Luca Ambrogioni#1824
I integrated our recent work, Spectral Progressive Diffusion a.k.a. SPEED (https://arxiv.org/abs/2605.18736), with the open-source @ideogram_ai model released yesterday. Turns out our method works out of the box and speeds up inference by up to 1.6× while preserving the high image quality!
[1/4]
Luca Ambrogioni#1824I integrated our recent work, Spectral Progressive Diffusion a.k.a. SPEED (https://arxiv.org/abs/2605.18736), with the open-source @ideogram_ai model released yesterday. Turns out our method works out of the box and speeds up inference by up to 1.6× while preserving the high image quality!
[1/4]
Users are excited about the SPEED Method accelerating open-source Ideogram 4 inference by 1.6× because it delivers impressive efficiency gains.
We are working hard to integrate SPEED into various open source frameworks and will release our code soon. Stay tuned!
[4/4]
Check out our original paper post here:
Ideogram4 uses Qwen3-VL-8B-Instruct as its text encoder, unlike CLIP or T5 used in FLUX-family models. Its maximum text token count is 2048, which is significantly longer than FLUX's 512. For diffusion inference speedup methods that only reduce image tokens (like ours), the speedup is inevitably bottlenecked by long prompts with large numbers of text tokens. For future work on efficient diffusion inference, designing methods that jointly reduce both text and image tokens in these unified token streams will be crucial!
[2/4]