[docs] Zero SNR (#3776)

* add zero snr doc

* fix image link

* apply feedback

* separate page

docs/source/en/_toctree.yml

@@ -50,6 +50,8 @@
       title: Distributed inference with multiple GPUs
     - local: using-diffusers/reusing_seeds
       title: Improve image quality with deterministic generation
+    - local: using-diffusers/control_brightness
+      title: Control image brightness
     - local: using-diffusers/reproducibility
       title: Create reproducible pipelines
     - local: using-diffusers/custom_pipeline_examples

docs/source/en/api/pipelines/stable_diffusion/stable_diffusion_2.mdx

@@ -101,7 +101,7 @@ Continue fine-tuning a checkpoint with [`train_text_to_image.py`](https://github
 and `--prediction_type="v_prediction"`.
 - (3) change the sampler to always start from the last timestep; 
 ```py
-pipe.scheduler = DDIMScheduler.from_config(pipe.scheduler.config, timestep_scaling="trailing")
+pipe.scheduler = DDIMScheduler.from_config(pipe.scheduler.config, timestep_spacing="trailing")
 ```
 - (4) rescale classifier-free guidance to prevent over-exposure. 
 ```py
@@ -118,7 +118,7 @@ from diffusers import DiffusionPipeline, DDIMScheduler
 
 pipe = DiffusionPipeline.from_pretrained("ptx0/pseudo-journey-v2", torch_dtype=torch.float16)
 pipe.scheduler = DDIMScheduler.from_config(
-    pipe.scheduler.config, rescale_betas_zero_snr=True, timestep_scaling="trailing"
+    pipe.scheduler.config, rescale_betas_zero_snr=True, timestep_spacing="trailing"
 )
 pipe.to("cuda")
 

docs/source/en/api/schedulers/ddim.mdx

@@ -59,7 +59,7 @@ Continue fine-tuning a checkpoint with [`train_text_to_image.py`](https://github
 and `--prediction_type="v_prediction"`.
 - (3) change the sampler to always start from the last timestep; 
 ```py
-pipe.scheduler = DDIMScheduler.from_config(pipe.scheduler.config, timestep_scaling="trailing")
+pipe.scheduler = DDIMScheduler.from_config(pipe.scheduler.config, timestep_spacing="trailing")
 ```
 - (4) rescale classifier-free guidance to prevent over-exposure. 
 ```py
@@ -76,7 +76,7 @@ from diffusers import DiffusionPipeline, DDIMScheduler
 
 pipe = DiffusionPipeline.from_pretrained("ptx0/pseudo-journey-v2", torch_dtype=torch.float16)
 pipe.scheduler = DDIMScheduler.from_config(
-    pipe.scheduler.config, rescale_betas_zero_snr=True, timestep_scaling="trailing"
+    pipe.scheduler.config, rescale_betas_zero_snr=True, timestep_spacing="trailing"
 )
 pipe.to("cuda")
 

docs/source/en/using-diffusers/control_brightness.mdx

@@ -0,0 +1,45 @@
+# Control image brightness
+
+The Stable Diffusion pipeline is mediocre at generating images that are either very bright or dark as explained in the [Common Diffusion Noise Schedules and Sample Steps are Flawed](https://huggingface.co/papers/2305.08891) paper. The solutions proposed in the paper are currently implemented in the [`DDIMScheduler`] which you can use to improve the lighting in your images.
+
+<Tip>
+
+💡 Take a look at the paper linked above for more details about the proposed solutions!
+
+</Tip>
+
+One of the solutions is to train a model with *v prediction* and *v loss*. Add the following flag to the [`train_text_to_image.py`](https://github.com/huggingface/diffusers/blob/main/examples/text_to_image/train_text_to_image.py) or [`train_text_to_image_lora.py`](https://github.com/huggingface/diffusers/blob/main/examples/text_to_image/train_text_to_image_lora.py) scripts to enable `v_prediction`:
+
+```bash
+--prediction_type="v_prediction"
+```
+
+For example, let's use the [`ptx0/pseudo-journey-v2`](https://huggingface.co/ptx0/pseudo-journey-v2) checkpoint which has been finetuned with `v_prediction`.
+
+Next, configure the following parameters in the [`DDIMScheduler`]:
+
+1. `rescale_betas_zero_snr=True`, rescales the noise schedule to zero terminal signal-to-noise ratio (SNR)
+2. `timestep_spacing="trailing"`, starts sampling from the last timestep
+
+```py
+>>> from diffusers import DiffusionPipeline, DDIMScheduler
+
+>>> pipeline = DiffusioPipeline.from_pretrained("ptx0/pseudo-journey-v2")
+# switch the scheduler in the pipeline to use the DDIMScheduler
+
+>>> pipeline.scheduler = DDIMScheduler.from_config(
+...     pipeline.scheduler.config, rescale_betas_zero_snr=True, timestep_spacing="trailing"
+... )
+>>> pipeline.to("cuda")
+```
+
+Finally, in your call to the pipeline, set `guidance_rescale` to prevent overexposure:
+
+```py
+prompt = "A lion in galaxies, spirals, nebulae, stars, smoke, iridescent, intricate detail, octane render, 8k"
+image = pipeline(prompt, guidance_rescale=0.7).images[0]
+```
+
+<div class="flex justify-center">
+    <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/zero_snr.png"/>
+</div>

tests/pipelines/stable_diffusion_2/test_stable_diffusion_v_pred.py

@@ -392,7 +392,7 @@ class StableDiffusion2VPredictionPipelineIntegrationTests(unittest.TestCase):
 
         pipe = StableDiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-2-1")
         pipe.scheduler = DDIMScheduler.from_config(
-            pipe.scheduler.config, timestep_scaling="trailing", rescale_betas_zero_snr=True
+            pipe.scheduler.config, timestep_spacing="trailing", rescale_betas_zero_snr=True
         )
         pipe.to(torch_device)
         pipe.enable_attention_slicing()