ostris/ideogram_4_turbotime_lora
Summary
A LoRA that adapts Ideogram 4 to generate high-quality images in as few as 2 steps without CFG, using a novel continuous turbo training method.
View Cached Full Text
Cached at: 06/21/26, 04:32 AM
ostris/ideogram_4_turbotime_lora · Hugging Face
Source: https://huggingface.co/ostris/ideogram_4_turbotime_lora
https://huggingface.co/ostris/ideogram_4_turbotime_lora#ideogram-4-turbotime-loraIdeogram 4 TurboTime LoRA
This LoRA will turn Ideogram 4 into a few step model. It is capable of generating good quality images in as little as 2 steps with no CFG and no unconditional model. It was created with a continuious turbo training method I am working on and still perfecting. I will release more information on that once it is fully polished. This will likely recieve updated versions as the method improves.
Some samples using the default AI Toolkit prompts at 8 step
Downloads last month1,679
Model tree forostris/ideogram_4_turbotime_lorahttps://huggingface.co/docs/hub/model-cards#specifying-a-base-model
Space usingostris/ideogram_4_turbotime_lora1
Similar Articles
ideogram-ai/ideogram-4-nf4
Ideogram has released Ideogram 4, their first open-weight text-to-image model trained from scratch, featuring state-of-the-art multilingual text rendering, JSON-structured prompting, bounding-box layout controls, and native 2K resolution output. The NF4-quantized version is available on Hugging Face, with the model claimed to be the best open-weight image model and competitive with proprietary frontier models.
Ideogram 4 (GitHub Repo)
Ideogram 4 is an open-weight text-to-image model trained from scratch, featuring structured JSON prompting, best-in-class multilingual text rendering, bounding-box layout controls, color-palette controls, and native 2K resolution output.
drbaph/MiniMax-H3-Turbo-Lora-ComfyUI
Third-party ComfyUI-compatible LoRA conversions for MiniMax-H3 Turbo 4-step audio-video generation, including further-trained checkpoint-500 variants and an example workflow.
larryvrh/MiniMax-H3-Turbo-Lora
An early-preview LoRA for MiniMax-H3 that enables joint video and synchronized audio generation in 4 sampling steps instead of ~20, offering roughly 5x faster sampling, with ComfyUI custom nodes and three bf16 checkpoints.
@aisearchio: It's finally here! Minimax H3 Turbo lora makes generations 5x faster. Use only 4 steps instead of 20. https://huggingfa…
An early-preview LoRA for MiniMax-H3 enables 4-step audio-video generation instead of ~20 steps, yielding roughly 5x faster sampling, though quality is still immature.