Create README.md

README.md

@@ -0,0 +1,28 @@
+---
+pipeline_tag: text-to-image
+---
+# wdv-tests
+
+alright since i've been promising everyone something for ages and i don't have a clue when wdV actual will get done other than soon, here's something that's better than nothing
+
+## **NOTE:** this is NOT a release, per se. it's a public test, if anything. this uses the TEs from Animagine 3.1 (with permission) and is not representative of the final model really. But it's something, and i rather like it.
+
+see below for setup instructions 
+
+- you *need* to use "simple" or "ddim_uniform" or *maybe* "karras" schedule for the sampler
+- dpmpp_2s_ancestral works best. **SDE samplers will not work.**
+- 20 steps or so at 5.5-7.5 CFG
+
+### comfy node 
+1. get it from [this gist](https://gist.github.com/neggles/ecb6327251a9e274428d07636c727eb9)
+2. put it betwe3n your model loader and sampler,
+3. set sampling mode to "EDM"
+4. set schedule to "XLTC",
+5. set scaling 1.6 (these 3 should all be defaults)
+
+### swarm extension
+1. get it from [this gist](https://gist.github.com/neggles/a3357765668b06a87c9bbf1db00de28e)
+2. make a folder at `src/Extensions/WaifuDiffusionV` and save that file in there named `WaifuDiffusionVExtension.cs`, shows up as "WaifuEDM"
+3. you will need to also have the custom comfy node in your swarm's backend comfy
+
+v0 is trained for five epochs or so on about 4.8 million assorted anime images and uses the text encoder from Animagine 3.1 (with permission from the creator). Actual release wdV models will not use this TE, to be quite honest i swapped it in for a test and forgot to remove it so here we are.