From 58812ab8ca601cc2dd9dbe64c1f3ffd4929fd0ca Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Fri, 12 Apr 2024 22:12:35 -0400 Subject: [PATCH 1/4] Support SDXS 512 model. --- comfy/model_detection.py | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/comfy/model_detection.py b/comfy/model_detection.py index 795af828a..23358a2c0 100644 --- a/comfy/model_detection.py +++ b/comfy/model_detection.py @@ -357,7 +357,14 @@ def unet_config_from_diffusers_unet(state_dict, dtype=None): 'context_dim': 1024, 'num_head_channels': 64, 'transformer_depth_output': [1, 1, 1, 1, 1, 1], 'use_temporal_attention': False, 'use_temporal_resblock': False, 'disable_self_attentions': [True, False, False]} - supported_models = [SDXL, SDXL_refiner, SD21, SD15, SD21_uncliph, SD21_unclipl, SDXL_mid_cnet, SDXL_small_cnet, SDXL_diffusers_inpaint, SSD_1B, Segmind_Vega, KOALA_700M, KOALA_1B, SD09_XS, SDXL_diffusers_ip2p] + SD_XS = {'use_checkpoint': False, 'image_size': 32, 'out_channels': 4, 'use_spatial_transformer': True, 'legacy': False, + 'adm_in_channels': None, 'dtype': dtype, 'in_channels': 4, 'model_channels': 320, 'num_res_blocks': [1, 1, 1], + 'transformer_depth': [0, 1, 1], 'channel_mult': [1, 2, 4], 'transformer_depth_middle': -2, 'use_linear_in_transformer': False, + 'context_dim': 768, 'num_head_channels': 64, 'transformer_depth_output': [0, 0, 1, 1, 1, 1], + 'use_temporal_attention': False, 'use_temporal_resblock': False} + + + supported_models = [SDXL, SDXL_refiner, SD21, SD15, SD21_uncliph, SD21_unclipl, SDXL_mid_cnet, SDXL_small_cnet, SDXL_diffusers_inpaint, SSD_1B, Segmind_Vega, KOALA_700M, KOALA_1B, SD09_XS, SD_XS, SDXL_diffusers_ip2p] for unet_config in supported_models: matches = True From 744ac944db24795881cf41fc4ea015e5ea07a444 Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Sat, 13 Apr 2024 16:12:09 -0400 Subject: [PATCH 2/4] Don't make dynamicPrompts the default on multiline string inputs. This should be less confusing to those who want to use multiline input without them. --- comfy_extras/nodes_clip_sdxl.py | 6 +++--- comfy_extras/nodes_cond.py | 2 +- comfy_extras/nodes_photomaker.py | 2 +- nodes.py | 4 ++-- web/extensions/core/dynamicPrompts.js | 2 +- 5 files changed, 8 insertions(+), 8 deletions(-) diff --git a/comfy_extras/nodes_clip_sdxl.py b/comfy_extras/nodes_clip_sdxl.py index dcf8859fa..3087b917b 100644 --- a/comfy_extras/nodes_clip_sdxl.py +++ b/comfy_extras/nodes_clip_sdxl.py @@ -8,7 +8,7 @@ class CLIPTextEncodeSDXLRefiner: "ascore": ("FLOAT", {"default": 6.0, "min": 0.0, "max": 1000.0, "step": 0.01}), "width": ("INT", {"default": 1024.0, "min": 0, "max": MAX_RESOLUTION}), "height": ("INT", {"default": 1024.0, "min": 0, "max": MAX_RESOLUTION}), - "text": ("STRING", {"multiline": True}), "clip": ("CLIP", ), + "text": ("STRING", {"multiline": True, "dynamicPrompts": True}), "clip": ("CLIP", ), }} RETURN_TYPES = ("CONDITIONING",) FUNCTION = "encode" @@ -30,8 +30,8 @@ class CLIPTextEncodeSDXL: "crop_h": ("INT", {"default": 0, "min": 0, "max": MAX_RESOLUTION}), "target_width": ("INT", {"default": 1024.0, "min": 0, "max": MAX_RESOLUTION}), "target_height": ("INT", {"default": 1024.0, "min": 0, "max": MAX_RESOLUTION}), - "text_g": ("STRING", {"multiline": True, "default": "CLIP_G"}), "clip": ("CLIP", ), - "text_l": ("STRING", {"multiline": True, "default": "CLIP_L"}), "clip": ("CLIP", ), + "text_g": ("STRING", {"multiline": True, "dynamicPrompts": True}), "clip": ("CLIP", ), + "text_l": ("STRING", {"multiline": True, "dynamicPrompts": True}), "clip": ("CLIP", ), }} RETURN_TYPES = ("CONDITIONING",) FUNCTION = "encode" diff --git a/comfy_extras/nodes_cond.py b/comfy_extras/nodes_cond.py index 646fefa17..4c3a1d5bf 100644 --- a/comfy_extras/nodes_cond.py +++ b/comfy_extras/nodes_cond.py @@ -3,7 +3,7 @@ class CLIPTextEncodeControlnet: @classmethod def INPUT_TYPES(s): - return {"required": {"clip": ("CLIP", ), "conditioning": ("CONDITIONING", ), "text": ("STRING", {"multiline": True})}} + return {"required": {"clip": ("CLIP", ), "conditioning": ("CONDITIONING", ), "text": ("STRING", {"multiline": True, "dynamicPrompts": True})}} RETURN_TYPES = ("CONDITIONING",) FUNCTION = "encode" diff --git a/comfy_extras/nodes_photomaker.py b/comfy_extras/nodes_photomaker.py index 90130142b..29d127d74 100644 --- a/comfy_extras/nodes_photomaker.py +++ b/comfy_extras/nodes_photomaker.py @@ -141,7 +141,7 @@ class PhotoMakerEncode: return {"required": { "photomaker": ("PHOTOMAKER",), "image": ("IMAGE",), "clip": ("CLIP", ), - "text": ("STRING", {"multiline": True, "default": "photograph of photomaker"}), + "text": ("STRING", {"multiline": True, "dynamicPrompts": True, "default": "photograph of photomaker"}), }} RETURN_TYPES = ("CONDITIONING",) diff --git a/nodes.py b/nodes.py index 78e0cf116..fda073cfc 100644 --- a/nodes.py +++ b/nodes.py @@ -47,7 +47,7 @@ MAX_RESOLUTION=16384 class CLIPTextEncode: @classmethod def INPUT_TYPES(s): - return {"required": {"text": ("STRING", {"multiline": True}), "clip": ("CLIP", )}} + return {"required": {"text": ("STRING", {"multiline": True, "dynamicPrompts": True}), "clip": ("CLIP", )}} RETURN_TYPES = ("CONDITIONING",) FUNCTION = "encode" @@ -966,7 +966,7 @@ class GLIGENTextBoxApply: return {"required": {"conditioning_to": ("CONDITIONING", ), "clip": ("CLIP", ), "gligen_textbox_model": ("GLIGEN", ), - "text": ("STRING", {"multiline": True}), + "text": ("STRING", {"multiline": True, "dynamicPrompts": True}), "width": ("INT", {"default": 64, "min": 8, "max": MAX_RESOLUTION, "step": 8}), "height": ("INT", {"default": 64, "min": 8, "max": MAX_RESOLUTION, "step": 8}), "x": ("INT", {"default": 0, "min": 0, "max": MAX_RESOLUTION, "step": 8}), diff --git a/web/extensions/core/dynamicPrompts.js b/web/extensions/core/dynamicPrompts.js index 599a9e685..7417361ba 100644 --- a/web/extensions/core/dynamicPrompts.js +++ b/web/extensions/core/dynamicPrompts.js @@ -17,7 +17,7 @@ app.registerExtension({ // Locate dynamic prompt text widgets // Include any widgets with dynamicPrompts set to true, and customtext const widgets = node.widgets.filter( - (n) => (n.type === "customtext" && n.dynamicPrompts !== false) || n.dynamicPrompts + (n) => n.dynamicPrompts ); for (const widget of widgets) { // Override the serialization of the value to resolve dynamic prompts for all widgets supporting it in this node From 258dbc06c34ebf723ae17fa23207407e2e05fad1 Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Sun, 14 Apr 2024 12:08:58 -0400 Subject: [PATCH 3/4] Fix some memory related issues. --- comfy/model_management.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/comfy/model_management.py b/comfy/model_management.py index 310ec2537..537df41ed 100644 --- a/comfy/model_management.py +++ b/comfy/model_management.py @@ -617,7 +617,8 @@ def supports_dtype(device, dtype): #TODO def device_supports_non_blocking(device): if is_device_mps(device): return False #pytorch bug? mps doesn't support non blocking - return True + return False + # return True #TODO: figure out why this causes issues def cast_to_device(tensor, device, dtype, copy=False): device_supports_cast = False From 719fb2c81d716ce8edd7f1bdc7804ae160a71d3a Mon Sep 17 00:00:00 2001 From: comfyanonymous Date: Sun, 14 Apr 2024 23:34:25 -0400 Subject: [PATCH 4/4] Add basic PAG node. --- comfy/model_patcher.py | 31 +++++++++++++++------- comfy_extras/nodes_pag.py | 56 +++++++++++++++++++++++++++++++++++++++ nodes.py | 1 + 3 files changed, 78 insertions(+), 10 deletions(-) create mode 100644 comfy_extras/nodes_pag.py diff --git a/comfy/model_patcher.py b/comfy/model_patcher.py index 657ddf843..cf51c4ad8 100644 --- a/comfy/model_patcher.py +++ b/comfy/model_patcher.py @@ -18,6 +18,26 @@ def apply_weight_decompose(dora_scale, weight): return weight * (dora_scale / weight_norm) +def set_model_options_patch_replace(model_options, patch, name, block_name, number, transformer_index=None): + to = model_options["transformer_options"].copy() + + if "patches_replace" not in to: + to["patches_replace"] = {} + else: + to["patches_replace"] = to["patches_replace"].copy() + + if name not in to["patches_replace"]: + to["patches_replace"][name] = {} + else: + to["patches_replace"][name] = to["patches_replace"][name].copy() + + if transformer_index is not None: + block = (block_name, number, transformer_index) + else: + block = (block_name, number) + to["patches_replace"][name][block] = patch + model_options["transformer_options"] = to + return model_options class ModelPatcher: def __init__(self, model, load_device, offload_device, size=0, current_device=None, weight_inplace_update=False): @@ -109,16 +129,7 @@ class ModelPatcher: to["patches"][name] = to["patches"].get(name, []) + [patch] def set_model_patch_replace(self, patch, name, block_name, number, transformer_index=None): - to = self.model_options["transformer_options"] - if "patches_replace" not in to: - to["patches_replace"] = {} - if name not in to["patches_replace"]: - to["patches_replace"][name] = {} - if transformer_index is not None: - block = (block_name, number, transformer_index) - else: - block = (block_name, number) - to["patches_replace"][name][block] = patch + self.model_options = set_model_options_patch_replace(self.model_options, patch, name, block_name, number, transformer_index=transformer_index) def set_model_attn1_patch(self, patch): self.set_model_patch(patch, "attn1_patch") diff --git a/comfy_extras/nodes_pag.py b/comfy_extras/nodes_pag.py new file mode 100644 index 000000000..c48a3958d --- /dev/null +++ b/comfy_extras/nodes_pag.py @@ -0,0 +1,56 @@ +#Modified/simplified version of the node from: https://github.com/pamparamm/sd-perturbed-attention +#If you want the one with more options see the above repo. + +#My modified one here is more basic but has less chances of breaking with ComfyUI updates. + +import comfy.model_patcher +import comfy.samplers + +class PerturbedAttentionGuidance: + @classmethod + def INPUT_TYPES(s): + return { + "required": { + "model": ("MODEL",), + "scale": ("FLOAT", {"default": 3.0, "min": 0.0, "max": 100.0, "step": 0.1, "round": 0.01}), + } + } + + RETURN_TYPES = ("MODEL",) + FUNCTION = "patch" + + CATEGORY = "_for_testing" + + def patch(self, model, scale): + unet_block = "middle" + unet_block_id = 0 + m = model.clone() + + def perturbed_attention(q, k, v, extra_options, mask=None): + return v + + def post_cfg_function(args): + model = args["model"] + cond_pred = args["cond_denoised"] + cond = args["cond"] + cfg_result = args["denoised"] + sigma = args["sigma"] + model_options = args["model_options"].copy() + x = args["input"] + + if scale == 0: + return cfg_result + + # Replace Self-attention with PAG + model_options = comfy.model_patcher.set_model_options_patch_replace(model_options, perturbed_attention, "attn1", unet_block, unet_block_id) + (pag,) = comfy.samplers.calc_cond_batch(model, [cond], x, sigma, model_options) + + return cfg_result + (cond_pred - pag) * scale + + m.set_model_sampler_post_cfg_function(post_cfg_function, disable_cfg1_optimization=True) + + return (m,) + +NODE_CLASS_MAPPINGS = { + "PerturbedAttentionGuidance": PerturbedAttentionGuidance, +} diff --git a/nodes.py b/nodes.py index fda073cfc..ea1e32030 100644 --- a/nodes.py +++ b/nodes.py @@ -1942,6 +1942,7 @@ def init_custom_nodes(): "nodes_differential_diffusion.py", "nodes_ip2p.py", "nodes_model_merging_model_specific.py", + "nodes_pag.py", ] import_failed = []