Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
LTX2 simple i2v.
|
| 2 |
|
| 3 |
Uses res2s and usually lower distill strength with fp8 undistilled model, 0.75-0.9 distilled lora (rank175 seems best) strength depending on application for first pass. Stack as many loras as you can even if barely related to the concept, lora stack drowns out the base model noise and makes the output more stable.
|
|
|
|
| 1 |
+
10Eros i2v/v2v.
|
| 2 |
+
|
| 3 |
+
All nodes colored red (not vae) are adjustment points to finetune output.
|
| 4 |
+
Extremely tempermental SDE sampling at highnoise. Produces good motion and anatomy with lots of ways to tweak the seed. Similiar to the triple sampling setups, LTX2.3 just needs CFG and more samples. Swap between er_sde and dpm_pp. Dpm is prone to audio problems with higher distilled strength and using the CFG on first steps. Needs to be balanced carefully.
|
| 5 |
+
|
| 6 |
+
Custom nodes you probably need:
|
| 7 |
+
https://github.com/chrisgoringe/cg-sigmas
|
| 8 |
+
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
|
| 13 |
+
|
| 14 |
LTX2 simple i2v.
|
| 15 |
|
| 16 |
Uses res2s and usually lower distill strength with fp8 undistilled model, 0.75-0.9 distilled lora (rank175 seems best) strength depending on application for first pass. Stack as many loras as you can even if barely related to the concept, lora stack drowns out the base model noise and makes the output more stable.
|