git clone https://github.com/SWivid/F5-TTS.git
cd F5-TTS

pip install -r requirements.txt

modelscope download --model=pengzhendong/vocos-mel-24khz --local_dir ../checkpoints/charactr/vocos-mel-24khz

modelscope download --model=SWivid/F5-TTS_Emilia-ZH-EN  --local_dir ./ckpts/ F5TTS_Base/model_1200000.bin
modelscope download --model=SWivid/E2-TTS_Emilia-ZH-EN  --local_dir ./ckpts/ E2TTS_Base/model_1200000.bin

python inference-cli.py \
--model "F5-TTS" \
--ref_audio "tests/ref_audio/test_en_1_ref_short.wav" \
--load_vocoder_from_local \
--ref_text "Some call me nature, others call me mother nature." \
--gen_text "I don't really care what you call me. I've been a silent spectator, watching species evolve, empires rise and fall. But always remember, I am mighty and enduring. Respect me and I'll nurture you; ignore me and you shall face the consequences."
python inference-cli.py \
--model "E2-TTS" \
--ref_audio "tests/ref_audio/test_zh_1_ref_short.wav" \
--load_vocoder_from_local \
--ref_text "对，这就是我，万人敬仰的太乙真人。" \
--gen_text "突然，身边一阵笑声。我看着他们，意气风发地挺直了胸膛，甩了甩那稍显肉感的双臂，轻笑道，我身上的肉，是为了掩饰我爆棚的魅力，否则，岂不吓坏了你们呢？"

import torch
from diffusers.pipelines import FluxPipeline
from modelscope import snapshot_download
model_id = snapshot_download("AI-ModelScope/FLUX.1-dev")
adapter_id = snapshot_download("alimama-creative/FLUX.1-Turbo-Alpha")
pipe = FluxPipeline.from_pretrained(
  model_id,
  torch_dtype=torch.bfloat16
)
pipe.to("cuda")
pipe.load_lora_weights(adapter_id)
pipe.fuse_lora()
prompt = "A DSLR photo of a shiny VW van that has a cityscape painted on it. A smiling sloth stands on grass in front of the van and is wearing a leather jacket, a cowboy hat, a kilt and a bowtie. The sloth is holding a quarterstaff and a big book."
image = pipe(
            prompt=prompt,
            guidance_scale=3.5,
            height=1024,
            width=1024,
            num_inference_steps=8,
            max_sequence_length=512).images[0]