NerdyRodent
patreon
Flux.1 - Faster Upscaling
🕑 Added 2024-09-05 20:44:52 +0000 UTCvideo - https://youtu.be/PRiqTnP3no8
Thanks to the increased resolution, up-scaling takes much longer than generating the initial image... if only there was a way to speed that up a bit?
Well, it looks like Hyper-SD also works great when up-scaling too, and combined with the Euler CFG PP sampler, a latent multiply, some noise injection and a de-noising upscaler (because why not?) you can get some pretty decent images when using just 4 steps in the upscale stage!
Going up to 8 steps does give more detail, but can sometimes be a bit too much. There may even be something like a 2, 4 or 6-step Hyper-SD lora soon too, which would speed things up even more ;)
I've included both the normal & GGUF loader options as it works great with either, and the switch seems to load only the 1 model at a time.
Latent multiply seems to act as a quick and easy built-in node way to reduce (or increase) the colour saturation, while the WAS Nodes noise injection can add some details.
They can also easily be added to any existing up-scaling workflow.
In ComfyUI Manager, the custom nodes installed are:
Impact Pack = ID 2
WAS Node Suite = ID 25
Extra Models for ComfyUI = ID 53
ComfyUI-GGUF = ID 54
Comfyroll Studio = ID 81
Use Everywhere (UE Nodes) = ID 247
As usual, I ran "update all" in manager to make sure everything has the current version.
Attachment info
Flux_Dev_TXT2IMG_HyperSD_MultiLora_NoisyHRF_CFGPP_Compare_v1.json - Loads of nodes. Just used for running a lot of things at once to compare
Flux_Dev_TXT2IMG_HyperSD_MultiLora_NoisyHRF_CFGPP_Basic_v1.json - The basic upscaler, no model loader option
Flux_Dev_TXT2IMG_HyperSD_MultiLora_NoisyHRF_CFGPP_BasicPlus_v1.json - The basic upscaler, including upscale model loader option
As a side note, I'll be away until next week so will answer any questions upon my return!
(update: I'm back! :)
Update - 11/9/2024
Just some minor updates to the new "Flux_Dev_TXT2IMG_HyperSD_MultiLora_NoisyHRF_CFGPP_BasicPlus_LowCFGXtraHiRes_v6.json" file:
Added 2 additional "after detailer" upscale options:
AuraSR - 4x upscale, so 1024 -> x2 = 2048 -> x4 = 8192x8192 in 16 steps
Upscale with model - Pick your own upscale resolution & model
Minimal banding defaults:
Banding is often present on higher resolution images, such as initial images over 1024^2, and if issues are present in the initial image they will be upscaled too
Though slightly slower, the defaults use x2 in 2 sets of 4 steps without the optional upscaling model to minimise banding
Fast group bypasser
As there are now multiple optional groups, there is a "fast group bypasser" node added. This is from the "rgthree" custom node pack - https://github.com/rgthree/rgthree-comfy
Example image showing the workflow results:
Initial Image from the example:
Example 2048x2048 Upscaled Image:
Example 8192x8192 Upscaled Image:
See attachments - ComfyUI_temp_pzpht_00002_.png - its too large ;)
Update 2 - IMG2IMG
Now also attached an IMG2IMG version ;)
Example image showing img2img result:
Update 3 - IMG2IMG + LLM
Now also attached an IMG2IMG + LLM version. Same as above, but LLM powered. See https://www.patreon.com/posts/ai-enhanced-flux-109665789 for more info on LLM party.
Example image showing the workflow results:
Example output:
Other example things for LLMs:
Input an image like this, along with the prompt "do this as a lego character instead"...
... to get a result like this:
It even works with animals too!
Plus text can be included as well!
The really tricky thing is wondering what you're going to re-imagine... ;)
Comments
Nerdy Rodent
Simply re-enable again :)
Ruud
Yes, that's a good option, thanks. But what if I decide I do like the generated image and want to upscale it afterwards? Is there an easy solution for that?
Nerdy Rodent
In ComfyUI it's easy to bypass groups by using the right mouse button and selecting "bypass"
Ruud
I'm running this on a 3070 with 8GB VRAM. I don't want all images to automatically upscale. How can I make it optional to upscale after checking the first result? Would it be possible to get a workflow where I can load the image to upscale separately? Thanks
Nerdy Rodent
Nope. Me blind for not seeing it wasn't attached ;) It's there now though!
Jacob Broms Engblom
hmm am I blind? I don't seem to see a IMG2IMG + LLM flow
Nerdy Rodent
Sure ;)
NetDude
sounds like my ex wife
Nerdy Rodent
Haven't tried myself as yet, but I'd guess the loras won't work... though schnell can do 4 steps anyway so no biggie there! Everything else should be fine!
Nerdy Rodent
The GGUF files are smaller (so less VRAM), but slower.
Guillaume C.
What's the difference with GGUF models ? Speed but quality ?
Case
Thanks!
V V
any chance you can upload an img2img workflow for this?
Cris DM
Hi! Does it work on flux schnell too?
Clayfacer
Sweet
