Clarity AI Upscaler Reproduction
β’
19
LaureΞ·t Fainsin
1aurent
AI & ML interests
Generative Models connoisseur, Pathology enthusiast, Reproducibility advocate
Recent Activity
liked
a model
about 1 hour ago
black-forest-labs/FLUX.1-Fill-dev
liked
a model
about 1 hour ago
black-forest-labs/FLUX.1-Redux-dev
New activity
about 4 hours ago
data-is-better-together-contributor/README
Articles
Organizations
1aurent's activity
posted
an
update
3 months ago
Post
1066
Hey everyone π€!
We (finegrain) have created some custom ComfyUI nodes to use our refiners micro-framework inside comfy! π
We only support our new Box Segmenter at the moment, but we're thinking of adding more nodes since there seems to be a demand for it. We leverage the new (beta) Comfy Registry to host our nodes. They are available at: https://registry.comfy.org/publishers/finegrain/nodes/comfyui-refiners. You can install them by running:
Or by unzipping the archive you can download by clicking "Download Latest" into your
We are eager to hear your feedbacks and suggestions for new nodes and how you'll use them! π
We (finegrain) have created some custom ComfyUI nodes to use our refiners micro-framework inside comfy! π
We only support our new Box Segmenter at the moment, but we're thinking of adding more nodes since there seems to be a demand for it. We leverage the new (beta) Comfy Registry to host our nodes. They are available at: https://registry.comfy.org/publishers/finegrain/nodes/comfyui-refiners. You can install them by running:
comfy node registry-install comfyui-refinersOr by unzipping the archive you can download by clicking "Download Latest" into your
custom_nodes comfy folder.We are eager to hear your feedbacks and suggestions for new nodes and how you'll use them! π
reacted to
their
post with π₯
3 months ago
Post
4347
Hey everyone π€!
Check out this awesome new model for object segmentation!
finegrain/finegrain-object-cutter.
We (finegrain) have trained this new model in partnership with Nfinite and some of their synthetic data, the resulting model is incredibly accurate π.
Itβs all open source under the MIT license ( finegrain/finegrain-box-segmenter), complete with a test set tailored for e-commerce ( finegrain/finegrain-product-masks-lite). Have fun experimenting with it!
Check out this awesome new model for object segmentation!
finegrain/finegrain-object-cutter.
We (finegrain) have trained this new model in partnership with Nfinite and some of their synthetic data, the resulting model is incredibly accurate π.
Itβs all open source under the MIT license ( finegrain/finegrain-box-segmenter), complete with a test set tailored for e-commerce ( finegrain/finegrain-product-masks-lite). Have fun experimenting with it!
posted
an
update
3 months ago
Post
4347
Hey everyone π€!
Check out this awesome new model for object segmentation!
finegrain/finegrain-object-cutter.
We (finegrain) have trained this new model in partnership with Nfinite and some of their synthetic data, the resulting model is incredibly accurate π.
Itβs all open source under the MIT license ( finegrain/finegrain-box-segmenter), complete with a test set tailored for e-commerce ( finegrain/finegrain-product-masks-lite). Have fun experimenting with it!
Check out this awesome new model for object segmentation!
finegrain/finegrain-object-cutter.
We (finegrain) have trained this new model in partnership with Nfinite and some of their synthetic data, the resulting model is incredibly accurate π.
Itβs all open source under the MIT license ( finegrain/finegrain-box-segmenter), complete with a test set tailored for e-commerce ( finegrain/finegrain-product-masks-lite). Have fun experimenting with it!
replied to
their
post
4 months ago
Hi @arcayi , the pipeline is indeed exposed via an API - I updated the post to clarify it.
reacted to
their
post with ππ₯
4 months ago
Post
2564
Hey everyone π€!
Check out this cool new space from Finegrain: finegrain/finegrain-object-eraser
Under the hoods, it's a pipeline of models (currently exposed via an API) that allows you to easily erase any object from your image just by naming it or selecting it! Not only will the object disappear, but so will its effects on the scene, like shadows and reflections. Built on top of Refiners, our micro-framework for simple foundation model adaptation (feel free to star it on GitHub if you like it: https://github.com/finegrain-ai/refiners)
Check out this cool new space from Finegrain: finegrain/finegrain-object-eraser
Under the hoods, it's a pipeline of models (currently exposed via an API) that allows you to easily erase any object from your image just by naming it or selecting it! Not only will the object disappear, but so will its effects on the scene, like shadows and reflections. Built on top of Refiners, our micro-framework for simple foundation model adaptation (feel free to star it on GitHub if you like it: https://github.com/finegrain-ai/refiners)
-
- 2 replies
posted
an
update
4 months ago
Post
2564
Hey everyone π€!
Check out this cool new space from Finegrain: finegrain/finegrain-object-eraser
Under the hoods, it's a pipeline of models (currently exposed via an API) that allows you to easily erase any object from your image just by naming it or selecting it! Not only will the object disappear, but so will its effects on the scene, like shadows and reflections. Built on top of Refiners, our micro-framework for simple foundation model adaptation (feel free to star it on GitHub if you like it: https://github.com/finegrain-ai/refiners)
Check out this cool new space from Finegrain: finegrain/finegrain-object-eraser
Under the hoods, it's a pipeline of models (currently exposed via an API) that allows you to easily erase any object from your image just by naming it or selecting it! Not only will the object disappear, but so will its effects on the scene, like shadows and reflections. Built on top of Refiners, our micro-framework for simple foundation model adaptation (feel free to star it on GitHub if you like it: https://github.com/finegrain-ai/refiners)
-
-
- 2 replies
reacted to
ehristoforu's
post with π
4 months ago
Post
3577
π Hello from Project Fluently Team!
β¨ Finally we can give you some details about Supple Diffusion. We worked on it for a long time and we have little left, we apologize that we had to increase the work time.
π οΈ Some technical information. The first version will be the Small version (there will also be Medium, Large, Huge, possibly Tiny), it will be based on the SD1 architecture, that is, one text encoder, U-net, VAE. Now about each component, the first is a text encoder, it will be a CLIP model (perhaps not CLIP-L-path14), CLIP was specially retrained by us in order to achieve the universality of the model in understanding completely different styles and to simplify the prompt as much as possible. Next, we did U-net, U-net in a rather complicated way, first we trained different parts (types) of data with different U-nets, then we carried out merging using different methods, then we trained DPO and SPO using methods, and then we looked at the remaining shortcomings and further trained model, details will come later. We left VAE the same as in SD1 architecture.
π Compatibility. Another goal of the Supple model series is full compatibility with Auto1111 and ComfyUI already at the release stage, the model is fully supported by these interfaces and the diffusers library and does not require adaptation, your usual Sampling methods are also compatible, such as DPM++ 2M Karras, DPM++ SDE and others.
π§ Today, without demo images (there wasnβt much time), final work is underway on the model and we are already preparing to develop the Medium version, the release of the Small version will most likely be in mid-August or earlier.
π» Feel free to ask your questions in the comments below the post, we will be happy to answer them, have a nice day!
β¨ Finally we can give you some details about Supple Diffusion. We worked on it for a long time and we have little left, we apologize that we had to increase the work time.
π οΈ Some technical information. The first version will be the Small version (there will also be Medium, Large, Huge, possibly Tiny), it will be based on the SD1 architecture, that is, one text encoder, U-net, VAE. Now about each component, the first is a text encoder, it will be a CLIP model (perhaps not CLIP-L-path14), CLIP was specially retrained by us in order to achieve the universality of the model in understanding completely different styles and to simplify the prompt as much as possible. Next, we did U-net, U-net in a rather complicated way, first we trained different parts (types) of data with different U-nets, then we carried out merging using different methods, then we trained DPO and SPO using methods, and then we looked at the remaining shortcomings and further trained model, details will come later. We left VAE the same as in SD1 architecture.
π Compatibility. Another goal of the Supple model series is full compatibility with Auto1111 and ComfyUI already at the release stage, the model is fully supported by these interfaces and the diffusers library and does not require adaptation, your usual Sampling methods are also compatible, such as DPM++ 2M Karras, DPM++ SDE and others.
π§ Today, without demo images (there wasnβt much time), final work is underway on the model and we are already preparing to develop the Medium version, the release of the Small version will most likely be in mid-August or earlier.
π» Feel free to ask your questions in the comments below the post, we will be happy to answer them, have a nice day!
- 1 reply
reacted to
rwightman's
post with π§
4 months ago
Post
1987
I can't resist an opportunity to update an old baseline. Read a new article on my latest look at improving MobileNet-V1 and EfficientNet-B0 baselines.
https://huggingface.co/blog/rwightman/mobilenet-baselines
timm/mobilenetv1_100.ra4_e3600_r224_in1k
timm/efficientnet_b0.ra4_e3600_r224_in1k
https://huggingface.co/blog/rwightman/mobilenet-baselines
timm/mobilenetv1_100.ra4_e3600_r224_in1k
timm/efficientnet_b0.ra4_e3600_r224_in1k
reacted to
their
post with π₯
4 months ago
Post
2664
Hey everyone π€!
Check out this cool little reproduction of the Clarity Upscaler (https://github.com/philz1337x/clarity-upscaler) using refiners (https://github.com/finegrain-ai/refiners): https://huggingface.co/spaces/finegrain/enhancer
Check out this cool little reproduction of the Clarity Upscaler (https://github.com/philz1337x/clarity-upscaler) using refiners (https://github.com/finegrain-ai/refiners): https://huggingface.co/spaces/finegrain/enhancer
-
- 3 replies
replied to
their
post
4 months ago
haha yes, that's one of the biases of the juggernaut model (it also tends to transform everyone into women). You can reduce this effect by changing the base model and/or tweaking the parameters of the diffusion pipeline.
posted
an
update
4 months ago
Post
2664
Hey everyone π€!
Check out this cool little reproduction of the Clarity Upscaler (https://github.com/philz1337x/clarity-upscaler) using refiners (https://github.com/finegrain-ai/refiners): https://huggingface.co/spaces/finegrain/enhancer
Check out this cool little reproduction of the Clarity Upscaler (https://github.com/philz1337x/clarity-upscaler) using refiners (https://github.com/finegrain-ai/refiners): https://huggingface.co/spaces/finegrain/enhancer
-
-
-
- 3 replies
reacted to
their
post with π
4 months ago
Post
2003
Hi everyone π€
You can easily use the new Model Explorer from Google (https://github.com/google-ai-edge/model-explorer) here: 1aurent/model-explorer
Unfortunately, it doesn't look like it can easily be preloaded with some models, so you'll have to bring your own. Here is a quick selection of models you can use:
- openai-community/gpt2
- qualcomm/ResNet50
- qualcomm/VIT
You can easily use the new Model Explorer from Google (https://github.com/google-ai-edge/model-explorer) here: 1aurent/model-explorer
Unfortunately, it doesn't look like it can easily be preloaded with some models, so you'll have to bring your own. Here is a quick selection of models you can use:
- openai-community/gpt2
- qualcomm/ResNet50
- qualcomm/VIT
posted
an
update
4 months ago
Post
2003
Hi everyone π€
You can easily use the new Model Explorer from Google (https://github.com/google-ai-edge/model-explorer) here: 1aurent/model-explorer
Unfortunately, it doesn't look like it can easily be preloaded with some models, so you'll have to bring your own. Here is a quick selection of models you can use:
- openai-community/gpt2
- qualcomm/ResNet50
- qualcomm/VIT
You can easily use the new Model Explorer from Google (https://github.com/google-ai-edge/model-explorer) here: 1aurent/model-explorer
Unfortunately, it doesn't look like it can easily be preloaded with some models, so you'll have to bring your own. Here is a quick selection of models you can use:
- openai-community/gpt2
- qualcomm/ResNet50
- qualcomm/VIT
posted
an
update
6 months ago
Post
1546
Is finding cool models/datasets and uploading them to the hub considered data hoarding ? I can't stop, send help.
1aurent/dinobloom-models-664ba2ab533c5d0c9c4b07e9
1aurent/tia-toolbox-models-654a3c7994d809b4e740105b
1aurent/kaikoai-models-66636c99d8e1e34bc6dcf795
1aurent/medmae-models-6565b4b766a4bce451a32ba7
1aurent/transpath-models-65639c6730a88a2f1d04321d
1aurent/lunit-models-65639b4149f816b7989185b4
1aurent/tcga-brca-ssl-models-65639d42f725fc09726909f1
1aurent/deblurringmim-models-6567446811b2bbd6c2a23071
1aurent/dinobloom-models-664ba2ab533c5d0c9c4b07e9
1aurent/tia-toolbox-models-654a3c7994d809b4e740105b
1aurent/kaikoai-models-66636c99d8e1e34bc6dcf795
1aurent/medmae-models-6565b4b766a4bce451a32ba7
1aurent/transpath-models-65639c6730a88a2f1d04321d
1aurent/lunit-models-65639b4149f816b7989185b4
1aurent/tcga-brca-ssl-models-65639d42f725fc09726909f1
1aurent/deblurringmim-models-6567446811b2bbd6c2a23071
- 1 reply
reacted to
albertvillanova's
post with π₯
7 months ago
Post
1660
π We recently released datasets 2.19.0! π¦
π₯ What's New:
- Polars integration π»ββοΈ
- fsspec support for conversion to JSON, CSV, and Parquet
- Mode parameter for Image feature
- CLI function to convert script-datasets to Parquet
- Dataset.take and Dataset.skip
Plus, a bunch of general improvements & bug fixes!
Check out the release notes: https://github.com/huggingface/datasets/releases/tag/2.19.0
Upgrade now and power up your data workflows! π₯
π₯ What's New:
- Polars integration π»ββοΈ
- fsspec support for conversion to JSON, CSV, and Parquet
- Mode parameter for Image feature
- CLI function to convert script-datasets to Parquet
- Dataset.take and Dataset.skip
Plus, a bunch of general improvements & bug fixes!
Check out the release notes: https://github.com/huggingface/datasets/releases/tag/2.19.0
Upgrade now and power up your data workflows! π₯
- 2 replies