Update README.md

README.md

@@ -1,3 +1,86 @@
----
-license: mit
----
+Pipeline generated with 
+
+```python
+import torch 
+from diffusers import AutoencoderKL, SD3Transformer2DModel, FlowMatchEulerDiscreteScheduler, StableDiffusion3Pipeline
+from transformers import CLIPTextConfig, CLIPTextModelWithProjection, T5EncoderModel, CLIPTokenizer, AutoTokenizer
+
+
+def get_dummy_components_sd3():
+    torch.manual_seed(0)
+    transformer = SD3Transformer2DModel(
+        sample_size=32,
+        patch_size=1,
+        in_channels=8,
+        num_layers=4,
+        attention_head_dim=8,
+        num_attention_heads=4,
+        joint_attention_dim=32,
+        caption_projection_dim=32,
+        pooled_projection_dim=64,
+        out_channels=8,
+    )
+
+    torch.manual_seed(0)
+    clip_text_encoder_config = CLIPTextConfig(
+        bos_token_id=0,
+        eos_token_id=2,
+        hidden_size=32,
+        intermediate_size=37,
+        layer_norm_eps=1e-05,
+        num_attention_heads=4,
+        num_hidden_layers=5,
+        pad_token_id=1,
+        vocab_size=1000,
+        hidden_act="gelu",
+        projection_dim=32,
+    )
+
+    torch.manual_seed(0)
+    text_encoder = CLIPTextModelWithProjection(clip_text_encoder_config)
+
+    torch.manual_seed(0)
+    text_encoder_2 = CLIPTextModelWithProjection(clip_text_encoder_config)
+
+    torch.manual_seed(0)
+    text_encoder_3 = T5EncoderModel.from_pretrained("./tiny-random-t5")
+
+    tokenizer = CLIPTokenizer.from_pretrained("./tiny-random-clip")
+    tokenizer_2 = CLIPTokenizer.from_pretrained("./tiny-random-clip")
+    tokenizer_3 = AutoTokenizer.from_pretrained("./tiny-random-t5")
+
+    torch.manual_seed(0)
+    vae = AutoencoderKL(
+        sample_size=32,
+        in_channels=3,
+        out_channels=3,
+        block_out_channels=(4,),
+        layers_per_block=1,
+        latent_channels=8,
+        norm_num_groups=1,
+        use_quant_conv=False,
+        use_post_quant_conv=False,
+        shift_factor=0.0609,
+        scaling_factor=1.5035,
+    )
+
+    scheduler = FlowMatchEulerDiscreteScheduler()
+
+    return {
+        "scheduler": scheduler,
+        "text_encoder": text_encoder,
+        "text_encoder_2": text_encoder_2,
+        "text_encoder_3": text_encoder_3,
+        "tokenizer": tokenizer,
+        "tokenizer_2": tokenizer_2,
+        "tokenizer_3": tokenizer_3,
+        "transformer": transformer,
+        "vae": vae,
+    }
+
+
+if __name__ == "__main__":
+    components = get_dummy_components_sd3()
+    pipeline = StableDiffusion3Pipeline(**components)
+    pipeline.push_to_hub("DavyMorgan/tiny-sd3-pipe")
+```