Update README.md
Browse files
README.md
CHANGED
|
@@ -30,4 +30,4 @@ Use a "Load Checkpoint" node. 1 CFG, 4 step. Use the "TextEncodeQwenImageEditPlu
|
|
| 30 |
|
| 31 |
**V4:** Mix of many Qwen Edit and base Qwen accelerators, which I think gives better results. Added a touch of a skin correction LORA. **4-5 steps: use sa_solver/simple, lcm/beta or euler_a/beta** and **6-8 steps: use lcm/beta or euler_a/beta only**.
|
| 32 |
|
| 33 |
-
**V5:** NSFW and SFW use cases interfered with eachother too much, so I separated them to specialize in their use cases. Significantly tweaked NSFW LORAs for v5, along with some accelerator tweaks. **lcm/beta or er_sde/beta generally recommended**. Please experiment! Looking for realism and/or a "candid" look? Try lcm/ddim_uniform with the NSFW model!
|
|
|
|
| 30 |
|
| 31 |
**V4:** Mix of many Qwen Edit and base Qwen accelerators, which I think gives better results. Added a touch of a skin correction LORA. **4-5 steps: use sa_solver/simple, lcm/beta or euler_a/beta** and **6-8 steps: use lcm/beta or euler_a/beta only**.
|
| 32 |
|
| 33 |
+
**V5:** NSFW and SFW use cases interfered with eachother too much, so I separated them to specialize in their use cases. Significantly tweaked NSFW LORAs for v5, along with some accelerator tweaks. **lcm/beta or er_sde/beta generally recommended**. Please experiment! Looking for realism and/or a "candid" look when not using input images? Try lcm/ddim_uniform with the NSFW model!
|