CiaraRowles

/

TemporalNet

like 349

hi @CiaraRowles , thanks for publishing this cool model
I have a question about your process, since we're writing a demo using the converted Diffusers model on PR #13 by @patrickvonplaten

Looking at the configuration on script, could you clarify the steps here?

1. Initial image + prompt using ControlNet Hed Boundary.
2. Generate Image + prompt, (no condition) just img2img using TemporalNet
3. LastFrame as init Image + prompt using TemporalNet
4. back to 3 until ends

Are these the steps?

Thanks

    data = {
        "init_images": [current_image],
        "inpainting_fill": 0,
        "inpaint_full_res": True,
        "inpaint_full_res_padding": 1,
        "inpainting_mask_invert": 1,
        "resize_mode": 0,
        "denoising_strength": 0.45,
        "prompt": "pop art, painting, highly detailed,",
        "negative_prompt": "(ugly:1.3), (fused fingers), (too many fingers), (bad anatomy:1.5), (watermark:1.5), (words), letters, untracked eyes, asymmetric eyes, floating head, (logo:1.5), (bad hands:1.3), (mangled hands:1.2), (missing hands), (missing arms), backward hands, floating jewelry, unattached jewelry, floating head, doubled head, unattached head, doubled head, head in body, (misshapen body:1.1), (badly fitted headwear:1.2), floating arms, (too many arms:1.5), limbs fused with body, (facial blemish:1.5), badly fitted clothes, imperfect eyes, untracked eyes, crossed eyes, hair growing from clothes, partial faces, hair not attached to head",
        "alwayson_scripts": {
            "ControlNet":{
                "args": [
                    {
                        "input_image": current_image,
                        "module": "hed",
                        "model": "control_hed-fp16 [13fee50b]",
                        "weight": 1.5,
                        "guidance": 1,
                   },
                    {
                        "input_image": last_image,
                        "model": "diff_control_sd15_temporalnet_fp16 [adc6bd97]",
                        "module": "none",
                        "weight": 0.7,
                        "guidance": 1,
                    }
                  
                ]
            }
        },
        "seed": 3189343382,
        "subseed": -1,
        "subseed_strength": -1,
        "sampler_index": "Euler a",
        "batch_size": 1,
        "n_iter": 1,
        "steps": 20,
        "cfg_scale": 6,
        "width": 512,
        "height": 512,
        "restore_faces": True,
        "include_init_images": True,
        "override_settings": {},
        "override_settings_restore_afterwards": True
    }