Update README.md
Browse files
README.md
CHANGED
|
@@ -72,6 +72,8 @@ Seems to work even on 8GB VRAM:
|
|
| 72 |
|
| 73 |
**MEGA v3:** Very different merging method using SkyReels 2.1 33% base and WAN 2.2 66% on top. I now also match accelerators for each version (2.1 and 2.2), then merge. I think this gets a better result by basing "mega" on models designed for 1 sampler (2.1) but then bringing in most of WAN 2.2 to lay on top. Camera control and prompt following is better, but keeping facial features still struggles compared to v10 I2V (might be a VACE limitation). ipndm/beta recommended. euler_a/beta seems to work better with the NSFW v3.1 merge, though.
|
| 74 |
|
|
|
|
|
|
|
| 75 |
Looking for GGUFs? Looks like DooFY87 on CivitAI has been doing that:
|
| 76 |
|
| 77 |
https://civitai.com/models/1855105/rapid-wan-22-i2v-gguf
|
|
|
|
| 72 |
|
| 73 |
**MEGA v3:** Very different merging method using SkyReels 2.1 33% base and WAN 2.2 66% on top. I now also match accelerators for each version (2.1 and 2.2), then merge. I think this gets a better result by basing "mega" on models designed for 1 sampler (2.1) but then bringing in most of WAN 2.2 to lay on top. Camera control and prompt following is better, but keeping facial features still struggles compared to v10 I2V (might be a VACE limitation). ipndm/beta recommended. euler_a/beta seems to work better with the NSFW v3.1 merge, though.
|
| 74 |
|
| 75 |
+
**MEGA v4:** Uses the WAN 2.2 finetune from https://huggingface.co/eddy1111111/WAN22.XX_Palingenesis (also slight tweaks to accelerator strengths)
|
| 76 |
+
|
| 77 |
Looking for GGUFs? Looks like DooFY87 on CivitAI has been doing that:
|
| 78 |
|
| 79 |
https://civitai.com/models/1855105/rapid-wan-22-i2v-gguf
|