Function worker

demo_gradio.py:103–315

(input_image, prompt, n_prompt, seed, total_second_length, latent_window_size, steps, cfg, gs, rs, gpu_memory_preservation, use_teacache, mp4_crf)

@torch.no_grad()
def worker(input_image, prompt, n_prompt, seed, total_second_length, latent_window_size, steps, cfg, gs, rs, gpu_memory_preservation, use_teacache, mp4_crf):
    total_latent_sections = (total_second_length * 30) / (latent_window_size * 4)
    total_latent_sections = int(max(round(total_latent_sections), 1))

    job_id = generate_timestamp()

    stream.output_queue.push(('progress', (None, '', make_progress_bar_html(0, 'Starting ...'))))

    try:
        # Clean GPU
        if not high_vram:
            unload_complete_models(
                text_encoder, text_encoder_2, image_encoder, vae, transformer
            )

        # Text encoding

        stream.output_queue.push(('progress', (None, '', make_progress_bar_html(0, 'Text encoding ...'))))

        if not high_vram:
            fake_diffusers_current_device(text_encoder, gpu)  # since we only encode one text - that is one model move and one encode, offload is same time consumption since it is also one load and one encode.
            load_model_as_complete(text_encoder_2, target_device=gpu)

        llama_vec, clip_l_pooler = encode_prompt_conds(prompt, text_encoder, text_encoder_2, tokenizer, tokenizer_2)

        if cfg == 1:
            llama_vec_n, clip_l_pooler_n = torch.zeros_like(llama_vec), torch.zeros_like(clip_l_pooler)
        else:
            llama_vec_n, clip_l_pooler_n = encode_prompt_conds(n_prompt, text_encoder, text_encoder_2, tokenizer, tokenizer_2)

        llama_vec, llama_attention_mask = crop_or_pad_yield_mask(llama_vec, length=512)
        llama_vec_n, llama_attention_mask_n = crop_or_pad_yield_mask(llama_vec_n, length=512)

        # Processing input image

        stream.output_queue.push(('progress', (None, '', make_progress_bar_html(0, 'Image processing ...'))))

        H, W, C = input_image.shape
        height, width = find_nearest_bucket(H, W, resolution=640)
        input_image_np = resize_and_center_crop(input_image, target_width=width, target_height=height)

        Image.fromarray(input_image_np).save(os.path.join(outputs_folder, f'{job_id}.png'))

        input_image_pt = torch.from_numpy(input_image_np).float() / 127.5 - 1
        input_image_pt = input_image_pt.permute(2, 0, 1)[None, :, None]

        # VAE encoding

        stream.output_queue.push(('progress', (None, '', make_progress_bar_html(0, 'VAE encoding ...'))))

        if not high_vram:
            load_model_as_complete(vae, target_device=gpu)

        start_latent = vae_encode(input_image_pt, vae)

        # CLIP Vision

        stream.output_queue.push(('progress', (None, '', make_progress_bar_html(0, 'CLIP Vision encoding ...'))))