Text-to-Image
Diffusers
Safetensors
Ideogram4Pipeline
image-generation
diffusion
flow-matching
dit
ideogram
Instructions to use ideogram-ai/ideogram-4-fp8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ideogram-ai/ideogram-4-fp8 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("ideogram-ai/ideogram-4-fp8", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Switch transformer & unconditional_transformer to split Q/K/V
#10 opened about 10 hours ago
by
multimodalart
Image Filter Feedback
1
#9 opened about 11 hours ago
by
Someontwothree
is it really open model
#8 opened about 11 hours ago
by
ryg81
I think ideogram-ai 4 is 18.6B + 8B mode not 9.3B model.
#7 opened about 13 hours ago
by
shivshankar
🚀 The best model for consistent text rendering
🔥 5
1
#6 opened about 13 hours ago
by
jqw5585
the pormpt "Photo of woman lying om grass" gets blocked. i guess easily outperforms Flux2, SD3, Zimage
👀👍 8
2
#5 opened about 13 hours ago
by
shivshankar
BF16 weights?
👍 2
#4 opened about 16 hours ago
by
TheLatentSpacer
the pormpt "a cat" gets blocked
🤯 3
12
#3 opened about 16 hours ago
by
Manni1000
Add diffusers snippet
#2 opened about 16 hours ago
by
multimodalart