diff --git a/CHANGELOG.md b/CHANGELOG.md
index 673dcd67..447d8f5a 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -2,6 +2,114 @@
 
 All notable changes to this project will be documented in this file. See [commit-and-tag-version](https://github.com/absolute-version/commit-and-tag-version) for commit guidelines.
 
+## [0.9.0](https://github.com/ssube/onnx-web/compare/v0.8.1...v0.9.0) (2023-03-28)
+
+
+### Features
+
+* **api:** add conversion script for LoRAs from sd-scripts ([#213](https://github.com/ssube/onnx-web/issues/213)) ([4c17edb](https://github.com/ssube/onnx-web/commit/4c17edb2673956833d0c769fdd35879c65a75dde))
+* **api:** add error flag to image ready response ([7cf5554](https://github.com/ssube/onnx-web/commit/7cf5554beff501988c0e1c740170d4e57e0c8e5e))
+* **api:** add flag for ORT float16 optimizations ([1c631c2](https://github.com/ssube/onnx-web/commit/1c631c28d3571827442b083cbf1d1345b6cc19c7))
+* **api:** add optimization for internal fp16 conversion ([afa8f5e](https://github.com/ssube/onnx-web/commit/afa8f5e706ab347f9e4d52738777ad85b0176489))
+* **api:** add pending field to image ready response ([8cbdad3](https://github.com/ssube/onnx-web/commit/8cbdad3a712eec6ba484407e1184e4946b8c4664))
+* **api:** add section to extras file for additional networks ([e3bf04a](https://github.com/ssube/onnx-web/commit/e3bf04ab8f259485193693feae475729c02c5d35))
+* **api:** add server setting for CUDA memory limit ([#211](https://github.com/ssube/onnx-web/issues/211)) ([aec540a](https://github.com/ssube/onnx-web/commit/aec540a524898b78b85dac5603322ae72ec1b3b7))
+* **api:** add trace log level ([959798e](https://github.com/ssube/onnx-web/commit/959798eabbd956920a19e241a83f16725b71f7ff))
+* **api:** blend LoRAs and Textual Inversions from extras file ([84bd852](https://github.com/ssube/onnx-web/commit/84bd852837df9791fbc75fdc09b3c586070a0501))
+* **api:** blend ONNX models in memory ([2a8c85c](https://github.com/ssube/onnx-web/commit/2a8c85cb3e892b3e39868c06046a282def7b5aff))
+* **api:** blend Textual Inversions from prompt ([506cf9f](https://github.com/ssube/onnx-web/commit/506cf9f65f8cbb5224ebd72377ec0004a9448585))
+* **api:** build a single token for multi-layer Textual Inversions ([#212](https://github.com/ssube/onnx-web/issues/212)) ([5dd14c1](https://github.com/ssube/onnx-web/commit/5dd14c19ce02ec9092cd3daea0dd97d8ec246c07))
+* **api:** check device worker pool and recycle on a regular interval ([#284](https://github.com/ssube/onnx-web/issues/284)) ([e552a55](https://github.com/ssube/onnx-web/commit/e552a5560f606857792c93e5d54c86473e883cdb))
+* **api:** detect Textual Inversion type from keys ([#262](https://github.com/ssube/onnx-web/issues/262)) ([0732058](https://github.com/ssube/onnx-web/commit/0732058aa89faeedac192e23989006319336d9d6))
+* **api:** load i18n labels from additional networks ([f8f36e6](https://github.com/ssube/onnx-web/commit/f8f36e602c6182b7d66f51b4eb0a3dda9ac9fdf5))
+* **api:** load Textual Inversions from prompt ([a2e21f4](https://github.com/ssube/onnx-web/commit/a2e21f427f70f010a7fff40b7db4b724eda66df8))
+* **api:** parse LoRA names from prompt ([143904f](https://github.com/ssube/onnx-web/commit/143904fc519c4f3aeeb1336fce1b2fca3d4d42e8))
+* **api:** parse LoRA weights from prompt ([a7f77a0](https://github.com/ssube/onnx-web/commit/a7f77a033dce5c763093de46f7b28acbcc499a17))
+* **api:** pin pytorch versions and update nightly ORT ([dca8a97](https://github.com/ssube/onnx-web/commit/dca8a97796c0b127186ded982aabf18a398b4d45))
+* **api:** split up status endpoint by job status ([ccf8d51](https://github.com/ssube/onnx-web/commit/ccf8d51e08a64b23eb1dfd6b268eae31a40cc5c8))
+* **gui:** add error status to image card ([6226778](https://github.com/ssube/onnx-web/commit/6226778cfbfa340eabaf64d84a24a9c60a43fe86))
+* **gui:** add menus to add LoRA and Textual Inversion tokens ([b195b59](https://github.com/ssube/onnx-web/commit/b195b59301d37452ceb2d3bdc51588b7d0d1509e))
+* **gui:** add retry function to error card ([8979064](https://github.com/ssube/onnx-web/commit/89790645cbaf74b7cad2d7e7fd693665db13caa4))
+* **scripts:** add env debug script ([#191](https://github.com/ssube/onnx-web/issues/191)) ([84718e5](https://github.com/ssube/onnx-web/commit/84718e5928919bef73b02166d6330e79515dd1da))
+* **scripts:** add model type guessing script ([#210](https://github.com/ssube/onnx-web/issues/210)) ([17e4fd7](https://github.com/ssube/onnx-web/commit/17e4fd7b061cfdd853a9e873310be41902666587))
+* show additional networks in client ([2d11210](https://github.com/ssube/onnx-web/commit/2d112104fb5df1d260fc00948f2a2f8ea3d7aace))
+
+
+### Bug Fixes
+
+* **api:** add base token for Textual Inversion as sum layer ([19d4d55](https://github.com/ssube/onnx-web/commit/19d4d554c3f382ee1cee7c104d24c6f7f67d8dc3))
+* **api:** add HF hub download to fetch logic for Inversion concepts ([ae3bcf3](https://github.com/ssube/onnx-web/commit/ae3bcf3b8ba7de8f58c367bf7dda19f972409fb0))
+* **api:** add theoretical support for 3x3 conv in LoRA ([315e5a3](https://github.com/ssube/onnx-web/commit/315e5a383771b5875dbaec623520d980d1b6904d))
+* **api:** allow dash in network names ([645da3d](https://github.com/ssube/onnx-web/commit/645da3d1a676f08cf043e91338a217a3fc7319a1))
+* **api:** always reset job counter when creating new device worker ([2b179be](https://github.com/ssube/onnx-web/commit/2b179bebacac99bbcc4ec270d408a2e6447fa948))
+* **api:** apply fp16 optimizations to LoRA and Textual Inversion blending ([0315a8c](https://github.com/ssube/onnx-web/commit/0315a8cbc623e22b5b88a09fc0bc88d18d24d399))
+* **api:** assume inversion tokens are embeddings for now ([e5862d1](https://github.com/ssube/onnx-web/commit/e5862d178cdeafa15d108adea162a668fdea0693))
+* **api:** attempt to read progress updates from recycled workers ([2d2283e](https://github.com/ssube/onnx-web/commit/2d2283e1ebb7381876b5d0a35ef2a9bb78865c3e))
+* **api:** avoid loading encoder twice when using LoRAs and inversions together ([af326a7](https://github.com/ssube/onnx-web/commit/af326a784f657aa333dfd12426b50acac1ff024b))
+* **api:** better error handling around tensor loading ([8acc15f](https://github.com/ssube/onnx-web/commit/8acc15f52e0aecb909bcfbe3c1929835131c95ef))
+* **api:** bump default model cache to 5 ([#242](https://github.com/ssube/onnx-web/issues/242)) ([a9456f4](https://github.com/ssube/onnx-web/commit/a9456f4a16fefeb59ff5ad447960607b2bfbfb52))
+* **api:** clear job cancelled flag when worker starts a new job ([#269](https://github.com/ssube/onnx-web/issues/269)) ([aefa5b4](https://github.com/ssube/onnx-web/commit/aefa5b4613c043811a00488bf731671dd2347609))
+* **api:** close queues after stopping workers ([e1219cc](https://github.com/ssube/onnx-web/commit/e1219cca907ebab5057f0e0f944cfd4c9c3c1283))
+* **api:** combine names for ONNX fp16 optimization ([c2f8fb1](https://github.com/ssube/onnx-web/commit/c2f8fb1d3128a0ff9b0acf67943985afd3a0a562))
+* **api:** convert back to model format after blending, convert samples as needed ([#274](https://github.com/ssube/onnx-web/issues/274)) ([c8aad85](https://github.com/ssube/onnx-web/commit/c8aad8554ed39a564b94c72a163e374b5a496e3c))
+* **api:** correctly load server env for conversion ([b8f8163](https://github.com/ssube/onnx-web/commit/b8f816323e64ed7d23baff6f7e1196c9d636f12f))
+* **api:** disable internal fp16 for VAE encoder ([#290](https://github.com/ssube/onnx-web/issues/290)) ([73e9cf8](https://github.com/ssube/onnx-web/commit/73e9cf8b66e6e0f11bbab1a484e12c3e4d12dcaa))
+* **api:** do not assume file extension for additional networks ([b797b3d](https://github.com/ssube/onnx-web/commit/b797b3d61636024116eadbf5900e12f19dd8af7f))
+* **api:** do not move jobs from pending to running until progress is reported ([27500ec](https://github.com/ssube/onnx-web/commit/27500eccb570d78004f97062ddb4404f2c0a8016))
+* **api:** download additional networks to their own subdir in models ([32b2a76](https://github.com/ssube/onnx-web/commit/32b2a76a0b64bc91810a69df991d311226e1e93e))
+* **api:** embed Inversion concepts using their name ([fe498b1](https://github.com/ssube/onnx-web/commit/fe498b16f0a31033aa1a6d559564683e885e0163))
+* **api:** enqueue next job when previous one finishes and after recycling worker ([14ade83](https://github.com/ssube/onnx-web/commit/14ade839377d64a874f1bc9d6ba29e0bb00a8d33))
+* **api:** fetch sources and additional networks by default ([0e43acc](https://github.com/ssube/onnx-web/commit/0e43acc0f7747980e4bf8b820708a48032e789be))
+* **api:** filter out temporary files from model lists ([#271](https://github.com/ssube/onnx-web/issues/271)) ([1971226](https://github.com/ssube/onnx-web/commit/19712262e6e8c8d0f42ca2e95040baf80cd520f9))
+* **api:** handle CUDA memory errors in workers ([b2eb406](https://github.com/ssube/onnx-web/commit/b2eb406197d208c135d51a2347a5b073ec3490f7))
+* **api:** handle more out-of-memory errors in the workers ([c8c5e9f](https://github.com/ssube/onnx-web/commit/c8c5e9f42e5b885be215c3576e9703b7cc81ee5a))
+* **api:** include worker totals in status endpoint ([36bfcca](https://github.com/ssube/onnx-web/commit/36bfccae09e29383c6c9b23f4edd0217f7eb6e15))
+* **api:** increment job counter for worker when it starts a new job ([#283](https://github.com/ssube/onnx-web/issues/283)) ([55e44e8](https://github.com/ssube/onnx-web/commit/55e44e8ac9842e5c514ab07811130bdd8cf58ed6))
+* **api:** load blending tensors onto CPU ([3300853](https://github.com/ssube/onnx-web/commit/33008531e976e6aa61750609d0e46efefc555ff4))
+* **api:** maintain list of pending jobs ([15b6e03](https://github.com/ssube/onnx-web/commit/15b6e036e1a71a31067cccb27421d1eb5a9f81fa))
+* **api:** make format list in schema match code ([580d621](https://github.com/ssube/onnx-web/commit/580d621209ed72c726b62ab71480fb23bd31d7d1))
+* **api:** move imports of patches modules into function ([c943a55](https://github.com/ssube/onnx-web/commit/c943a55a44c2630d8ec7fb6924d54ec35e38e8cb))
+* **api:** move model conversion messages to trace level ([9f0a6f1](https://github.com/ssube/onnx-web/commit/9f0a6f134e97354468c030cf4dcd76371dc4f1cd))
+* **api:** move prompt parsing logs to trace level ([ed8a7c8](https://github.com/ssube/onnx-web/commit/ed8a7c893411ae8458465979b3ed48f4968abf74))
+* **api:** only remove running jobs from running state ([2e89fd4](https://github.com/ssube/onnx-web/commit/2e89fd43d3223177bc9a157a9b9a8fa1a06c5638))
+* **api:** provide noise parameter to SD upscaling ([#196](https://github.com/ssube/onnx-web/issues/196)) ([f336cc5](https://github.com/ssube/onnx-web/commit/f336cc5d024ba61d041cf59c009c36b5e0f0397d))
+* **api:** remove prefix before downloading for HF hub ([f779fbd](https://github.com/ssube/onnx-web/commit/f779fbd5cc74e6abab3dcee00090454238395d4c))
+* **api:** restart worker threads if they crash ([4dd68ea](https://github.com/ssube/onnx-web/commit/4dd68ea6b64113431910d157e7b735908fab57a7))
+* **api:** restart worker threads when their respective queues are full ([95a61f3](https://github.com/ssube/onnx-web/commit/95a61f3573ff621262daea890c476044bc679c1c))
+* **api:** restore python 3.8 compatibility ([1d44f98](https://github.com/ssube/onnx-web/commit/1d44f985a48165ae485ae5d250bc7f96945b0405))
+* **api:** restrict CLIP skip token to integers, allow negative LoRA and Inversion weights ([27bd10d](https://github.com/ssube/onnx-web/commit/27bd10d2f7e29a6c4cc6eeb161afe386ab1cf198))
+* **api:** track last progress within worker ([588c8c7](https://github.com/ssube/onnx-web/commit/588c8c7fdb4007f8d83ece40ebdac06f94089298))
+* **api:** update LPW pipeline ([#298](https://github.com/ssube/onnx-web/issues/298)) ([93fcfd1](https://github.com/ssube/onnx-web/commit/93fcfd142284e1f5c96381714ac03abc780d076c))
+* **api:** use exception level logs ([226710a](https://github.com/ssube/onnx-web/commit/226710a015014cf6ed3ba8b93904a85e29284a98))
+* **api:** use lock when restarting workers ([88f4713](https://github.com/ssube/onnx-web/commit/88f4713e235ef80c132e3fcc72399d8c1ba31752))
+* **api:** use ORT session for correct device when loading blended nets ([9f9b73b](https://github.com/ssube/onnx-web/commit/9f9b73b780d926dff240741ee3ef90c72d4b10a7))
+* **api:** use Torch JIT and fallback loading ([0762269](https://github.com/ssube/onnx-web/commit/07622690dc01f632489eba806fa2dda48232ac5a))
+* **api:** watch for progress events from leaking workers ([4ddd69b](https://github.com/ssube/onnx-web/commit/4ddd69ba07ce73c8829787f358fddf6ea6065000))
+* **build:** allow long-running jobs to be interrupted ([641456f](https://github.com/ssube/onnx-web/commit/641456fd42e8ff132e1d8926ea2efe0d4f482346))
+* **build:** install wheel for basicsr ([d9bae80](https://github.com/ssube/onnx-web/commit/d9bae80778bc5b2b4ff74c11d65ab97d363a4290))
+* **build:** make sure Torch is installed first in containers ([4de8c16](https://github.com/ssube/onnx-web/commit/4de8c160c92149a4c4f5c021896082eb3b3119f0))
+* **build:** pin Torch to 1.x for now ([a21750f](https://github.com/ssube/onnx-web/commit/a21750ff8eabbf2b756e7c0a52301a4618c8adf3))
+* **buil:** limit torchvision versions to match torch ([fc9245f](https://github.com/ssube/onnx-web/commit/fc9245f4ee01de070dc4811ca7b3728ad749867c))
+* **deps:** update dependency i18next to v22.4.13 ([35ebb2a](https://github.com/ssube/onnx-web/commit/35ebb2af7b33c4835e53538fd8b4092ac7ab429f))
+* **deps:** update dependency react-query to v3.39.3 ([92cb6ac](https://github.com/ssube/onnx-web/commit/92cb6acdf9d968ec53f7f479b395e2e2d1af9501))
+* **docs:** add check scripts to user guide ([fca9ba8](https://github.com/ssube/onnx-web/commit/fca9ba893caba50d2e0433525fcfce88651b4183))
+* **docs:** add more runtimes to memory usage table ([c0ece24](https://github.com/ssube/onnx-web/commit/c0ece2453d98b9604cd6f2e708d13b57c6ca9cfb))
+* **docs:** describe LoRA and Textual Inversion tokens in user guide ([74dc0e9](https://github.com/ssube/onnx-web/commit/74dc0e9484d36aac1a914a4bbf61c9e91008da36))
+* **docs:** explain CLIP skip, describe tokens better ([b99c8c8](https://github.com/ssube/onnx-web/commit/b99c8c8bae944f8c35e5e8232402eb4bd659d56e))
+* **docs:** explain extras file format in user guide ([a1c3b28](https://github.com/ssube/onnx-web/commit/a1c3b28bee5c7d118677073ca269fa520e18dd9f))
+* **docs:** explain how to optimize models ([31e841a](https://github.com/ssube/onnx-web/commit/31e841ab4a3930b1623d12823491613289da682a))
+* **gui:** add progress bar to menus while loading ([#216](https://github.com/ssube/onnx-web/issues/216)) ([0ab52f0](https://github.com/ssube/onnx-web/commit/0ab52f0c24bd2577b66ef3303f7d6c3004e0c0af))
+* **gui:** add prompt tokens to correct tab ([#296](https://github.com/ssube/onnx-web/issues/296)) ([d19bbfc](https://github.com/ssube/onnx-web/commit/d19bbfc1d39c40915b56adc1bfe1ec62d975eb47))
+* **gui:** only enable blend tab's generate button with two source images ([#235](https://github.com/ssube/onnx-web/issues/235)) ([3f9789a](https://github.com/ssube/onnx-web/commit/3f9789a0a8621f7381b09e709480022856bfa8aa))
+* **gui:** remove images from history beyond limit ([#267](https://github.com/ssube/onnx-web/issues/267)) ([ba07671](https://github.com/ssube/onnx-web/commit/ba0767179cdb1b64b95927a12e4d8e01383c4b5c))
+* **gui:** remove prompt length error condition ([#268](https://github.com/ssube/onnx-web/issues/268)) ([382316f](https://github.com/ssube/onnx-web/commit/382316f0c9cc21a660718faf757f47822c7240bc))
+* **gui:** split base models and additional options ([7553040](https://github.com/ssube/onnx-web/commit/755304059515f34c21cb1752ed7b09a57d9024ff))
+* **scripts:** check for ORT modules ([c465b61](https://github.com/ssube/onnx-web/commit/c465b61fb5af0e7c1d710fd37a3946f0abdb9b52))
+* **scripts:** check Torch CUDA devices ([#242](https://github.com/ssube/onnx-web/issues/242)) ([391a707](https://github.com/ssube/onnx-web/commit/391a707c846109fd05ab03f302400e99bd8931d7))
+* **scripts:** diff model nodes as well ([8cf6f22](https://github.com/ssube/onnx-web/commit/8cf6f2215d9ee854371e6eca571bd6b747acc973))
+* **tests:** add reference image for UniPC scheduler ([cf429ad](https://github.com/ssube/onnx-web/commit/cf429ad715252a8ed573a9a78a3b3240d6cf40e7))
+* **tests:** make release tests fail if image was not successful ([#287](https://github.com/ssube/onnx-web/issues/287)) ([d7e5480](https://github.com/ssube/onnx-web/commit/d7e548037af81db5d157b367a977b09f661ea108))
+
 ### [0.8.1](https://github.com/ssube/onnx-web/compare/v0.8.0...v0.8.1) (2023-03-11)
 
 
diff --git a/README.md b/README.md
index f3a48042..71b5af19 100644
--- a/README.md
+++ b/README.md
@@ -497,7 +497,7 @@ To update the server, make sure you are on the `main` branch and pull the latest
 > git pull
 ```
 
-If you want to run a specific tag of the server, run `git checkout v0.8.1` with the desired tag.
+If you want to run a specific tag of the server, run `git checkout v0.9.0` with the desired tag.
 
 ### Building the client
 
diff --git a/api/setup.py b/api/setup.py
index 34e7e35e..6ee87d46 100644
--- a/api/setup.py
+++ b/api/setup.py
@@ -5,7 +5,7 @@ with open("README.md", "r") as fh:
 
 setuptools.setup(
     name="onnx-web",
-    version="0.8.1",
+    version="0.9.0",
     author="ssube",
     author_email="seansube@gmail.com",
     description="web UI for running ONNX models",
diff --git a/gui/examples/config.json b/gui/examples/config.json
index aa3e83ee..69de988e 100644
--- a/gui/examples/config.json
+++ b/gui/examples/config.json
@@ -3,7 +3,7 @@
     "root": "http://127.0.0.1:5000"
   },
   "params": {
-    "version": "0.8.0",
+    "version": "0.9.0",
     "batch": {
       "default": 1,
       "min": 1,
@@ -166,4 +166,4 @@
       "step": 8
     }
   }
-}
\ No newline at end of file
+}
diff --git a/gui/package.json b/gui/package.json
index 61e100db..622e8458 100644
--- a/gui/package.json
+++ b/gui/package.json
@@ -1,6 +1,6 @@
 {
   "name": "@apextoaster/onnx-web",
-  "version": "0.8.1",
+  "version": "0.9.0",
   "description": "onnx web gui",
   "type": "module",
   "main": "out/src/main.js",