NEW 2vXpSwA7: anytest-v4 | openpose-v2_1 || abovzv: segment || bdsqlsz: canny | depth | lineart-anime | mlsdv2 | normal | normal-dsine | openpose | recolor | segment | segmentv2 | sketch | softedge | t2i-color-shuffle | tile-anime-α | tile-anime-β | tile-real || BRIA AI: bg-gen | canny | colorgrid | depth | NEW fill | openpose | recolor || CVL-Heidelberg: canny | depth || destitech: inpaint | inpaintv2 || diffusers: canny small | mid | full | depth small | mid | full | zoe || EcomXL: inpaint | softedge || Eugeoter: NEW noobai canny | depth | lineart-anime | lineart-real | mangaline | normal | scribble-pidi | scribble-hed | softedge-hed | tile | sdxl anime-canny | vidit-depth || h94: ip-adapter | ipa-vith | ipa+ | ipa+face || Hetaneko: pony canny | cannyv2 | color | depth | replicate | replicatev2 || HighCWu: canny-v3 || huchenlei: PuLID || Kataragi: canny | flatline | flatline-lora | inpaint | NEW ipa | line2color | line2color-lora | lineart | lineart-lora | NEW noob-ipa | recolor | recolor-lora | NEW rough-coating | tori29-blur | xdog-sketch || kohya-ss: real blur | canny | depth | anime blur | blur-beta | canny | depth | openpose | openposev2 | replicate | replicatev2 | scribble || PromeAI: lineart || ShermanG lineart || Stability.ai: canny | depth | recolor | revision | sketch || SargeZT: depth-16b-zoe | depth-faid-vidit | depth-zeed | depth-zoe | softedge | t2i-adapters binary | canny | color | depth | segmentation | softedge || TencentARC: canny | depth-midas | depth-zoe | lineart | openpose | recolor | sketch || TheMistoAI: mistoline | mistoline-lora || thibaud: openpose | openpose-lora || ttplanet: tile-real | tile-realv2 || NEW windsingai: pose | tile | tile-10w || xinsir: canny | cannyv2 | depth | openpose | openpose-twins | scribble | scribble-anime | tile | union | union-promax
ControlNetXL (CNXL) - A collection of Controlnet models for SDXL
(13.01.2025 - First NoobAI controlnets uploaded by Eugeoter)
(12.01.2025 - First Illustrious controlnets uploaded: windsingai-pose & -tile)
This collection strives to create a convenient download location of all currently available Controlnet models for SDXL. Please do read the version info for model specific instructions and further resources. If you are the author of one of these models and don't want it to appear here, please contact me to sort this out. The naming scheme of the files follows lllyasviel's from here https://huggingface.co/lllyasviel/sd_control_collection/tree/main.
CAUTION: The variants of controlnet models are marked as checkpoints only to make it possible to upload them all under one version, otherwise the already huge list would be even bigger. If you use downloading helpers the correct target folders are extensions/sd-webui-controlnet/models for automatic1111 and models/controlnet for forge/comfyui.
Requirements for Automatic1111: at least version 1.5.0, better upgrade to the latest version of 1.6.0. + sd-webui-controlnet extension v0.400+. Bugs or weird behaviour might occur. If you encounter any irregularities you can join us on our discord and ask for support or get in contact with the developers of Automatic1111/Controlnet via github/huggingface.
A huge thanks to all the authors, devs and contributors including but not limited to: abovzv, bdsqlsz, BRIA AI, CVL-Heidelberg, destitech, the diffusers institution, Eugeoter, h94, Hetaneko, HighCWu, huchenlei, lllyasviel, kataragi, kohya-ss, Mikubill, PromeAI, SargeZT, ShermanG, Stability.ai, TencentARC, TheMistoAI, thibaud, ttplanet, windsingai and xinsir.
Description
OpenPose LoRA model trained and released by thibaud at huggingface
FAQ
Comments (18)
Hard to navigate here... can you tell us what's been updated?
nothing, sorry, had to reupload one model. if a model would be new/updated, i would mark them in the link collection at the beginning of the description :)
@eurotaku Ah okay, makes sense, thanks for the reply.
Thanks @eurotaku. Any insight regarding CNXL Tile model? (for photorealistic images)
@Atomease nope, seems noone bothered to make one, yet.
@Atomease There is a new Anime contolnet lllite tile SDXL lite model out there, but it's not good at all with other subjects and not even all that useful for anime IMHO. https://huggingface.co/bdsqlsz/qinglong_controlnet-lllite
@EricRollei21 Indeed, I've seen some talks about it but I'm not really interested in anime. I'm unsure how hard it is to train the equivalent of the 1.5 tile model for SDXL. I guess it has to be non-trivial because for me it's the single most powerful tool in the ecosystem.
@Atomease Yes, I was wondering how hard it must be because no one else has done it so far. I read, but not sure if it's true, that SargeZT who put up the first batch of SDXL controlnets has passed away.
Annnnd no tile... :(
this paper promises an adaptor that makes all sd1.5 resources work on sdxl, seeemingly the tile model, too https://showlab.github.io/X-Adapter/
The lack of Tile Resample and Inpaint Global Harmonious is brutal for SDXL.
There IS an experimental anime tile resample (not on this page) that sorta works, but it's pretty buggy.
this paper promises an adaptor that makes all sd1.5 resources work on sdxl, seeemingly the tile model, too https://showlab.github.io/X-Adapter/
Thanks for answering, I had not seen that new paper. Here's to hoping it works, a well-working Tile and Inpaint are sorely missing!
I can't for the life of me get Openpose to work with SDXL in comfyui. Anyone want to give a pointer? I'm no novice, but it just isn't producing anything in terms of matching poses. Even with preprocessed images.
hard to say anything helpful without any further info, but the sdxl openpose models indeed seem to be less consistent than their sd1.x counterpart. in my experience the controlnet lllite anime v1 model gave me the best results, even for realistic images. if you are on discord, join our official server, so we can take a more thorough look at it then :)
@eurotaku hi, thanks for taking the time to comment. I actually spent a couple hours troubleshooting last night and found the issue. Seems Kohya Deep Shrink negates Controlnet entirely, so if someone is using it in their workflow during same pass as controlnet, controlnet won't work.
Will look to join your discord regardless. Always interested in new resources.
@CJG interesting, didn't even know that since now. glad you could at least identify the cause :)
Details
Files
controlnetxlCNXL_thibauldOpenposeLora.safetensors
Mirrors
controlnetxlCNXL_thibauldOpenposeLora.safetensors
thibaud_xl_openpose_256lora.safetensors
control-lora-openposeXL2-rank256.safetensors
control-lora-openposeXL2-rank256.safetensors
control-lora-openposeXL2-rank256.safetensors
control-lora-openposeXL2-rank256.safetensors
control-lora-openposeXL2-rank256.safetensors
controlnetxlCNXL_thibauldOpenposeLora.safetensors
control-lora-openposeXL2-rank256.safetensors
control-lora-openposeXL2-rank256.safetensors
control-lora-openposeXL2-rank256.safetensors
control-lora-openposeXL2-rank256.safetensors
control-lora-openposeXL2-rank256.safetensors
control-lora-openposeXL2-rank256.safetensors
control-lora-openposeXL2-rank256.safetensors