ComfyUI icon indicating copy to clipboard operation
ComfyUI copied to clipboard
Published 3 weeks ago • verified publisher icon comfyanonymous

Comfui images vs Offical demo about Lumina-Image 2.0

Open ChinChyi opened this issue 11 months ago • 8 comments

Thanks to ComfyUI for supporting Lumina-Image 2.0. We have noticed that the images generated by ComfyUI differ significantly from those produced by our official demo, as shown below:

Prompt ComfyUI Images Official Demo
一位穿着深蓝色盔甲的神秘剑士特写，他的面容隐没在金属面罩后，眼中透露着冷酷的光芒，背后是闪烁的城市灯火，剑身上闪现着红色能量，面罩上有复杂的纹路，环境暗淡、充满肃杀气氛 ComfyUI Official
A charming half-body portrait of a female with deep eyes and long curly hair, soft light outlines her delicate facial features. Her skin is delicate, with a smile on the corner of her mouth, and her eyes are gentle but firm. Her right hand gently stroked her collarbone, her fingertips were slender and elegant, and her hand lines were smooth and natural. A beam of sunlight shone on her face, sharp light and shadow, the background is soft warm tones to blur the light and shadow, ComfyUI Official
This is a high-definition indoor photo with a style that leans towards daily life In the picture, there is a young woman wearing a gray tank top and black sports shorts, sitting on the floor with her legs slightly bent and her body facing to the right Her eyes were fixed on the camera in her hand, as if carefully observing or adjusting the camera settings Her expression was calm, her hair was flowing down, dark brown in color, with long hair flowing down and no bangs She wears a white wristband on her left hand and holds a camera in her right hand On her left side, there is a wooden table with a glass of water and a pair of headphones placed on it In the background, some blurry furniture and items can be seen, such as white plush toys and wooden cabinets ComfyUI Official
A charismatic speaker is captured mid-speech. He has short, tousled brown hair that's slightly messy on top. He has a round circle face, clean shaven, adorned with rounded rectangular-framed glasses with dark rims, is animated as he gestures with his left hand. He is holding a black microphone in his right hand, speaking passionately. The man is wearing a light grey sweater over a white t-shirt. He's also wearing a simple black lanyard hanging around his neck. ComfyUI Official
充满魔法光辉的城市，夕阳下，拥有粉色长发的魔法少女穿着华丽的战斗服，手持发光权杖，背景是未来都市的摩天大楼，光影交错，充满梦幻色彩 ComfyUI Official
Layered paper of wave, aesthetic, epic detail, dreamy blue color, starry night ComfyUI Official

The potential reasons for the differences are:

  • CFG Renorm is vital for improving generation quality.
  • System prompt is missing, which plays an important role in enhancing the visual quality and instrution following ability.
  • CFG truncation is not implemented, acceleration without compromising quality.

These factors contribute significantly to the variations observed between ComfyUI and our official demo outputs.

ChinChyi avatar Feb 07 '25 19:02 ChinChyi

Seeds are not equivalent between your demo and ComfyUI. If I use the same settings the output image is very close.

You have to change the code of your demo to use cpu noise instead of GPU and then the results will be very close.

comfyanonymous avatar Feb 08 '25 00:02 comfyanonymous

Lumina2 implements CFGRenorm as demonstrated in the code. However, the current version of Lumina-Image 2.0 supported by ComfyUI does not include CFGRenorm. In our modified version of modified ComfyUI, we have added support for CFGRenorm through a new node, as shown below.

Image

We test several prompts using ComfyUI as below. The comparison uses the same cpu seed in ComfyUI. Our results indicate that CFGRenorm plays a crucial role in generating high-quality images.

prompt seed 1 with cfg_renorm seed 2 with cfg_renorm seed 1 without cfg_renorm seed 2 without cfg_renorm
(((Masterpiece))), (((Best Quality))), a majestic snow leopard gracefully strides across a pristine snowy landscape, its fur shimmering under the soft moonlight. The scene is captured as a (((cinematic shot))), emphasizing the animal's silent yet powerful elegance. The image is rendered in the style of (((digital painting))) with (((surreal details))), including intricate patterns of the leopard’s fur and glistening snowflakes. The atmosphere is tranquil and (((awe-inspiring))), with the (((glowing))) Northern Lights illuminating the night sky, adding a magical touch to the winter wonderland. Image Image Image Image
一只画着指甲的手，手里拿着一张以抽象水彩设计为特色的肯定卡，上面用粗体字“LOREM IPSUM”和“dolor sit amet”写着手写字体。 Image Image Image Image
一位穿着深蓝色盔甲的神秘剑士特写，他的面容隐没在金属面罩后，眼中透露着冷酷的光芒，背后是闪烁的城市灯火，剑身上闪现着红色能量，面罩上有复杂的纹路，环境暗淡、充满肃杀气氛 Image Image Image Image
Layered paper of wave, aesthetic, epic detail, dreamy blue color, starry night Image Image Image Image
充满魔法光辉的城市，夕阳下，拥有粉色长发的魔法少女穿着华丽的战斗服，手持发光权杖，背景是未来都市的摩天大楼，光影交错，充满梦幻色彩 Image Image Image Image

Additionally, we observe that the prompts in the current Lumina-Image 2.0 supported by ComfyUI are inaccurate.

positive prompt negative prompt
official system_prompt + caption system_prompt + blurry ugly bad
ComfyUI system_prompt + <Prompt Start> + caption blurry ugly bad

lzyhha avatar Feb 08 '25 11:02 lzyhha

Workflow from here (minorly altered) https://comfyanonymous.github.io/ComfyUI_examples/lumina2/ In my subjective opinion the result is not 1 to 1 but is quite similar.

Image

Image

Ratinod avatar Feb 08 '25 17:02 Ratinod

@Ratinod @comfyanonymous Although the results you implemented are very close to the ones we showcased, there are still some differences in the implementation, including components like CFG Renorm. Would it be possible for us to submit a PR to update these?

ChinChyi avatar Feb 10 '25 07:02 ChinChyi

Yes you can submit a PR.

comfyanonymous avatar Feb 11 '25 13:02 comfyanonymous

@comfyanonymous Hello, we have already submitted the PR and would appreciate it if you could review it at your earliest convenience. Thank you!

ChinChyi avatar Feb 13 '25 14:02 ChinChyi

@comfyanonymous The renormCFG throw an error when using batch size bigger than 1

2025-03-03T19:37:00.239906 - 0%| | 0/25 [00:02<?, ?it/s]2025-03-03T19:37:00.239906 - 2025-03-03T19:37:00.242906 - !!! Exception during processing !!! Boolean value of Tensor with more than one value is ambiguous 2025-03-03T19:37:00.244904 - Traceback (most recent call last): File "C:\Users\keven\myspace\projet\ComfyUI_windows_portable\ComfyUI\execution.py", line 327, in execute output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\keven\myspace\projet\ComfyUI_windows_portable\ComfyUI\execution.py", line 202, in get_output_data return_values = _map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\keven\myspace\projet\ComfyUI_windows_portable\ComfyUI\execution.py", line 174, in map_node_over_list process_inputs(input_dict, i) File "C:\Users\keven\myspace\projet\ComfyUI_windows_portable\ComfyUI\execution.py", line 163, in process_inputs results.append(getattr(obj, func)(**inputs)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\keven\myspace\projet\ComfyUI_windows_portable\ComfyUI\nodes.py", line 1542, in sample return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\keven\myspace\projet\ComfyUI_windows_portable\ComfyUI\nodes.py", line 1509, in common_ksampler samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\keven\myspace\projet\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-impact-pack\modules\impact\sample_error_enhancer.py", line 22, in informative_sample raise e File "C:\Users\keven\myspace\projet\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-impact-pack\modules\impact\sample_error_enhancer.py", line 9, in informative_sample return original_sample(*args, **kwargs) # This code helps interpret error messages that occur within exceptions but does not have any impact on other operations. ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\keven\myspace\projet\ComfyUI_windows_portable\ComfyUI\comfy\sample.py", line 45, in sample samples = sampler.sample(noise, positive, negative, cfg=cfg, latent_image=latent_image, start_step=start_step, last_step=last_step, force_full_denoise=force_full_denoise, denoise_mask=noise_mask, sigmas=sigmas, callback=callback, disable_pbar=disable_pbar, seed=seed) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\keven\myspace\projet\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 1133, in sample return sample(self.model, noise, positive, negative, cfg, self.device, sampler, sigmas, self.model_options, latent_image=latent_image, denoise_mask=denoise_mask, callback=callback, disable_pbar=disable_pbar, seed=seed) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\keven\myspace\projet\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 1023, in sample return cfg_guider.sample(noise, latent_image, sampler, sigmas, denoise_mask, callback, disable_pbar, seed) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\keven\myspace\projet\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 1008, in sample output = executor.execute(noise, latent_image, sampler, sigmas, denoise_mask, callback, disable_pbar, seed) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\keven\myspace\projet\ComfyUI_windows_portable\ComfyUI\comfy\patcher_extension.py", line 110, in execute return self.original(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\keven\myspace\projet\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 976, in outer_sample output = self.inner_sample(noise, latent_image, device, sampler, sigmas, denoise_mask, callback, disable_pbar, seed) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\keven\myspace\projet\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 959, in inner_sample samples = executor.execute(self, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\keven\myspace\projet\ComfyUI_windows_portable\ComfyUI\comfy\patcher_extension.py", line 110, in execute return self.original(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\keven\myspace\projet\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 738, in sample samples = self.sampler_function(model_k, noise, sigmas, extra_args=extra_args, callback=k_callback, disable=disable_pbar, **self.extra_options) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\keven\myspace\projet\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\utils_contextlib.py", line 116, in decorate_context return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "C:\Users/keven/myspace/projet/ComfyUI_windows_portable/ComfyUI\comfy\k_diffusion\sampling.py", line 1333, in sample_res_multistep return res_multistep(model, x, sigmas, extra_args=extra_args, callback=callback, disable=disable, s_noise=s_noise, noise_sampler=noise_sampler, eta=0., cfg_pp=False) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\keven\myspace\projet\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\utils_contextlib.py", line 116, in decorate_context return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "C:\Users/keven/myspace/projet/ComfyUI_windows_portable/ComfyUI\comfy\k_diffusion\sampling.py", line 1292, in res_multistep denoised = model(x, sigmas[i] * s_in, **extra_args) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\keven\myspace\projet\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 390, in call out = self.inner_model(x, sigma, model_options=model_options, seed=seed) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\keven\myspace\projet\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 939, in call return self.predict_noise(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\keven\myspace\projet\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 942, in predict_noise return sampling_function(self.inner_model, x, timestep, self.conds.get("negative", None), self.conds.get("positive", None), self.cfg, model_options=model_options, seed=seed) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\keven\myspace\projet\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 377, in sampling_function return cfg_function(model, out[0], out[1], cond_scale, x, timestep, model_options=model_options, cond=cond, uncond=uncond) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\keven\myspace\projet\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 350, in cfg_function cfg_result = x - model_options"sampler_cfg_function" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\keven\myspace\projet\ComfyUI_windows_portable\ComfyUI\comfy_extras\nodes_lumina2.py", line 40, in renorm_cfg_func if new_pos_norm >= max_new_norm: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ RuntimeError: Boolean value of Tensor with more than one value is ambiguous

2025-03-03T19:37:00.247904 - Prompt executed in 2.10 seconds

## Attached Workflow
Please make sure that workflow does not contain any sensitive information such as API keys or passwords.

{"last_node_id":17,"last_link_id":23,"nodes":[{"id":7,"type":"CLIPTextEncode","pos":[420,400],"size":[425.27801513671875,180.6060791015625],"flags":{},"order":6,"mode":0,"inputs":[{"name":"clip","localized_name":"clip","type":"CLIP","link":5}],"outputs":[{"name":"CONDITIONING","localized_name":"CONDITIONING","type":"CONDITIONING","links":[6],"slot_index":0}],"title":"CLIP Text Encode (Negative Prompt)","properties":{"cnr_id":"comfy-core","ver":"0.3.19","Node name for S&R":"CLIPTextEncode"},"widgets_values":["blurry ugly bad",[false,true]],"color":"#322","bgcolor":"#533"},{"id":14,"type":"Note","pos":[860,-50],"size":[310,180],"flags":{},"order":0,"mode":0,"inputs":[],"outputs":[],"properties":{},"widgets_values":["The official way to sample this model is: shift 6 with 36 steps\n\nSampling it with lower steps works but you might have to lower the shift value to reduce the amount of artifacts.\n\nEx: 20 steps with shift 3 seems to not produce artifacts"],"color":"#432","bgcolor":"#653"},{"id":3,"type":"KSampler","pos":[863,186],"size":[315,474],"flags":{},"order":8,"mode":0,"inputs":[{"name":"model","localized_name":"model","type":"MODEL","link":23},{"name":"positive","localized_name":"positive","type":"CONDITIONING","link":4},{"name":"negative","localized_name":"negative","type":"CONDITIONING","link":6},{"name":"latent_image","localized_name":"latent_image","type":"LATENT","link":17}],"outputs":[{"name":"LATENT","localized_name":"LATENT","type":"LATENT","links":[14],"slot_index":0}],"properties":{"cnr_id":"comfy-core","ver":"0.3.19","Node name for S&R":"KSampler"},"widgets_values":[611313298494029,"randomize",25,4,"res_multistep","simple",1]},{"id":6,"type":"CLIPTextEncode","pos":[420,190],"size":[423.83001708984375,177.11770629882812],"flags":{},"order":5,"mode":0,"inputs":[{"name":"clip","localized_name":"clip","type":"CLIP","link":3}],"outputs":[{"name":"CONDITIONING","localized_name":"CONDITIONING","type":"CONDITIONING","links":[4],"slot_index":0}],"title":"CLIP Text Encode (Positive Prompt)","properties":{"cnr_id":"comfy-core","ver":"0.3.19","Node name for S&R":"CLIPTextEncode"},"widgets_values":["You are an assistant designed to generate superior images with the superior degree of image-text alignment based on textual prompts or user prompts. <Prompt Start> a cute anime girl with massive fennec ears mouth open and a big fluffy tail long blonde hair and blue eyes wearing a maid outfit with a long black dress and a large purple liquid stained white apron and white gloves and black leggings sitting on a large cushion in the middle of a kitchen in a dark victorian mansion with a stained glass window drinking a glass with a galaxy inside",[false,true]],"color":"#232","bgcolor":"#353"},{"id":8,"type":"VAEDecode","pos":[1209,188],"size":[210,46],"flags":{},"order":9,"mode":0,"inputs":[{"name":"samples","localized_name":"samples","type":"LATENT","link":14},{"name":"vae","localized_name":"vae","type":"VAE","link":8}],"outputs":[{"name":"IMAGE","localized_name":"IMAGE","type":"IMAGE","links":[20],"slot_index":0}],"properties":{"cnr_id":"comfy-core","ver":"0.3.19","Node name for S&R":"VAEDecode"},"widgets_values":[]},{"id":17,"type":"PreviewImage","pos":[1493.858154296875,222.2717742919922],"size":[210,26],"flags":{},"order":10,"mode":0,"inputs":[{"name":"images","localized_name":"images","type":"IMAGE","link":20}],"outputs":[],"properties":{"cnr_id":"comfy-core","ver":"0.3.19","Node name for S&R":"PreviewImage"}},{"id":13,"type":"EmptySD3LatentImage","pos":[530,620],"size":[315,106],"flags":{},"order":1,"mode":0,"inputs":[],"outputs":[{"name":"LATENT","localized_name":"LATENT","type":"LATENT","links":[17],"slot_index":0}],"properties":{"cnr_id":"comfy-core","ver":"0.3.19","Node name for S&R":"EmptySD3LatentImage"},"widgets_values":[1024,1024,2]},{"id":15,"type":"Note","pos":[-211.4844207763672,208.56251525878906],"size":[319.26513671875,197.89625549316406],"flags":{},"order":2,"mode":0,"inputs":[],"outputs":[],"properties":{},"widgets_values":["The "You are an assistant... <Prompt Start> " text before the actual prompt is the one used in the official example.\n\nThe reason it is exposed to the user like this is because the model still works if you modify or remove it."],"color":"#432","bgcolor":"#653"},{"id":4,"type":"CheckpointLoaderSimple","pos":[26,474],"size":[315,98],"flags":{},"order":3,"mode":0,"inputs":[],"outputs":[{"name":"MODEL","localized_name":"MODEL","type":"MODEL","links":[21],"slot_index":0},{"name":"CLIP","localized_name":"CLIP","type":"CLIP","links":[3,5],"slot_index":1},{"name":"VAE","localized_name":"VAE","type":"VAE","links":[8],"slot_index":2}],"properties":{"cnr_id":"comfy-core","ver":"0.3.19","Node name for S&R":"CheckpointLoaderSimple"},"widgets_values":["Lumina\lumina_2.safetensors"]},{"id":11,"type":"ModelSamplingAuraFlow","pos":[122.44300842285156,142.53707885742188],"size":[315,58],"flags":{},"order":4,"mode":0,"inputs":[{"name":"model","localized_name":"model","type":"MODEL","link":21}],"outputs":[{"name":"MODEL","localized_name":"MODEL","type":"MODEL","links":[22],"slot_index":0}],"properties":{"cnr_id":"comfy-core","ver":"0.3.19","Node name for S&R":"ModelSamplingAuraFlow"},"widgets_values":[6]},{"id":16,"type":"RenormCFG","pos":[167.6195526123047,-36.08639144897461],"size":[315,82],"flags":{},"order":7,"mode":0,"inputs":[{"name":"model","localized_name":"model","type":"MODEL","link":22}],"outputs":[{"name":"MODEL","localized_name":"MODEL","type":"MODEL","links":[23],"slot_index":0}],"properties":{"cnr_id":"comfy-core","ver":"0.3.19","Node name for S&R":"RenormCFG"},"widgets_values":[100,1]}],"links":[[3,4,1,6,0,"CLIP"],[4,6,0,3,1,"CONDITIONING"],[5,4,1,7,0,"CLIP"],[6,7,0,3,2,"CONDITIONING"],[8,4,2,8,1,"VAE"],[14,3,0,8,0,"LATENT"],[17,13,0,3,3,"LATENT"],[20,8,0,17,0,"IMAGE"],[21,4,0,11,0,"MODEL"],[22,11,0,16,0,"MODEL"],[23,16,0,3,0,"MODEL"]],"groups":[],"config":{},"extra":{"ds":{"scale":0.7627768444385583,"offset":[361.54938638321636,174.020548913309]},"ue_links":[]},"version":0.4}

poluramus avatar Mar 04 '25 00:03 poluramus

Can be closed since https://github.com/comfyanonymous/ComfyUI/pull/6795 was merged

Weathercold avatar Dec 18 '25 02:12 Weathercold