SDXL microconditioning documentation should indicate the correct default order of parameters, so that developers know (huggingface#5155)

* SDXL microconditioning documentation should indicate the correct default order of parameters, so that developers know

* SDXL microconditioning documentation should indicate the correct default order of parameters, so that developers know

* empty

---------

Co-authored-by: bghira <[email protected]>
Co-authored-by: Patrick von Platen <[email protected]>

Author: 3 people

examples/community/lpw_stable_diffusion_xl.py

@@ -1029,7 +1029,7 @@ def __call__(
                 Guidance rescale factor should fix overexposure when using zero terminal SNR.
             original_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
                 If `original_size` is not the same as `target_size` the image will appear to be down- or upsampled.
-                `original_size` defaults to `(width, height)` if not specified. Part of SDXL's micro-conditioning as
+                `original_size` defaults to `(height, width)` if not specified. Part of SDXL's micro-conditioning as
                 explained in section 2.2 of
                 [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
             crops_coords_top_left (`Tuple[int]`, *optional*, defaults to (0, 0)):
@@ -1039,7 +1039,7 @@ def __call__(
                 [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
             target_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
                 For most cases, `target_size` should be set to the desired height and width of the generated image. If
-                not specified it will default to `(width, height)`. Part of SDXL's micro-conditioning as explained in
+                not specified it will default to `(height, width)`. Part of SDXL's micro-conditioning as explained in
                 section 2.2 of [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
 
         Examples:

src/diffusers/pipelines/controlnet/pipeline_controlnet_sd_xl.py

@@ -863,7 +863,7 @@ def __call__(
                 The percentage of total steps at which the ControlNet stops applying.
             original_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
                 If `original_size` is not the same as `target_size` the image will appear to be down- or upsampled.
-                `original_size` defaults to `(width, height)` if not specified. Part of SDXL's micro-conditioning as
+                `original_size` defaults to `(height, width)` if not specified. Part of SDXL's micro-conditioning as
                 explained in section 2.2 of
                 [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
             crops_coords_top_left (`Tuple[int]`, *optional*, defaults to (0, 0)):
@@ -873,7 +873,7 @@ def __call__(
                 [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
             target_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
                 For most cases, `target_size` should be set to the desired height and width of the generated image. If
-                not specified it will default to `(width, height)`. Part of SDXL's micro-conditioning as explained in
+                not specified it will default to `(height, width)`. Part of SDXL's micro-conditioning as explained in
                 section 2.2 of [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
             negative_original_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
                 To negatively condition the generation process based on a specific image resolution. Part of SDXL's

src/diffusers/pipelines/controlnet/pipeline_controlnet_sd_xl_img2img.py

@@ -1028,7 +1028,7 @@ def __call__(
                 The percentage of total steps at which the controlnet stops applying.
             original_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
                 If `original_size` is not the same as `target_size` the image will appear to be down- or upsampled.
-                `original_size` defaults to `(width, height)` if not specified. Part of SDXL's micro-conditioning as
+                `original_size` defaults to `(height, width)` if not specified. Part of SDXL's micro-conditioning as
                 explained in section 2.2 of
                 [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
             crops_coords_top_left (`Tuple[int]`, *optional*, defaults to (0, 0)):
@@ -1038,7 +1038,7 @@ def __call__(
                 [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
             target_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
                 For most cases, `target_size` should be set to the desired height and width of the generated image. If
-                not specified it will default to `(width, height)`. Part of SDXL's micro-conditioning as explained in
+                not specified it will default to `(height, width)`. Part of SDXL's micro-conditioning as explained in
                 section 2.2 of [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
             negative_original_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
                 To negatively condition the generation process based on a specific image resolution. Part of SDXL's

src/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl.py

@@ -676,7 +676,7 @@ def __call__(
                 Guidance rescale factor should fix overexposure when using zero terminal SNR.
             original_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
                 If `original_size` is not the same as `target_size` the image will appear to be down- or upsampled.
-                `original_size` defaults to `(width, height)` if not specified. Part of SDXL's micro-conditioning as
+                `original_size` defaults to `(height, width)` if not specified. Part of SDXL's micro-conditioning as
                 explained in section 2.2 of
                 [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
             crops_coords_top_left (`Tuple[int]`, *optional*, defaults to (0, 0)):
@@ -686,7 +686,7 @@ def __call__(
                 [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
             target_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
                 For most cases, `target_size` should be set to the desired height and width of the generated image. If
-                not specified it will default to `(width, height)`. Part of SDXL's micro-conditioning as explained in
+                not specified it will default to `(height, width)`. Part of SDXL's micro-conditioning as explained in
                 section 2.2 of [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
             negative_original_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
                 To negatively condition the generation process based on a specific image resolution. Part of SDXL's

src/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl_img2img.py

@@ -794,7 +794,7 @@ def __call__(
                 Guidance rescale factor should fix overexposure when using zero terminal SNR.
             original_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
                 If `original_size` is not the same as `target_size` the image will appear to be down- or upsampled.
-                `original_size` defaults to `(width, height)` if not specified. Part of SDXL's micro-conditioning as
+                `original_size` defaults to `(height, width)` if not specified. Part of SDXL's micro-conditioning as
                 explained in section 2.2 of
                 [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
             crops_coords_top_left (`Tuple[int]`, *optional*, defaults to (0, 0)):
@@ -804,7 +804,7 @@ def __call__(
                 [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
             target_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
                 For most cases, `target_size` should be set to the desired height and width of the generated image. If
-                not specified it will default to `(width, height)`. Part of SDXL's micro-conditioning as explained in
+                not specified it will default to `(height, width)`. Part of SDXL's micro-conditioning as explained in
                 section 2.2 of [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
             negative_original_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
                 To negatively condition the generation process based on a specific image resolution. Part of SDXL's

src/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl_inpaint.py

@@ -1028,7 +1028,7 @@ def __call__(
                 [diffusers.models.attention_processor](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py).
             original_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
                 If `original_size` is not the same as `target_size` the image will appear to be down- or upsampled.
-                `original_size` defaults to `(width, height)` if not specified. Part of SDXL's micro-conditioning as
+                `original_size` defaults to `(height, width)` if not specified. Part of SDXL's micro-conditioning as
                 explained in section 2.2 of
                 [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
             crops_coords_top_left (`Tuple[int]`, *optional*, defaults to (0, 0)):
@@ -1038,7 +1038,7 @@ def __call__(
                 [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
             target_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
                 For most cases, `target_size` should be set to the desired height and width of the generated image. If
-                not specified it will default to `(width, height)`. Part of SDXL's micro-conditioning as explained in
+                not specified it will default to `(height, width)`. Part of SDXL's micro-conditioning as explained in
                 section 2.2 of [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
             negative_original_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
                 To negatively condition the generation process based on a specific image resolution. Part of SDXL's

src/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl_instruct_pix2pix.py

@@ -706,7 +706,7 @@ def __call__(
                 Guidance rescale factor should fix overexposure when using zero terminal SNR.
             original_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
                 If `original_size` is not the same as `target_size` the image will appear to be down- or upsampled.
-                `original_size` defaults to `(width, height)` if not specified. Part of SDXL's micro-conditioning as
+                `original_size` defaults to `(height, width)` if not specified. Part of SDXL's micro-conditioning as
                 explained in section 2.2 of
                 [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
             crops_coords_top_left (`Tuple[int]`, *optional*, defaults to (0, 0)):
@@ -716,7 +716,7 @@ def __call__(
                 [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
             target_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
                 For most cases, `target_size` should be set to the desired height and width of the generated image. If
-                not specified it will default to `(width, height)`. Part of SDXL's micro-conditioning as explained in
+                not specified it will default to `(height, width)`. Part of SDXL's micro-conditioning as explained in
                 section 2.2 of [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
             aesthetic_score (`float`, *optional*, defaults to 6.0):
                 Used to simulate an aesthetic score of the generated image by influencing the positive text condition.

src/diffusers/pipelines/t2i_adapter/pipeline_stable_diffusion_xl_adapter.py

@@ -734,7 +734,7 @@ def __call__(
                 Guidance rescale factor should fix overexposure when using zero terminal SNR.
             original_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
                 If `original_size` is not the same as `target_size` the image will appear to be down- or upsampled.
-                `original_size` defaults to `(width, height)` if not specified. Part of SDXL's micro-conditioning as
+                `original_size` defaults to `(height, width)` if not specified. Part of SDXL's micro-conditioning as
                 explained in section 2.2 of
                 [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
             crops_coords_top_left (`Tuple[int]`, *optional*, defaults to (0, 0)):
@@ -744,7 +744,7 @@ def __call__(
                 [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
             target_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
                 For most cases, `target_size` should be set to the desired height and width of the generated image. If
-                not specified it will default to `(width, height)`. Part of SDXL's micro-conditioning as explained in
+                not specified it will default to `(height, width)`. Part of SDXL's micro-conditioning as explained in
                 section 2.2 of [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
                 section 2.2 of [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
             negative_original_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):