NerdyRodent patreon

Flux.1 - Speed Boost + More ControlNets & LoRAs!

🕑 Added 2024-09-01 12:51:44 +0000 UTC

Comments

Nerdy Rodent

It's been a while, but I'd say it's still back with AnimateDiff & SD1.5 - https://github.com/nerdyrodent/AVeryComfyNerd/blob/main/workflows/SD15/Video_Restyler.png

Christopher Manzione

Thanks. What do you think the best Vid2Vid workflow is right now?

Nerdy Rodent

Nothing V2V as yet, though Flux I2V should be next quarter

Christopher Manzione

Somehow fixed this. I have no idea how. Working great! Would love to do Video to Video with this

Christopher Manzione

Also I have the following error on this workflow "The size of tensor a (3072) must match the size of tensor b (38) at non-singleton dimension 3" Any idea why this is happening?

Christopher Manzione

Hey Nerdy Rodent, Is there a workflow here for Flux that would work for Video to Video?

Nerdy Rodent

I clone environments in quite a few cases, but especially if I'm upgrading or testing custom nodes (especially ones with strict requirements.txt files). It's much easier to just create a new clone should anything go a bit weird and start downgrading packages, etc :)

Nerdy Rodent

Yup, should work just fine!

NetDude

whoa. you make new environments just for the extensions? i mean i guess it IS a party. :) that's a good idea but I always assumed it wouldnt work.

John Doe

Do you recon it would be possible to use xlab's ipadapter and these controlnets in combination with one another?

Nerdy Rodent

LLM party only uses the VRAM while it's loaded, so with OLLAMA_KEEP_ALIVE=0 it essentially uses 0 extra VRAM. It's also easily removable if you don't want any LLM enhacements :)

Nerdy Rodent

LLM party doesn't have any fixed version numbers in it's requirements.txt, so it should play well with everything else (I've got over 30 custom nodes installed XD). If you do find you've got other custom nodes impacting your install, just run another environment. (I tend to clone them first when I see custom nodes with hard version numbers in)

ed.enai

LLM-Party node broke my ComfyUI install due to something with torch, It was a hassle to figure out how to restore it, please continue to create workflows without in the future if possible!

Asyouare

I find the LLM party addition which has become a staple in your workflows really eats up unecessary ressources while not giving, really, that much of a benefit(in terms of ressource cost) could you think about returning to or maybe making something a little more simplified? Of course it is up to you...I mean, who am I too...really no but who am I....(who am I?)....Thank you for your time!

Richard Gates

Thank you good sir. All is well in the world!

Nerdy Rodent

I've deleted the node in this version - Flux_Dev_TXT2IMG_LLMParty_HyperSD_MultiLora_NoClear_v3.json

Richard Gates

I tried that and for some reason I get this with it disabled. Error occurred when executing CR Text Concatenate: can only concatenate str (not "NoneType") to str File "D:\AI\pinokio\api\comfy.git\app\execution.py", line 317, in execute output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb) File "D:\AI\pinokio\api\comfy.git\app\execution.py", line 192, in get_output_data return_values = _map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb) File "D:\AI\pinokio\api\comfy.git\app\execution.py", line 169, in _map_node_over_list process_inputs(input_dict, i) File "D:\AI\pinokio\api\comfy.git\app\execution.py", line 158, in process_inputs results.append(getattr(obj, func)(**inputs)) File "D:\AI\pinokio\api\comfy.git\app\custom_nodes\ComfyUI_Comfyroll_CustomNodes\nodes\nodes_utils_text.py", line 222, in concat_text return (text1 + separator + text2, )

Nerdy Rodent

I've added an option "clear model" node for lower VRAM systems. You can change the settings in that node so that "is_enable" = false. That way the ollama model won't unload each time.

Richard Gates

Hey Nerdy for the Flux_Dev_TXT2IMG_LLMParty_HyperSD_MultiLora_v3.json workflow, any idea why the LLM Party section would create a prompt very quickly the first time and then take several minutes to do the next one? I have 32GB of system RAM and 16GB of VRAM. I thought one of your previous workflows with the LLM party was faster, but I could be mistaken.

Nerdy Rodent

Yup! Almost enough for Flux Reposer... just need a face-plus IP adapter!

Nerdy Rodent

Added the video guide link for more info ;)

KING LIFER

Yeah.... this doesnt work.

Andro.Meta

One of my favorite workflows in SDXL is taking the union ControlNet and using IP-Adapters style transfer to effectively restyle or reimagine a base image with a new image. I'm excited to plug these technologies together in Flux!