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
Recolor t2i adapter trained and released by TencentARC at huggingface
https://huggingface.co/TencentARC/t2i-adapter-recolor-sdxl-1.0
FAQ
Comments (17)
Is there a visible difference between using fp32 vs fp16 here?
i haven't seen any
Does the new controlnet work for Deforum?
not entirely sure, but a fix seems to at least be in the works https://github.com/Mikubill/sd-webui-controlnet/pull/1952#issuecomment-1704366664
@eurotaku giga nice
@bigTiddyLover looks like it's fixed? https://github.com/Mikubill/sd-webui-controlnet/issues/2019#issuecomment-1705455253
The Deforum looks a bit nasty a lot of the time, no offence, just true feelings
@wuliang19862014 true, it's a novelty really. Some animations are worse than others, a lot of them give me a headache!
what does it do? :)
it's a smaller variant of the full 5gb openpose model by thibaud. it should work like any other controlnet model
@eurotaku Perfect! Thanks for the uploads, super useful to just have them all here! <3
How to use it in A1111? No OpenPose model could be made to work in Automatic1111 :(
@Rollingrollingrocks hm, hard to tell without any context/error message. you can join us on our discord if you want, we got a dedicated help & support section there :)
Thanks for the stuff! But please make sure t2i models say that in the file name (like the TencentARC models)... Normal models run continuously through the generation, but t2i run only once, right before the generation starts, so they are less accurate but don't affect generation speed much (plus t2i only work in Text to Image... hence the name).
did i miss one?
@eurotaku Not sure if they were live when you were setting them up? Not sure now, but when I donwloaded the TencentARC models they didn't have "t2i" in the file name. Anyway, it's no big deal, I just don't like having to rename every file afterwards (after I got them I happened to check the huggingface links to see the details and noticed they were all t2i so I renamed them). Anyway, thanks for gathering the files in one place.
@Alverik hm, no idea what happened there. just as i stated in the description: i tried to stick to lllyasviel's naming scheme for all file names.