Skip to main content
← Back to news

ComfyUI v0.40.0: comfy_attention for all models, local asset API and 3D outputs

Tools & releases
Source:ComfyUI
v0.40.0 extends comfy_attention and AttentionTensorContainer to the rest of the models, brings the asset export API directly into the local server, and makes every 3D node output its models as a standard 3D item. Plus: CreateCameraInfo node with a CameraInfoState widget, video metadata extracted into system_metadata on ingest, and the CSP updated for blob: and data:.
Read original article

Related articles

Local Images: ComfyUI 0.40 and comfy_attention — new for all models

ComfyUI 0.40 extends the comfy_attention attention engine to all models, turns on the local asset API, and standardizes 3D output. Plus the VRAM table that tells you what runs on your hardware.

Costs: local vs API, done with real numbers

How much does local really cost compared to a cloud API? Verified per-token prices, GPU amortization, electricity and the break-even point, calculated with real numbers.

How to Choose Your First Local AI Model

The three criteria for picking your first model: use case, memory (with the exact formula) and context. Recommended models for 8, 16 and 24 GB, and your first model in two commands.

Get the next local-AI briefing

Once a week, the top selection from iaLocale: articles, news and resources on local AI, and more.

After signing up you receive a confirmation email (double opt-in). Without confirmation we send nothing. No spam, we promise.

Related resources

Tools and resources from the iaLocale archive relevant to this content.

Kandinsky 6.0 Video

Models

Kandinsky Lab's foundation models for synchronized video and audio generation: from a prompt they generate video clips with aligned audio, released as open weights. Top paper of the day on Hugging Face (2026-10-06), with checkpoints and Spaces already available.

🎬

LTX-Video

Models

Fast, open video generation: text or image to 768px video with good motion quality. One of the fastest open video models.

🔶

OpenAI API

Inference

Inference API for OpenAI's frontier models (GPT series). You pay per token: a fixed price per million input and output tokens, no GPUs to manage, with rate limits per account tier.

🎬

Stable Video Diffusion

Models

Turns an image into a short ~2s video clip. The entry point for local video generation; 16GB VRAM recommended.

Browse all resources