Downloads · 30 days
4
5% of all-time downloads
ideogram-4-fp8-merged
kmax002/ideogram-4-fp8-merged
ideogram-4-fp8-merged is a text-to-image model from kmax002. Use it when you need an image from a text prompt. It is set up for diffusers.
NOTE: weights are now bf16, not fp8. Ideogram-4 with the twinks10000 LoKr merged in at full bf16 precision (crisp, no fp8 requantization). Layout matches ideogram-ai/ideogram-4-fp8 (transformer/ + unconditionaltransfo…
All-time downloads
82
Public
Parameters
9.3B
64.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors46.1 GB · 100%
At a glance
- Task
- Text-to-Image
- Library
- diffusers
- Access
- Public
- Created
- Jun 9, 2026
- Updated
- Jun 10, 2026
- SHA
- 1d1544b2
Model card
From the Hugging Face model README
ideogram-4-fp8-merged
NOTE: weights are now bf16, not fp8. Ideogram-4 with the twinks_10000 LoKr merged in at full bf16 precision (crisp, no fp8 requantization). Layout matches ideogram-ai/ideogram-4-fp8 (transformer/ + unconditional_transformer/), but each diffusion_pytorch_model.safetensors is bf16, single-shard, 458 tensors, no weight_scale. Text encoder / VAE / tokenizer / scheduler are the stock Ideogram-4 files. For AI Toolkit, set the Ideogram model name_or_path to this repo.
- Task
- Text-to-Image
- Library
- diffusers
- Created
- Jun 9, 2026
- Updated
- Jun 10, 2026