Fix Diffusers class metadata warning

README.md

@@ -41,6 +41,7 @@ from diffusers import DiffusionPipeline
 
 pipe = DiffusionPipeline.from_pretrained(
     "WaveCut/Anima-Preview-3-SDNQ-uint4-diffusers",
+    custom_pipeline="pipeline",
     torch_dtype=torch.bfloat16,
     trust_remote_code=True,
 ).to("cuda")
@@ -59,6 +60,8 @@ image = pipe(
 ).images[0]
 ```
 
+Because the Anima pipeline is custom code, pass `custom_pipeline="pipeline"`; `trust_remote_code=True` allows Diffusers to load `pipeline.py` from this repo.
+
 ## Prompting
 
 Anima was trained on Danbooru-style tags, natural language captions, and mixtures of both. The upstream Anima Preview 3 card recommends about 1MP generation, for example `1024x1024`, `896x1152`, or `1152x896`, with roughly 30-50 steps and CFG 4-5.

model_index.json

@@ -1,8 +1,5 @@
 {
-  "_class_name": [
-    "pipeline",
-    "AnimaTextToImagePipeline"
-  ],
+  "_class_name": "AnimaTextToImagePipeline",
   "_diffusers_version": "0.37.0",
   "text_encoder": [
     "transformers",