Hugging Face's logo

TenStrip
/
LTX2.3-10Eros

Image-to-Video
Diffusers
Model card Files
xet
 Community
10
TenStrip commited on
Commit
cdefc53
·
verified ·
1 Parent(s): 4275277

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -1
README.md CHANGED
@@ -1,7 +1,11 @@
1
  https://huggingface.co/TenStrip/LTX2.3-10Eros_Workflows
2
 
 
 
 
3
  BF16 loads as a checkpoint with clip and VAEs.
4
- Kijai Split files for 10Eros FP8 Transformer version, goes inside diffusion_models.:
 
5
  https://huggingface.co/Kijai/LTX2.3_comfy/tree/main
6
 
7
  Larger distilled Loras will harm the model's fine tune, try the cond_safe ones:
 
1
  https://huggingface.co/TenStrip/LTX2.3-10Eros_Workflows
2
 
3
+ Reliant on data from https://huggingface.co/SulphurAI/Sulphur-2-base
4
+ This is a different merge attempt for ideal I2V use. It uses layer scaled merges of different steps, it's not a straight weight merge. It behaves much nicer than lora load and respects prompt. Prompt should be enhanced, LTX has very little self reasoning inpuit, it must be guided and conditioned.
5
+
6
  BF16 loads as a checkpoint with clip and VAEs.
7
+
8
+ Kijai split files are for 10Eros FP8 Transformer version, which goes inside diffusion_models:
9
  https://huggingface.co/Kijai/LTX2.3_comfy/tree/main
10
 
11
  Larger distilled Loras will harm the model's fine tune, try the cond_safe ones: