hf-internal-testing/tiny-hidream-i1-pipe

created using the following code based on https://github.com/huggingface/diffusers/blob/main/tests/pipelines/hidream/test_pipeline_hidream.py

import numpy as np
import torch
from transformers import (
    AutoTokenizer,
    CLIPTextConfig,
    CLIPTextModelWithProjection,
    CLIPTokenizer,
    LlamaForCausalLM,
    T5EncoderModel,
)

from diffusers import (
    AutoencoderKL,
    FlowMatchEulerDiscreteScheduler,
    HiDreamImagePipeline,
    HiDreamImageTransformer2DModel,
)
def get_dummy_components():
        torch.manual_seed(0)
        transformer = HiDreamImageTransformer2DModel(
            patch_size=2,
            in_channels=4,
            out_channels=4,
            num_layers=1,
            num_single_layers=1,
            attention_head_dim=8,
            num_attention_heads=4,
            caption_channels=[32, 16],
            text_emb_dim=64,
            num_routed_experts=4,
            num_activated_experts=2,
            axes_dims_rope=(4, 2, 2),
            max_resolution=(32, 32),
            llama_layers=(0, 1),
        ).eval()
        torch.manual_seed(0)
        vae = AutoencoderKL(scaling_factor=0.3611, shift_factor=0.1159)
        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,
            max_position_embeddings=128,
        )

        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("hf-internal-testing/tiny-random-t5")

        torch.manual_seed(0)
        text_encoder_4 = LlamaForCausalLM.from_pretrained("hf-internal-testing/tiny-random-LlamaForCausalLM")
        text_encoder_4.generation_config.pad_token_id = 1
        tokenizer = CLIPTokenizer.from_pretrained("hf-internal-testing/tiny-random-clip")
        tokenizer_2 = CLIPTokenizer.from_pretrained("hf-internal-testing/tiny-random-clip")
        tokenizer_3 = AutoTokenizer.from_pretrained("hf-internal-testing/tiny-random-t5")
        tokenizer_4 = AutoTokenizer.from_pretrained("hf-internal-testing/tiny-random-LlamaForCausalLM")

        scheduler = FlowMatchEulerDiscreteScheduler()

        components = {
            "scheduler": scheduler,
            "vae": vae,
            "text_encoder": text_encoder,
            "tokenizer": tokenizer,
            "text_encoder_2": text_encoder_2,
            "tokenizer_2": tokenizer_2,
            "text_encoder_3": text_encoder_3,
            "tokenizer_3": tokenizer_3,
            "text_encoder_4": text_encoder_4,
            "tokenizer_4": tokenizer_4,
            "transformer": transformer,
        }
        return components


if __name__ == "__main__":
    components = get_dummy_components()
    pipeline = HiDreamImagePipeline(**components)
    pipeline.push_to_hub("hf-internal-testing/tiny-hidream-i1-pipe")