Merge branch 'master' into master

README.md

@@ -228,6 +228,12 @@ Just execute the command below:
 
 ```LISTEN_IP``` - IP address for ComfyUI to listen
 
+### AMD ROCm Tips
+
+You can enable experimental memory efficient attention on pytorch 2.5 in ComfyUI on RDNA3 and potentially other AMD GPUs using this command:
+
+```TORCH_ROCM_AOTRITON_ENABLE_EXPERIMENTAL=1 python main.py --use-pytorch-cross-attention```
+
 # Notes
 
 Only parts of the graph that have an output with all the correct inputs will be executed.

comfy/clip_vision.py

@@ -16,13 +16,18 @@ class Output:
     def __setitem__(self, key, item):
         setattr(self, key, item)
 
-def clip_preprocess(image, size=224, mean=[0.48145466, 0.4578275, 0.40821073], std=[0.26862954, 0.26130258, 0.27577711]):
+def clip_preprocess(image, size=224, mean=[0.48145466, 0.4578275, 0.40821073], std=[0.26862954, 0.26130258, 0.27577711], crop=True):
     mean = torch.tensor(mean, device=image.device, dtype=image.dtype)
     std = torch.tensor(std, device=image.device, dtype=image.dtype)
     image = image.movedim(-1, 1)
     if not (image.shape[2] == size and image.shape[3] == size):
-        scale = (size / min(image.shape[2], image.shape[3]))
-        image = torch.nn.functional.interpolate(image, size=(round(scale * image.shape[2]), round(scale * image.shape[3])), mode="bicubic", antialias=True)
+        if crop:
+            scale = (size / min(image.shape[2], image.shape[3]))
+            scale_size = (round(scale * image.shape[2]), round(scale * image.shape[3]))
+        else:
+            scale_size = (size, size)
+
+        image = torch.nn.functional.interpolate(image, size=scale_size, mode="bicubic", antialias=True)
         h = (image.shape[2] - size)//2
         w = (image.shape[3] - size)//2
         image = image[:,:,h:h+size,w:w+size]
@@ -51,9 +56,9 @@ class ClipVisionModel():
     def get_sd(self):
         return self.model.state_dict()
 
-    def encode_image(self, image):
+    def encode_image(self, image, crop=True):
         comfy.model_management.load_model_gpu(self.patcher)
-        pixel_values = clip_preprocess(image.to(self.load_device), size=self.image_size, mean=self.image_mean, std=self.image_std).float()
+        pixel_values = clip_preprocess(image.to(self.load_device), size=self.image_size, mean=self.image_mean, std=self.image_std, crop=crop).float()
         out = self.model(pixel_values=pixel_values, intermediate_output=-2)
 
         outputs = Output()

comfy/k_diffusion/sampling.py

@@ -280,6 +280,9 @@ def sample_dpm_2(model, x, sigmas, extra_args=None, callback=None, disable=None,
 
 @torch.no_grad()
 def sample_dpm_2_ancestral(model, x, sigmas, extra_args=None, callback=None, disable=None, eta=1., s_noise=1., noise_sampler=None):
+    if isinstance(model.inner_model.inner_model.model_sampling, comfy.model_sampling.CONST):
+        return sample_dpm_2_ancestral_RF(model, x, sigmas, extra_args, callback, disable, eta, s_noise, noise_sampler)
+
     """Ancestral sampling with DPM-Solver second-order steps."""
     extra_args = {} if extra_args is None else extra_args
     noise_sampler = default_noise_sampler(x) if noise_sampler is None else noise_sampler
@@ -306,6 +309,39 @@ def sample_dpm_2_ancestral(model, x, sigmas, extra_args=None, callback=None, dis
             x = x + noise_sampler(sigmas[i], sigmas[i + 1]) * s_noise * sigma_up
     return x
 
+@torch.no_grad()
+def sample_dpm_2_ancestral_RF(model, x, sigmas, extra_args=None, callback=None, disable=None, eta=1., s_noise=1., noise_sampler=None):
+    """Ancestral sampling with DPM-Solver second-order steps."""
+    extra_args = {} if extra_args is None else extra_args
+    noise_sampler = default_noise_sampler(x) if noise_sampler is None else noise_sampler
+    s_in = x.new_ones([x.shape[0]])
+    for i in trange(len(sigmas) - 1, disable=disable):
+        denoised = model(x, sigmas[i] * s_in, **extra_args)
+        sigma_down, sigma_up = get_ancestral_step(sigmas[i], sigmas[i + 1], eta=eta)
+        downstep_ratio = 1 + (sigmas[i+1]/sigmas[i] - 1) * eta
+        sigma_down = sigmas[i+1] * downstep_ratio
+        alpha_ip1 = 1 - sigmas[i+1]
+        alpha_down = 1 - sigma_down
+        renoise_coeff = (sigmas[i+1]**2 - sigma_down**2*alpha_ip1**2/alpha_down**2)**0.5
+
+        if callback is not None:
+            callback({'x': x, 'i': i, 'sigma': sigmas[i], 'sigma_hat': sigmas[i], 'denoised': denoised})
+        d = to_d(x, sigmas[i], denoised)
+        if sigma_down == 0:
+            # Euler method
+            dt = sigma_down - sigmas[i]
+            x = x + d * dt
+        else:
+            # DPM-Solver-2
+            sigma_mid = sigmas[i].log().lerp(sigma_down.log(), 0.5).exp()
+            dt_1 = sigma_mid - sigmas[i]
+            dt_2 = sigma_down - sigmas[i]
+            x_2 = x + d * dt_1
+            denoised_2 = model(x_2, sigma_mid * s_in, **extra_args)
+            d_2 = to_d(x_2, sigma_mid, denoised_2)
+            x = x + d_2 * dt_2
+            x = (alpha_ip1/alpha_down) * x + noise_sampler(sigmas[i], sigmas[i + 1]) * s_noise * renoise_coeff
+    return x
 
 def linear_multistep_coeff(order, t, i, j):
     if order - 1 > i:

nodes.py

@@ -392,7 +392,7 @@ class InpaintModelConditioning:
 
     CATEGORY = "conditioning/inpaint"
 
-    def encode(self, positive, negative, pixels, vae, mask, noise_mask):
+    def encode(self, positive, negative, pixels, vae, mask, noise_mask=True):
         x = (pixels.shape[1] // 8) * 8
         y = (pixels.shape[2] // 8) * 8
         mask = torch.nn.functional.interpolate(mask.reshape((-1, 1, mask.shape[-2], mask.shape[-1])), size=(pixels.shape[1], pixels.shape[2]), mode="bilinear")
@@ -971,15 +971,19 @@ class CLIPVisionEncode:
     @classmethod
     def INPUT_TYPES(s):
         return {"required": { "clip_vision": ("CLIP_VISION",),
-                              "image": ("IMAGE",)
+                              "image": ("IMAGE",),
+                              "crop": (["center", "none"],)
                              }}
     RETURN_TYPES = ("CLIP_VISION_OUTPUT",)
     FUNCTION = "encode"
 
     CATEGORY = "conditioning"
 
-    def encode(self, clip_vision, image):
-        output = clip_vision.encode_image(image)
+    def encode(self, clip_vision, image, crop):
+        crop_image = True
+        if crop != "center":
+            crop_image = False
+        output = clip_vision.encode_image(image, crop=crop_image)
         return (output,)
 
 class StyleModelLoader:
@@ -1004,14 +1008,19 @@ class StyleModelApply:
         return {"required": {"conditioning": ("CONDITIONING", ),
                              "style_model": ("STYLE_MODEL", ),
                              "clip_vision_output": ("CLIP_VISION_OUTPUT", ),
+                             "strength": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 10.0, "step": 0.001}),
+                             "strength_type": (["multiply"], ),
                              }}
     RETURN_TYPES = ("CONDITIONING",)
     FUNCTION = "apply_stylemodel"
 
     CATEGORY = "conditioning/style_model"
 
-    def apply_stylemodel(self, clip_vision_output, style_model, conditioning):
+    def apply_stylemodel(self, clip_vision_output, style_model, conditioning, strength, strength_type):
         cond = style_model.get_cond(clip_vision_output).flatten(start_dim=0, end_dim=1).unsqueeze(dim=0)
+        if strength_type == "multiply":
+            cond *= strength
+
         c = []
         for t in conditioning:
             n = [torch.cat((t[0], cond), dim=1), t[1].copy()]