[Bug]: New SD3 model not load

[colotoon]

Is there an existing issue for this?

• I have searched the existing issues and checked the recent builds/commits of both this extension and the webui

Are you using the latest version of the extension?

• I have the modelscope text2video extension updated to the lastest version and I still have the issue.

What happened?

Hello.

I downloaded new stable diffusion model (SD3), and then i try to change it to SD3 - its fails

i try use 4gb and 5gb files from HF: https://huggingface.co/stabilityai/stable-diffusion-3-medium

And i ask u, if u can start this model weights - plz told me how run.

TNX

Steps to reproduce the problem

1. load any model u have.
2. change to SD3 model

What should have happened?

No response

WebUI and Deforum extension Commit IDs

sysinfo-2024-06-13-05-45.json

Torch version

sysinfo-2024-06-13-05-45.json

What GPU were you using for launching?

RTX 3060 (12gb)

On which platform are you launching the webui backend with the extension?

Local PC setup (Windows)

Settings

what page of settings u need? i dont understand, sry

Console logs

changing setting sd_model_checkpoint to sd3_medium.safetensors [cc236278d2]: RuntimeError
Traceback (most recent call last):
  File "F:\AI\Soft\sd.webui\webui\modules\options.py", line 165, in set
    option.onchange()
  File "F:\AI\Soft\sd.webui\webui\modules\call_queue.py", line 13, in f
    res = func(*args, **kwargs)
  File "F:\AI\Soft\sd.webui\webui\modules\initialize_util.py", line 181, in <lambda>
    shared.opts.onchange("sd_model_checkpoint", wrap_queued_call(lambda: sd_models.reload_model_weights()), call=False)
  File "F:\AI\Soft\sd.webui\webui\modules\sd_models.py", line 883, in reload_model_weights
    load_model_weights(sd_model, checkpoint_info, state_dict, timer)
  File "F:\AI\Soft\sd.webui\webui\modules\sd_models.py", line 393, in load_model_weights
    model.load_state_dict(state_dict, strict=False)
  File "F:\AI\Soft\sd.webui\system\python\lib\site-packages\torch\nn\modules\module.py", line 2152, in load_state_dict
    raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for LatentDiffusion:
        size mismatch for first_stage_model.encoder.conv_out.weight: copying a param with shape torch.Size([32, 512, 3, 3]) from checkpoint, the shape in current model is torch.Size([8, 512, 3, 3]).
        size mismatch for first_stage_model.encoder.conv_out.bias: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([8]).
        size mismatch for first_stage_model.decoder.conv_in.weight: copying a param with shape torch.Size([512, 16, 3, 3]) from checkpoint, the shape in current model is torch.Size([512, 4, 3, 3]).

Additional information

No response