Error 1006 when using image prompt

[cristicozea]

Read Troubleshoot

[x] I confirm that I have read the Troubleshoot guide before making this issue.

Describe the problem

I have downloaded Fooocus as instructed. Clicked on run.bat and waited until the download is ready. However nothing happens after the download is finished. Each time I open the run file it starts downloading again.

Can you please help?

Full Console Log

C:\Focus>.\python_embeded\python.exe -s Fooocus\entry_with_update.py
Already up-to-date
Update succeeded.
[System ARGV] ['Fooocus\entry_with_update.py']
Python 3.10.9 (tags/v3.10.9:1dd9be6, Dec 6 2022, 20:01:21) [MSC v.1934 64 bit (AMD64)]
Fooocus version: 2.1.865
Downloading: "https://huggingface.co/lllyasviel/fav_models/resolve/main/fav/juggernautXL_v8Rundiffusion.safetensors" to C:\Focus\Fooocus\models\checkpoints\juggernautXL_v8Rundiffusion.safetensors

100%|████████████████████████████████████████████████████████████████████████████▉| 6.62G/6.62G [09:33<00:00, 12.7MB/s]

[eddyizm]

Huggingface was likely having some issues yesterday.

It should only download the first time. It could possibly be corrupt. Try shutting down the app, delete that model ]juggernautXL_v8Rundiffusion.safetensors` then start it back up. It will hopefully download it successfully and then continue.

If that doesn't work try to go to the browser and download it directly. Then you can move it to the proper folder and restart the app.

[cristicozea]

Huggingface was likely having some issues yesterday.

It should only download the first time. It could possibly be corrupt. Try shutting down the app, delete that model ]juggernautXL_v8Rundiffusion.safetensors` then start it back up. It will hopefully download it successfully and then continue.

If that doesn't work try to go to the browser and download it directly. Then you can move it to the proper folder and restart the app.

Thanks for getting back to me. I have tried deleting everything and starting from scratch. Did not work. I have also tried downloading it from the browser directly. I have tried this by clicking on the file - it started downloading from the browser. Still doesn't work.

[cristicozea]

UPDATE: I have now managed to download the file directly from the browser and Foocus does open. However when I ask to generate something i get 'ERROR'

[cristicozea]

UPDATE: I have now managed to download the file directly from the browser and Foocus does open. However when I ask to generate something i get 'ERROR'

UPDATE2: Apparently I had to update my driver and now it works. However it took 347.50 seconds to generate an image :(
Is it normal to take that long?

I have 16GB RAM and 6GB Vram GTX 1660 Ti

[cristicozea]

UPDATE: I have now managed to download the file directly from the browser and Foocus does open. However when I ask to generate something i get 'ERROR'

UPDATE2: Apparently I had to update my driver and now it works. However it took 347.50 seconds to generate an image :( Is it normal to take that long?

I have 16GB RAM and 6GB Vram GTX 1660 Ti

UPDATE3: When I try image input I get 'Connection errored out' -- I have checked the System swap and it looks good. Automatic is checked.

[eddyizm]

Can you post your full log?

[cristicozea]

Can you post your full log?

The log only says '1006'

[eddyizm]

That is not your log, the full terminal output from the window.

[mashb1t]

https://github.com/lllyasviel/Fooocus/blob/main/troubleshoot.md#error-1006 => System swap or memory issue, please double check and provide your full terminal log.

[cristicozea]

https://github.com/lllyasviel/Fooocus/blob/main/troubleshoot.md#error-1006 => System swap or memory issue, please double check and provide your full terminal log.

Each time i input an image i get: Error Connection errored out.

I have followed the guide and I checked the box 'Automatically manage paging file size for all drivers'
I also have 60GB free space on my SSD

Please find the log below ( this is what i get in cmd ):

C:\Focus>.\python_embeded\python.exe -s Fooocus\entry_with_update.py
Already up-to-date
Update succeeded.
[System ARGV] ['Fooocus\entry_with_update.py']
Python 3.10.9 (tags/v3.10.9:1dd9be6, Dec 6 2022, 20:01:21) [MSC v.1934 64 bit (AMD64)]
Fooocus version: 2.1.865
Running on local URL: http://127.0.0.1:7865

To create a public link, set share=True in launch().
Total VRAM 6144 MB, total RAM 16221 MB
Set vram state to: NORMAL_VRAM
Always offload VRAM
Device: cuda:0 NVIDIA GeForce GTX 1660 Ti : native
VAE dtype: torch.float32
Using pytorch cross attention
Refiner unloaded.
model_type EPS
UNet ADM Dimension 2816
Using pytorch attention in VAE
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
Using pytorch attention in VAE
extra {'cond_stage_model.clip_l.text_projection', 'cond_stage_model.clip_g.transformer.text_model.embeddings.position_ids', 'cond_stage_model.clip_l.logit_scale'}
1006
Base model loaded: C:\Focus\Fooocus\models\checkpoints\juggernautXL_v8Rundiffusion.safetensors
Request to load LoRAs [['sd_xl_offset_example-lora_1.0.safetensors', 0.1], ['None', 1.0], ['None', 1.0], ['None', 1.0], ['None', 1.0]] for model [C:\Focus\Fooocus\models\checkpoints\juggernautXL_v8Rundiffusion.safetensors].
Loaded LoRA [C:\Focus\Fooocus\models\loras\sd_xl_offset_example-lora_1.0.safetensors] for UNet [C:\Focus\Fooocus\models\checkpoints\juggernautXL_v8Rundiffusion.safetensors] with 788 keys at weight 0.1.
Fooocus V2 Expansion: Vocab with 642 words.
Fooocus Expansion engine loaded for cpu, use_fp16 = False.
Requested to load SDXLClipModel
Requested to load GPT2LMHeadModel
Loading 2 new models
App started successful. Use the app with http://127.0.0.1:7865/ or 127.0.0.1:7865
1006

[mashb1t]

I don't know if this helps but please check on which disk the pagefile has been created. You can see the location in the same dialogue where you've checked "Automatically manage paging file size for all drivers".
Your 1660 should be able to run Fooocus, not very fast but at least without errors like this one.

[cristicozea]

I don't know if this helps but please check on which disk the pagefile has been created. You can see the location in the same dialogue where you've checked "Automatically manage paging file size for all drivers". Your 1660 should be able to run Fooocus, not very fast but at least without errors like this one.

Thanks for getting back to me. I only have one partition on this PC so it should be fine. When I installed Windows it created a secondary windriver partition, hopefully it doesn;t affect this. Anyway, I checked and it all looks ok.

Do you have any other ideas? I can generate an image, but i only get this error when I input an image :(

[mashb1t]

Check any issue in https://github.com/search?q=repo%3Alllyasviel%2FFooocus+1006&type=issues

This issue has turned into a duplicate of many 1006 issues.

On Colab this indicates too high RAM usage or resource linit peaks. Feel free to check with either or a combination of the following args which helped some users in #1710 to balance the load:

--attention-split --disable-offload-from-vram --always-high-vram

Maybe --attention-split helps but the other args are not suitable for you as VRAM is small compared to RAM on your system. It's 99% a swap issue.

[cristicozea]

Check any issue in https://github.com/search?q=repo%3Alllyasviel%2FFooocus+1006&type=issues

This issue has turned into a duplicate of many 1006 issues.

On Colab this indicates too high RAM usage or resource linit peaks. Feel free to check with either or a combination of the following args which helped some users in #1710 to balance the load:

--attention-split --disable-offload-from-vram --always-high-vram

Maybe --attention-split helps but the other args are not suitable for you as VRAM is small compared to RAM on your system. It's 99% a swap issue.

Thank you. I will try this. Can you tell me in which file I should add it?

[cristicozea]

--attention-split --disable-offload-from-vram --always-high-vram

I am not a programmer so I'm not sure how to put it exactly. Step by step instructions will help. I put it in networking.py but now i get a syntax error.

[cristicozea]

--attention-split --disable-offload-from-vram --always-high-vram

I am not a programmer so I'm not sure how to put it exactly. Step by step instructions will help. I put it in networking.py but now i get a syntax error.

UPDATE: I have solved the issue by adding this code starting from line 162:

            ws_max_queue=64,
            ws_ping_interval=60.0,
            ws_ping_timeout=10.0,
            ws_per_message_deflate=False,
            reload=True,
            timeout_notify=120

Thank you all for your help!