Every iteration results in a 3.5gb load getting added into ram = pc crashes at fill

[Enferlain]

I set iterations to 10 each, for like 10 images, and after the scoring process and when it starts a new iteration, it adds the I assume model size to the ram. I have 64gb, and it fills in after 10 iterations of warmup, I can't even get to the optimization part.

What should I do to fix this?

[s1dlx]

mmm weird... the models should be loaded and unloaded to avoid this behaviour

what's the webui version you are using?

[Enferlain]

My version is 1.6.0 https://github.com/AUTOMATIC1111/stable-diffusion-webui/commit/5ef669de080814067961f28357256e8fe27544f4

Maybe this error output has some information, I got it once but I don't remember if subsequent crashes cuz of ram fill had this exact error message

Saving merge to /home/imi/stable-diffusion-webui/models/Stable-diffusion/bbwm-cetusMix_Whalefall2-AOM3A3_orangemixs-best-16bit.safetensors
Unloading model 8 over the limit of 1: 218v5caa.safetensors [c5a1dcb091]
*** API error: POST: http://127.0.0.1:7860/bbwm/merge-models {'error': 'AttributeError', 'detail': '', 'body': '', 'errors': "'NoneType' object has no attribute 'lowvram'"}
    Traceback (most recent call last):
      File "/home/imi/stable-diffusion-webui/venv/lib/python3.11/site-packages/anyio/streams/memory.py", line 98, in receive
        return self.receive_nowait()
               ^^^^^^^^^^^^^^^^^^^^^
      File "/home/imi/stable-diffusion-webui/venv/lib/python3.11/site-packages/anyio/streams/memory.py", line 93, in receive_nowait
        raise WouldBlock
    anyio.WouldBlock

    During handling of the above exception, another exception occurred:

    Traceback (most recent call last):
      File "/home/imi/stable-diffusion-webui/venv/lib/python3.11/site-packages/starlette/middleware/base.py", line 78, in call_next
        message = await recv_stream.receive()
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^
      File "/home/imi/stable-diffusion-webui/venv/lib/python3.11/site-packages/anyio/streams/memory.py", line 118, in receive
        raise EndOfStream
    anyio.EndOfStream

    During handling of the above exception, another exception occurred:

    Traceback (most recent call last):
      File "/home/imi/stable-diffusion-webui/modules/api/api.py", line 187, in exception_handling
        return await call_next(request)
               ^^^^^^^^^^^^^^^^^^^^^^^^
      File "/home/imi/stable-diffusion-webui/venv/lib/python3.11/site-packages/starlette/middleware/base.py", line 84, in call_next
        raise app_exc
      File "/home/imi/stable-diffusion-webui/venv/lib/python3.11/site-packages/starlette/middleware/base.py", line 70, in coro
        await self.app(scope, receive_or_disconnect, send_no_error)
      File "/home/imi/stable-diffusion-webui/venv/lib/python3.11/site-packages/starlette/middleware/base.py", line 108, in __call__
        response = await self.dispatch_func(request, call_next)
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
      File "/home/imi/stable-diffusion-webui/modules/api/api.py", line 151, in log_and_time
        res: Response = await call_next(req)
                        ^^^^^^^^^^^^^^^^^^^^
      File "/home/imi/stable-diffusion-webui/venv/lib/python3.11/site-packages/starlette/middleware/base.py", line 84, in call_next
        raise app_exc
      File "/home/imi/stable-diffusion-webui/venv/lib/python3.11/site-packages/starlette/middleware/base.py", line 70, in coro
        await self.app(scope, receive_or_disconnect, send_no_error)
      File "/home/imi/stable-diffusion-webui/venv/lib/python3.11/site-packages/starlette/middleware/cors.py", line 84, in __call__
        await self.app(scope, receive, send)
      File "/home/imi/stable-diffusion-webui/venv/lib/python3.11/site-packages/starlette/middleware/gzip.py", line 24, in __call__
        await responder(scope, receive, send)
      File "/home/imi/stable-diffusion-webui/venv/lib/python3.11/site-packages/starlette/middleware/gzip.py", line 44, in __call__
        await self.app(scope, receive, self.send_with_gzip)
      File "/home/imi/stable-diffusion-webui/venv/lib/python3.11/site-packages/starlette/middleware/exceptions.py", line 79, in __call__
        raise exc
      File "/home/imi/stable-diffusion-webui/venv/lib/python3.11/site-packages/starlette/middleware/exceptions.py", line 68, in __call__
        await self.app(scope, receive, sender)
      File "/home/imi/stable-diffusion-webui/venv/lib/python3.11/site-packages/fastapi/middleware/asyncexitstack.py", line 21, in __call__
        raise e
      File "/home/imi/stable-diffusion-webui/venv/lib/python3.11/site-packages/fastapi/middleware/asyncexitstack.py", line 18, in __call__
        await self.app(scope, receive, send)
      File "/home/imi/stable-diffusion-webui/venv/lib/python3.11/site-packages/starlette/routing.py", line 718, in __call__
        await route.handle(scope, receive, send)
      File "/home/imi/stable-diffusion-webui/venv/lib/python3.11/site-packages/starlette/routing.py", line 276, in handle
        await self.app(scope, receive, send)
      File "/home/imi/stable-diffusion-webui/venv/lib/python3.11/site-packages/starlette/routing.py", line 66, in app
        response = await func(request)
                   ^^^^^^^^^^^^^^^^^^^
      File "/home/imi/stable-diffusion-webui/venv/lib/python3.11/site-packages/fastapi/routing.py", line 237, in app
        raw_response = await run_endpoint_function(
                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
      File "/home/imi/stable-diffusion-webui/venv/lib/python3.11/site-packages/fastapi/routing.py", line 163, in run_endpoint_function
        return await dependant.call(**values)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
      File "/home/imi/stable-diffusion-webui/extensions/sd-webui-bayesian-merger/scripts/api.py", line 103, in merge_models_api
        sd_models.reload_model_weights()
      File "/home/imi/stable-diffusion-webui/modules/sd_models.py", line 732, in reload_model_weights
        sd_model = reuse_model_from_already_loaded(sd_model, checkpoint_info, timer)
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
      File "/home/imi/stable-diffusion-webui/modules/sd_models.py", line 681, in reuse_model_from_already_loaded
        send_model_to_cpu(sd_model)
      File "/home/imi/stable-diffusion-webui/modules/sd_models.py", line 541, in send_model_to_cpu
        if m.lowvram:
           ^^^^^^^^^
    AttributeError: 'NoneType' object has no attribute 'lowvram'

[Enferlain]

My config is

device: cpu
work_device: cpu
threads: 16

prune: True
weights_clip: False
rebasin: False
rebasin_iterations: 1

optimiser: bayes                 # tpe
bounds_transformer: False        # bayes only
latin_hypercube_sampling: True  # bayes only
guided_optimisation: False
batch_size: 4
init_points: 5
n_iters: 6

save_imgs: True

scorer_device: cpu # cuda
scorer_method: manual # chad, laion, manual

save_best: True
best_format: safetensors # ckpt
best_precision: 16 # 32

settings in webui

[Enferlain]

in the api section of the opened webui

merger.py

[GumGum10]

Same issue here, have you ever fixed this @Enferlain ?