π Support My Work & Explore More
If this model is useful to you, your support helps me keep publishing free models and open-source AI tools.
Patreon: Support on Patreon
Ko-fi: Buy me a Ko-fi
Buy Me a Coffee: Buy me a Coffee
Discover more of my models, projects, and practical AI resources:
Portfolio: artificialguy.com β models, projects, and experiments.
Prompt library: FindGoodPrompt β curated prompts for image and language models.
AI tools directory: JustGoodAI β a curated directory of useful AI tools.
Twitter/X: @artificialguybr β new models announced here first.
Invictus.Redmond is here!
I'm grateful for the GPU time from Redmond.AI that allowed me to finish this model!
This is a generalist model fine-tuned on Stable Cascade!
The model has a high capacity to generate realistic, artistic images, cars, people, and a wide variety of themes. It's a versatile model.
I really hope you like the model and use it.
Description
This version has less training. It shows better results than the base model and version V1.0, but is a little more similar to the original version of Stable Cascade.
The model seems extremely sensitive to higher training runs even with low LR.
FAQ
Comments (11)
Nice work man, after cursory testing this seems to be the first Stage C finetune I've tried that's actually an upgrade over base. Small details are much less blobby and incoherent compared to base stage c.
Also your model can generate objects. I like to try generating a wrench to test a model's coherence β base C struggles to generate a recognizable wrench, but yours doesn't.
Really great model. I plan to use this for the next while. Thanks.
How to use in Comfyui:
1) Place downloaded model in comfyui's unet folder.
2) Save the following text in a file (do NOT include the leading and trailing --> ```<-- symbols , rename as .json, load in comfyui, make sure to specify both model names, as the one in this file corresponds to how I've name the models on my machine:
```
{"last_node_id":47,"last_link_id":120,"nodes":[{"id":46,"type":"Note","pos":[1622,360],"size":{"0":210,"1":73.69999694824219},"flags":{},"order":0,"mode":0,"properties":{"text":""},"widgets_values":["Stage a is what the VAE is called. It decodes the stage b latent into pixel space."],"color":"#432","bgcolor":"#653"},{"id":44,"type":"Note","pos":[931,418],"size":{"0":272.0986633300781,"1":138.81549072265625},"flags":{},"order":1,"mode":0,"properties":{"text":""},"widgets_values":["This is stage b where the low resolution stage c latent is passed to the stage b model as conditioning. Stage b takes the low resolution latent and upscales it to a higher resolution one. \n\n"],"color":"#432","bgcolor":"#653"},{"id":9,"type":"SaveImage","pos":[1864,269],"size":{"0":971.827392578125,"1":1000.2752075195312},"flags":{},"order":12,"mode":0,"inputs":[{"name":"images","type":"IMAGE","link":9}],"properties":{},"widgets_values":["ComfyUI"]},{"id":3,"type":"KSampler","pos":[552,293],"size":{"0":315,"1":262},"flags":{},"order":8,"mode":0,"inputs":[{"name":"model","type":"MODEL","link":118,"slot_index":0},{"name":"positive","type":"CONDITIONING","link":107},{"name":"negative","type":"CONDITIONING","link":108},{"name":"latent_image","type":"LATENT","link":82}],"outputs":[{"name":"LATENT","type":"LATENT","links":[88],"slot_index":0}],"properties":{"Node name for S&R":"KSampler"},"widgets_values":[548417133970999,"randomize",20,4,"euler_ancestral","simple",1]},{"id":33,"type":"KSampler","pos":[1278,265],"size":{"0":315,"1":262},"flags":{},"order":10,"mode":0,"inputs":[{"name":"model","type":"MODEL","link":113,"slot_index":0},{"name":"positive","type":"CONDITIONING","link":86},{"name":"negative","type":"CONDITIONING","link":117},{"name":"latent_image","type":"LATENT","link":83}],"outputs":[{"name":"LATENT","type":"LATENT","links":[98],"slot_index":0}],"properties":{"Node name for S&R":"KSampler"},"widgets_values":[1120880850824007,"randomize",10,1.1,"euler_ancestral","simple",1]},{"id":34,"type":"StableCascade_EmptyLatentImage","pos":[210,725],"size":{"0":315,"1":150},"flags":{},"order":2,"mode":0,"outputs":[{"name":"stage_c","type":"LATENT","links":[82],"shape":3,"slot_index":0},{"name":"stage_b","type":"LATENT","links":[83],"shape":3,"slot_index":1}],"properties":{"Node name for S&R":"StableCascade_EmptyLatentImage"},"widgets_values":[1024,1024,42,1]},{"id":36,"type":"StableCascade_StageB_Conditioning","pos":[960,240],"size":{"0":277.20001220703125,"1":46},"flags":{},"order":9,"mode":0,"inputs":[{"name":"conditioning","type":"CONDITIONING","link":116,"slot_index":0},{"name":"stage_c","type":"LATENT","link":88}],"outputs":[{"name":"CONDITIONING","type":"CONDITIONING","links":[86],"shape":3,"slot_index":0}],"properties":{"Node name for S&R":"StableCascade_StageB_Conditioning"}},{"id":7,"type":"CLIPTextEncode","pos":[96,528],"size":{"0":432,"1":96},"flags":{},"order":7,"mode":0,"inputs":[{"name":"clip","type":"CLIP","link":120}],"outputs":[{"name":"CONDITIONING","type":"CONDITIONING","links":[108,117],"slot_index":0}],"title":"CLIP Text Encode (Negative Prompt)","properties":{"Node name for S&R":"CLIPTextEncode"},"widgets_values":["text, watermark"],"color":"#322","bgcolor":"#533"},{"id":8,"type":"VAEDecode","pos":[1630,260],"size":{"0":210,"1":46},"flags":{},"order":11,"mode":0,"inputs":[{"name":"samples","type":"LATENT","link":98},{"name":"vae","type":"VAE","link":114,"slot_index":1}],"outputs":[{"name":"IMAGE","type":"IMAGE","links":[9],"slot_index":0}],"properties":{"Node name for S&R":"VAEDecode"}},{"id":43,"type":"Note","pos":[-242,502],"size":{"0":287.48663330078125,"1":173.3572998046875},"flags":{},"order":3,"mode":0,"properties":{"text":""},"widgets_values":["This is stage c, the model generates a low resolution latent, the default compression of 42 means that the width and height of the stage c latent are 1024 divided by 42."],"color":"#432","bgcolor":"#653"},{"id":6,"type":"CLIPTextEncode","pos":[100,280],"size":{"0":432,"1":192},"flags":{},"order":6,"mode":0,"inputs":[{"name":"clip","type":"CLIP","link":119}],"outputs":[{"name":"CONDITIONING","type":"CONDITIONING","links":[107,116],"slot_index":0}],"title":"CLIP Text Encode (Positive Prompt)","properties":{"Node name for S&R":"CLIPTextEncode"},"widgets_values":["evening sunset scenery blue sky nature, glass bottle with a fizzy ice cold freezing rainbow liquid in it"],"color":"#232","bgcolor":"#353"},{"id":47,"type":"UNETLoader","pos":[-250,287],"size":{"0":315,"1":58},"flags":{},"order":4,"mode":0,"outputs":[{"name":"MODEL","type":"MODEL","links":[118],"shape":3,"slot_index":0}],"properties":{"Node name for S&R":"UNETLoader"},"widgets_values":["invictusredmondStable_v11LessTraining.safetensors"]},{"id":42,"type":"CheckpointLoaderSimple","pos":[901,21],"size":[486.2307382812503,98],"flags":{},"order":5,"mode":0,"outputs":[{"name":"MODEL","type":"MODEL","links":[113],"shape":3,"slot_index":0},{"name":"CLIP","type":"CLIP","links":[119,120],"shape":3,"slot_index":1},{"name":"VAE","type":"VAE","links":[114],"shape":3,"slot_index":2}],"properties":{"Node name for S&R":"CheckpointLoaderSimple"},"widgets_values":["SD Cascade\\Official\\stable_cascade_stage_b.safetensors"]}],"links":[[9,8,0,9,0,"IMAGE"],[82,34,0,3,3,"LATENT"],[83,34,1,33,3,"LATENT"],[86,36,0,33,1,"CONDITIONING"],[88,3,0,36,1,"LATENT"],[98,33,0,8,0,"LATENT"],[107,6,0,3,1,"CONDITIONING"],[108,7,0,3,2,"CONDITIONING"],[113,42,0,33,0,"MODEL"],[114,42,2,8,1,"VAE"],[116,6,0,36,0,"CONDITIONING"],[117,7,0,33,2,"CONDITIONING"],[118,47,0,3,0,"MODEL"],[119,42,1,6,0,"CLIP"],[120,42,1,7,0,"CLIP"]],"groups":[{"title":"Stage B","bounding":[877,-63,736,662],"color":"#8A8","font_size":24},{"title":"Stage C","bounding":[-284,188,1159,491],"color":"#b06634","font_size":24}],"config":{},"extra":{},"version":0.4}
```
hello not working?
Error occurred when executing CheckpointLoaderSimple: 'model.diffusion_model.input_blocks.0.0.weight' File "/home/tobias/ComfyUI/execution.py", line 152, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/tobias/ComfyUI/execution.py", line 82, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/tobias/ComfyUI/execution.py", line 75, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/tobias/ComfyUI/nodes.py", line 540, in load_checkpoint out = comfy.sd.load_checkpoint_guess_config(ckpt_path, output_vae=True, output_clip=True, embedding_directory=folder_paths.get_folder_paths("embeddings")) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/tobias/ComfyUI/comfy/sd.py", line 506, in load_checkpoint_guess_config model_config = model_detection.model_config_from_unet(sd, "model.diffusion_model.") ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/tobias/ComfyUI/comfy/model_detection.py", line 193, in model_config_from_unet unet_config = detect_unet_config(state_dict, unet_key_prefix) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/tobias/ComfyUI/comfy/model_detection.py", line 77, in detect_unet_config model_channels = state_dict['{}input_blocks.0.0.weight'.format(key_prefix)].shape[0] ~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Queue size: 0
Extra options
anyone managed to make it do text?
anyone know how to fix "Error occurred when executing CheckpointLoaderSimple: 'model.diffusion_model.input_blocks.0.0.weight'"?
The method of loading the model is "UNET".
ya, this is a Unet Model, not a normal Checkpoint
so you need to put it in your unet folder
Pleasant model. It letΒ΄s artistic styles come through quite a bit more compared to the base model, very welcomed here. :thumbsup: Thank you :-)
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.














