DPM++ 2M Alt Sampler for ComfyUI

DPM++ 2M Alt Sampler for ComfyUI

Made the DPM++ 2M Alt Karras Sampler to work with ComfyUI.

Comparison: Left DPMPP 2M Karras | Right DPMPP 2M Alt Karras

Note: The face isn't an accurate comparison due to different seed in facedetailer, other parts of the picture is using the same seed.

Credits to hallastore, original thread: https://github.com/AUTOMATIC1111/stable-diffusion-webui/discussions/8457

Instructions:

Unzip method:

1. IMPORTANT: Make backup of these two files of just in case new update affects the samplers.

   For ComfyUI Portable:

• ComfyUI_windows_portable\ComfyUI\comfy\samplers.py

• ComfyUI_windows_portable\ComfyUI\comfy\k_diffusion\sampling.py

  For Automatic 1111:

• Stable-diffusion-webui\extensions\sd-webui-comfyui\ComfyUI\comfy\samplers.py

• Stable-diffusion-webui\extensions\sd-webui-comfyui\ComfyUI\comfy\k_diffusion\sampling.py

1. Unpack zip to directory

• For Portable ComfyUI: ComfyUI_windows_portable\ComfyUI\comfy

• For Automatic 1111 ComfyUI extension: Stable-diffusion-webui\extensions\sd-webui-comfyui\ComfyUI\comfy

1. Sampler is named dpmpp_2m_alt in ComfyUI

Manual Method:

1. IMPORTANT: Make backup of these two files of just in case new update affects the samplers.

   For ComfyUI Portable:

• ComfyUI_windows_portable\ComfyUI\comfy\samplers.py

• ComfyUI_windows_portable\ComfyUI\comfy\k_diffusion\sampling.py

  For Automatic 1111:

• Stable-diffusion-webui\extensions\sd-webui-comfyui\ComfyUI\comfy\samplers.py

• Stable-diffusion-webui\extensions\sd-webui-comfyui\ComfyUI\comfy\k_diffusion\sampling.py

  Tips: The following instructions is for ComfyUI Portable but it is the same for Automatic 1111, just navigate to the path given above for the *.py files with the same name.

1. Open ComfyUI_windows_portable\ComfyUI\comfy\samplers.py

   search for KSAMPLER_NAMES

2. 

3. Add dpmpp_2m_alt as a new value and save file, make sure you include the comma and quotes.

4. 

5. Open ComfyUI_windows_portable\ComfyUI\comfy\k_diffusion\sampling.py\

6. Copy the following code.

   @torch.no_grad()
   def sample_dpmpp_2m_alt(model, x, sigmas, extra_args=None, callback=None, disable=None):
       """DPM-Solver++(2M)."""
       extra_args = {} if extra_args is None else extra_args
       s_in = x.new_ones([x.shape[0]])
       sigma_fn = lambda t: t.neg().exp()
       t_fn = lambda sigma: sigma.log().neg()
       old_denoised = None
   for i in trange(len(sigmas) - 1, disable=disable):
       denoised = model(x, sigmas[i] * s_in, **extra_args)
       if callback is not None:
           callback({'x': x, 'i': i, 'sigma': sigmas[i], 'sigma_hat': sigmas[i], 'denoised': denoised})
       t, t_next = t_fn(sigmas[i]), t_fn(sigmas[i + 1])
       h = t_next - t
       
       t_min = min(sigma_fn(t_next), sigma_fn(t))
       t_max = max(sigma_fn(t_next), sigma_fn(t))
   
       if old_denoised is None or sigmas[i + 1] == 0:
           x = (t_min / t_max) * x - (-h).expm1() * denoised
       else:
           h_last = t - t_fn(sigmas[i - 1])
   
           h_min = min(h_last, h)
           h_max = max(h_last, h)
           r = h_max / h_min
   
           h_d = (h_max + h_min) / 2
           denoised_d = (1 + 1 / (2 * r)) * denoised - (1 / (2 * r)) * old_denoised
           x = (t_min / t_max) * x - (-h_d).expm1() * denoised_d
   
       old_denoised = denoised
   return x</code></pre></li><li><p>Scroll all the way to the bottom and paste the code as of the screenshot below then save.</p></li><li><p><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/e9443a54-d320-46de-9587-f876f502a5ff/width=525/e9443a54-d320-46de-9587-f876f502a5ff.jpeg" /></p><ol><li><p>Sampler is named dpmpp_2m_alt in ComfyUI.</p><p></p><p></p></li></ol></li></ol>