Hippotes commited on
Commit
4589e20
·
verified ·
1 Parent(s): 7fa336f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -0
README.md CHANGED
@@ -3,3 +3,17 @@ license: other
3
  license_name: ideogram-4-non-commercial
4
  license_link: https://huggingface.co/ideogram-ai/ideogram-4-fp8/blob/main/LICENSE.md
5
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  license_name: ideogram-4-non-commercial
4
  license_link: https://huggingface.co/ideogram-ai/ideogram-4-fp8/blob/main/LICENSE.md
5
  ---
6
+
7
+ Repackages of Fal's [Ideogram4-Fast](https://huggingface.co/fal/ideogram-v4-fast) and [Ideogram4-Instant](https://huggingface.co/fal/ideogram-v4-instant) to ComfyUI compatible files, with int8 and nvfp4 conversion done with [Silveroxides/convert_to_quant](https://github.com/silveroxides/convert_to_quant), targeting only attention and MLP tensors.
8
+
9
+ Officially recommended parameters:
10
+ - for Fast: 20 steps, CFG 1
11
+ - for Instant: 8 steps, CFG 1
12
+
13
+ Reported gen speed on a 5090 at 1536x1536:
14
+ - bf16: 0.85 it/s
15
+ - int8: 1.7 it/s
16
+ - nvfp4: 1.9 it/s
17
+
18
+ Note that Fast has QAD (Quantization Aware Distillation) and can be better than its larger variants, especially on long texts.
19
+ Fal's readme of Instant says it doesn't have QAD but it's just as good as the larger ones too.