ThereforeGames / txt2img2img

Improve the editability of any Stability Diffusion subject while retaining a high degree of likeness
151 stars 22 forks source link

incompatibilities with latest automatic1111 webui repo #17

Open jmp909 opened 1 year ago

jmp909 commented 1 year ago

quite a few changes to the latest a1111

been working throught it from here...

File "D:\py\automatic1111\stable-diffusion-webui\scripts\txt2img2img.py", line 234, in run
p.sampler_index = samplers_dict.get(getattr(img_opts,"sampler_name","euler a").lower(), p.sampler_index)

I'll see what else I can spot and update notes

def img2img(
    mode: int,
    prompt: str, 
    negative_prompt: str, 
    prompt_style: str, 
    prompt_style2: str, 
    init_img, 
    init_img_with_mask, 
    init_img_with_mask_orig, 
    init_img_inpaint, 
    init_mask_inpaint, 
    mask_mode, 
    steps: int, 
    sampler_index: int, 
    mask_blur: int, 
    mask_alpha: float, 
    inpainting_fill: int, 
    restore_faces: bool, 
    tiling: bool, 
    n_iter: int, 
    batch_size: int, 
    cfg_scale: float, 
    denoising_strength: float, 
    seed: int, 
    subseed: int, 
    subseed_strength: float, 
    seed_resize_from_h: int, 
    seed_resize_from_w: int, 
    seed_enable_extras: bool, 
    height: int, 
    width: int, 
    resize_mode: int, 
    inpaint_full_res: bool, 
    inpaint_full_res_padding: int, 
    inpainting_mask_invert: int, 
    img2img_batch_input_dir: str, 
    img2img_batch_output_dir: str, 
    *args):
jav12z commented 1 year ago

This was such a nice script, I wish it can work again with the lastest versions. Specially with 512-depth-ema would be great.

Jonseed commented 1 year ago

I would also like to see this script updated and implemented as an extension. I almost always have to do img2img after using textual inversion on a subject in txt2img mode. If @ThereforeGames isn't interested in updating it, maybe someone can fork it and do the updates?