API workflow as .json
4. Your LoRA stack is now applied automatically in Blender on every generation

Any ComfyUI-compatible LoRA works. Stack multiple LoRAs in a single workflow. Find models at CivitAI.