diff --git a/docs/compatibility.md b/docs/compatibility.md index f114a44c..7f3c880b 100644 --- a/docs/compatibility.md +++ b/docs/compatibility.md @@ -34,15 +34,23 @@ ## Model/Platform Acceleration -| Model | CUDA | DirectML | ROCm | CPU | -| ---------------- | ---- | -------- | ----- | --- | -| Stable Diffusion | yes | yes | yes | yes | -| Real ESRGAN | yes | yes | no, 1 | yes | -| GFPGAN | 2 | 2 | 2 | yes | +| Model | ONNX | CUDA | DirectML | ROCm | CPU | +| ---------------- | ---- | ----- | -------- | ----- | --- | +| Stable Diffusion | yes | yes | yes | yes | yes | +| - txt2img | yes | ^ | ^ | ^ | ^ | +| - img2img | yes | ^ | ^ | ^ | ^ | +| - inpaint | yes | ^ | ^ | ^ | ^ | +| - upscale | yes | ^ | ^ | ^ | ^ | +| Real ESRGAN | yes | no, 1 | yes | no, 2 | yes | +| - x2/x4 plus | yes | ^ | ^ | ^ | ^ | +| - v3 | yes | ^ | ^ | ^ | ^ | +| GFPGAN | no | - | - | - | - | +| CodeFormer | no | - | - | - | - | ### Model Notes -1. Real ESRGAN running on ROCm crashes with an error: +1. Real ESRGAN running on CUDA falls back to the CPU provider with an unspecified error +2. Real ESRGAN running on ROCm crashes with an error: ```none File "/home/ssube/onnx-web/api/onnx_web/upscale.py", line 67, in __call__ @@ -51,5 +59,3 @@ return self._sess.run(output_names, input_feed, run_options) onnxruntime.capi.onnxruntime_pybind11_state.Fail: [ONNXRuntimeError] : 1 : FAIL : Non-zero status code returned while running FusedConv node. Name:'/body/body.0/rdb1/conv1/Conv' Status Message: MIOPEN failure 1: miopenStatusNotInitialized ; GPU=0 ; hostname=ssube-notwin ; expr=status_; ``` - -2. GFPGAN seems to always be running in CPU mode diff --git a/docs/dev-test.md b/docs/dev-test.md index 1a9af8c4..d822fb44 100644 --- a/docs/dev-test.md +++ b/docs/dev-test.md @@ -91,6 +91,11 @@ Testing: - 1024x768 input - [ ] should work - inpaint + - regular inpaint + - black mask + - [ ] should keep all pixels, same image + - white mask + - [ ] should replace all pixels, different image - outpaint - 0 all sides - [ ] should work, run 1 tile @@ -101,7 +106,6 @@ Testing: - 512 left and right, 0 top and bottom - [ ] should work, run 3 tiles - upscale - - Real ESRGAN - Real ESRGAN - x4 with CodeFormer - [ ] should work @@ -113,8 +117,6 @@ Testing: - [ ] should sort of work: ignores scale and uses x2 - x4 model and x2 scale - [ ] should fail: tiles - - v3 model and x2 scale - - [ ] should work - v3 model and x4 scale - [ ] should work - Stable Diffusion @@ -128,6 +130,16 @@ Testing: - [ ] should work - without face correction - [ ] should work +- blend + - two 512x512 inputs + - [ ] should work + - two 1024x1024 inputs + - [ ] should work + - two different size inputs + - 256x256 and 512x512 + - [ ] should work + - 512x512 and 1024x1024 + - [ ] should work - interactions - generate a new image - [ ] should request and then load an image from the server @@ -151,9 +163,25 @@ Testing: - [ ] should switch to the blend tab - [ ] should populate the image sources - [ ] the generate button should be enabled once both sources have been populated - - persist on refresh + - state should persist on refresh - [ ] loading images - [ ] switching tabs + - [ ] images sources do not +- schedulers + - [ ] DDIM + - [ ] DDPM + - [ ] DEIS Multi + - [ ] DPM Multi + - [ ] DPM Single + - [ ] Euler A + - [ ] Euler + - [ ] Heun + - [ ] iPNDM + - [ ] KDPM2 A + - [ ] KDPM2 + - [ ] Karras Ve + - [ ] LMS + - [ ] PNDM Release: