* If you like this model and my other work consider showing you support by Joining my Patreon, buying from my wirestock portfolio or any of the other means available
New Playground v2.5 version.
Finally HGHD_PLAYGROUND_XL meets PLAYGROUND V2.5 though they are unrelated except by name they compliment each other well. This is the best version of the Base HGHD XL model yet. it does exceptionally well with text from prompting if you do it logically. It does an amazing job with realism and photo realistic outputs, it is very artistic and the output quality is unbelievable. none of the test images are altered in any way. they are all exactly as they came out of generation. no edits no upscaling, nothing but the model my LoRAs and the prompting used to create the images. Give It a try and please like rate review and past your creations to the page. also tips don't hurt. if you like this model please consider showing the creator some buzz love!
< NEW CASCADE VERSION>
IMPORTANT READ
There are 2 models needed HGHD_PLAYGROUND_CASCADE LITE B and HGHD_CASCADE LITE C you must have both of these to use STABLE CASCADE though you can likely mix and match as long as they are b and c versions. I created both so they could work together for optimum outputs in the PLAYGROUND style. You will also need the cascade clip and the Cascade 'A' VAE Model the last 2 are just stable cascade versions though I may see about a HGHD version when things improve. I do have the full size versions but they are quite large files and will only do those if the lite versions do well. My testing was basically to see that it works LOL. so try it out. It does take getting used to using but the words work well once you find the right seed and fixed seed will be consistent. It does work in different samplers and schedulers but it definitely takes some trial and error to find your sweet spots. I foung the cfg and steps will vary depending on which you use. Seems fine with long and short prompts. Have fun and please plst to the galleries to show how you were able to use it!
** I have noticed cascade doesn't like weighting--tends to break the model. **
XL version of Original HGHD_PLAYGROUND model. I took some time to upgrade the basic PLAYGROUND model to be better out of the box. I did a couple merges of XL models in the same style as the original. though all are SDXL based. So A blend of artistic and realistic trending on realism. I find it works best between 2 and 5 cfg and 12 and 35 steps though you can push those as you like. It works with XL LoRAS and embeddings so you can tweek as you see fit. I use a wide range of samplers and schedulers but some will definitely do better than others. I like the KARRAS and EXPONENTIAL schedulers and the eular A and DPMPP_3M_sde_gpu and huenpp samplers give some cool outputs But Please experiment with what you like. And I would love to see and hear how it works for you . All feed back is appreciated and I take it seriously so I can improve going forward. Thanks and enjoy
* New Lightening version!
I merged The base PLAYGROUND_XL with SDXL Lightening 4step base. WOW is it fast lol. It is a bit challenging and takes some experimenting but in testing cfg from 1-2.5 were best with the lower end doing best. I would recommend starting a 4 steps. and if lacking detail or clarity increase as needed. Steps from 4 to 8 are fastest and extremely good when run in the Euler sampler with the sgm uniform scheduler. You can use other samplers and schedulers. If you do you may find settings you like more. if you increase cfg and steps above recommended you will get very different results and some just don't run, but it can do the higher counts just slows it down as if you were not using a "LIGHTENING" model lol. again you should try different settings and combinations to find what is working best for the prompt etc. It works well with LoRAS and embeds of various weights. I hope you have as much fun as I did XD.
Legal Stuff
AI model output may sometimes be unpredictable and is not guaranteed to match the input prompt nor to be of any given nature or quality. Do not attempt to generate content that is illegal in your legal jurisdiction or within your country or district of residence. By using this model, you agree that the creator of this model shall in no event be responsible or liable to you or to any third party, whether under contract, warranty, tort (including negligence), strict liability, indemnity or other theory, for any direct, indirect, special, incidental, consequential, exemplary, liquidated or punitive damages or any other damages, including but not limited to loss of profit, revenue or business, cost of substitute procurement, arising in whole or in part from your use of (or inability to use) the model.
Model Restrictions:
To be clear, this model is a derivative of the SDXL 1.0 model and the following restrictions are part of the 2023 Stability AI CreativeML Open RAIL++-M License dated July 26, 2023, with applies to this model and all models that use any component or derivatives of this model. You agree not to use the Model or Derivatives of the Model:
In any way that violates any applicable national, federal, state, local or international law or regulation;
For the purpose of exploiting, harming or attempting to exploit or harm minors in any way;
To generate or disseminate verifiably false information and/or content with the purpose of harming others;
To generate or disseminate personal identifiable information that can be used to harm an individual;
To defame, disparage or otherwise harass others;
For fully automated decision making that adversely impacts an individual’s legal rights or otherwise creates or modifies a binding, enforceable obligation;
For any use intended to or which has the effect of discriminating against or harming individuals or groups based on online or offline social behavior or known or predicted personal or personality characteristics;
To exploit any of the vulnerabilities of a specific group of persons based on their age, social, physical or mental characteristics, in order to materially distort the behavior of a person pertaining to that group in a manner that causes or is likely to cause that person or another person physical or psychological harm; For any use intended to or which has the effect of discriminating against individuals or groups based on legally protected characteristics or categories;
To provide medical advice and medical results interpretation;
To generate or disseminate information for the purpose to be used for administration of justice, law enforcement, immigration or asylum processes, such as predicting an individual will commit fraud/crime commitment (e.g. by text profiling, drawing causal relationships between assertions made in documents, indiscriminate and arbitrarily-targeted use).
Clarifications on the permissible use of this model:
This model is a merge. Therefore it inherits the permissions and restrictions of all models used in its creation.
You may not make merges, extractions, or derivatives of this model and use a less restrictive license than the 2023 Stability AI CreativeML Open RAIL++-M License.
This model may be run and hosted for download on Civitai.com. At this time, no other organization or individual is authorized to host or distribute this model.
You may not sell this model or any of this model’s merges or derivatives.
You must credit this model’s creator if you use this model to create a new merged, mixed, trained, or extracted model.
You may sell images you generate with this model.
You may share merges using this model as long as any merge has the same or more restrictive permissions.
Description
This is the larger part of the 2 models needed to run cascade. It is the unet lite version by the description in the model download information. It is merged with My Playground Base. It is not the lightest version
FAQ
Comments (17)
Hey, did you train the Cascade Lite from scratch?
Edit: Sorry I just saw you wrote you merged it, what tool did you use to merge the Cascade Models?
I am not exactly sure how to train models from scratch. I use comfyUI but have been looking into Kohya though still not sure it does checkpoints. The merge was done with the Workflow I use to do merges in comfy I just had to train 2 separate checkpoints to get the b and c points needed for Cascade.
@HalfGawedHalfDevil So you say they are checkpoints? It's possible that they are not lite models then, as far as I know it's not possible yet to set the lite SC in ckpt files
@gsgsdg I did not set anything I selected stable cascade and used the checkpoint downloaded form stable cascade that is listed as lite. the full versions are at least 50% larger in gb size.
@HalfGawedHalfDevil Hmm you uploaded 8 gb stage C and 4 gb stage B, while the lite versions are 2 gb and 1.3 gb?
@gsgsdg I will check my work flow for exactly what I used. and let you know I ran 2 versions one of which I did not upload here. I installed the regular lite not the bf16 so b was 2.8 and c was 4.12gb. the full version are b 4.55 and c 9.22gb so perhaps it is a result of merging into a 6gb base not sure how it works I just load the models
Can this model somehow be used with ComfyUI? I'm using the standard workflow, Stable Cascade Examples | ComfyUI_examples (comfyanonymous.github.io)
I created the checkpoints and the images in the post in ComfyUI. I could not se the actual workflow in the link you sent for whatever reason so not sure what you are running. It is important to have both the B and C models as well as the A model VAE and the necessary clip. so basically 4 pieces needed. it runs through 2 k samplers and some other things so not sure exactly what you may be missing. if you want to attach the workflow maybe I can see whats what.
You can just drag the first image into comfyUI and it will appear. I don't know how to attach a workflow. I'm just confused, I don't even know how to insert the stage A VAE into that workflow, but as far as I can tell, it's the last workflow posted by comfyanonymous himself so I guess it's the one to use for now. It works fine with the default comfy checkpoints. Instructions for stable cascade usage seems in general to be hard to find. Thanks anyway for your effort. I'd just like to be able to try it out.
@snobbias124 I will see if I can send you the workflow i used. sometimes the file is to big to share but you may be at least able to see what you need to run it. I had trouble the first time I tried to set it up
Hey Sorry I wasn't able to share the wf here. you can find one on any of the share platforms on the comfy que side bar. I can also share it in my discord server if you want to join there. https://discord.gg/5Azx3AfP
There is three model workflow. It is however early version what is on hugging face since it sometimes simply generates nonsense. eg a blur where you set the prompt as "a forest"
This should work. You need to place B and C into unet and a into VAE
```
{
"last_node_id": 42,
"last_link_id": 109,
"nodes": [
{
"id": 8,
"type": "VAEDecode",
"pos": [
1026,
178
],
"size": {
"0": 210,
"1": 46
},
"flags": {},
"order": 13,
"mode": 0,
"inputs": [
{
"link": 98,
"name": "samples",
"type": "LATENT"
},
{
"link": 68,
"name": "vae",
"slot_index": 1,
"type": "VAE"
}
],
"outputs": [
{
"links": [
9
],
"name": "IMAGE",
"slot_index": 0,
"type": "IMAGE"
}
],
"properties": {
"Node name for S&R": "VAEDecode"
}
},
{
"id": 29,
"type": "VAELoader",
"pos": [
969,
686
],
"size": {
"0": 315,
"1": 58
},
"flags": {},
"order": 0,
"mode": 0,
"outputs": [
{
"links": [
68
],
"name": "VAE",
"shape": 3,
"type": "VAE"
}
],
"properties": {
"Node name for S&R": "VAELoader"
},
"widgets_values": [
"stage_a.safetensors"
],
"color": "#432",
"bgcolor": "#653"
},
{
"id": 9,
"type": "SaveImage",
"pos": [
1313,
148
],
"size": {
"0": 935.7432250976562,
"1": 1006.83154296875
},
"flags": {},
"order": 14,
"mode": 0,
"inputs": [
{
"link": 9,
"name": "images",
"type": "IMAGE"
}
],
"properties": {},
"widgets_values": [
"ComfyUI"
]
},
{
"id": 41,
"type": "LoraLoader",
"pos": [
141,
-203
],
"size": {
"0": 315,
"1": 126
},
"flags": {},
"order": 1,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": null
},
{
"name": "clip",
"type": "CLIP",
"link": null
}
],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": null,
"shape": 3
},
{
"name": "CLIP",
"type": "CLIP",
"links": null,
"shape": 3
}
],
"properties": {
"Node name for S&R": "LoraLoader"
},
"widgets_values": [
"00_gundam-10.safetensors",
1,
1
]
},
{
"id": 42,
"type": "LoraLoader",
"pos": [
517,
-203
],
"size": {
"0": 315,
"1": 126
},
"flags": {},
"order": 2,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": null
},
{
"name": "clip",
"type": "CLIP",
"link": null
}
],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": null,
"shape": 3
},
{
"name": "CLIP",
"type": "CLIP",
"links": null,
"shape": 3
}
],
"properties": {
"Node name for S&R": "LoraLoader"
},
"widgets_values": [
"00_gundam-10.safetensors",
1,
1
]
},
{
"id": 32,
"type": "UNETLoader",
"pos": [
-194,
273
],
"size": {
"0": 315,
"1": 58
},
"flags": {},
"order": 3,
"mode": 0,
"outputs": [
{
"links": [
84
],
"name": "MODEL",
"shape": 3,
"slot_index": 0,
"type": "MODEL"
}
],
"properties": {
"Node name for S&R": "UNETLoader"
},
"widgets_values": [
"stage_b.safetensors"
],
"color": "#432",
"bgcolor": "#653"
},
{
"id": 30,
"type": "UNETLoader",
"pos": [
-189,
394
],
"size": {
"0": 315,
"1": 58
},
"flags": {},
"order": 4,
"mode": 0,
"outputs": [
{
"links": [
76
],
"name": "MODEL",
"shape": 3,
"slot_index": 0,
"type": "MODEL"
}
],
"properties": {
"Node name for S&R": "UNETLoader"
},
"widgets_values": [
"stage_c.safetensors"
],
"color": "#432",
"bgcolor": "#653"
},
{
"id": 40,
"type": "ConditioningZeroOut",
"pos": [
705,
208
],
"size": {
"0": 211.60000610351562,
"1": 26
},
"flags": {},
"order": 9,
"mode": 0,
"inputs": [
{
"link": 109,
"name": "conditioning",
"type": "CONDITIONING"
}
],
"outputs": [
{
"links": [
104,
105
],
"name": "CONDITIONING",
"shape": 3,
"slot_index": 0,
"type": "CONDITIONING"
}
],
"properties": {
"Node name for S&R": "ConditioningZeroOut"
}
},
{
"id": 36,
"type": "StableCascade_StageB_Conditioning",
"pos": [
975,
270
],
"size": {
"0": 277.20001220703125,
"1": 46
},
"flags": {},
"order": 11,
"mode": 0,
"inputs": [
{
"link": 105,
"name": "conditioning",
"type": "CONDITIONING"
},
{
"link": 88,
"name": "stage_c",
"type": "LATENT"
}
],
"outputs": [
{
"links": [
86
],
"name": "CONDITIONING",
"shape": 3,
"slot_index": 0,
"type": "CONDITIONING"
}
],
"properties": {
"Node name for S&R": "StableCascade_StageB_Conditioning"
}
},
{
"id": 33,
"type": "KSampler",
"pos": [
974,
374
],
"size": {
"0": 315,
"1": 262
},
"flags": {},
"order": 12,
"mode": 0,
"inputs": [
{
"link": 84,
"name": "model",
"slot_index": 0,
"type": "MODEL"
},
{
"link": 86,
"name": "positive",
"type": "CONDITIONING"
},
{
"link": 104,
"name": "negative",
"type": "CONDITIONING"
},
{
"link": 83,
"name": "latent_image",
"type": "LATENT"
}
],
"outputs": [
{
"links": [
98
],
"name": "LATENT",
"slot_index": 0,
"type": "LATENT"
}
],
"properties": {
"Node name for S&R": "KSampler"
},
"widgets_values": [
304817353511516,
"randomize",
20,
1.1,
"ddim",
"ddim_uniform",
1
],
"color": "#223",
"bgcolor": "#335"
},
{
"id": 3,
"type": "KSampler",
"pos": [
603,
311
],
"size": {
"0": 315,
"1": 262
},
"flags": {},
"order": 10,
"mode": 0,
"inputs": [
{
"link": 76,
"name": "model",
"slot_index": 0,
"type": "MODEL"
},
{
"link": 107,
"name": "positive",
"type": "CONDITIONING"
},
{
"link": 108,
"name": "negative",
"type": "CONDITIONING"
},
{
"link": 82,
"name": "latent_image",
"type": "LATENT"
}
],
"outputs": [
{
"links": [
88
],
"name": "LATENT",
"slot_index": 0,
"type": "LATENT"
}
],
"properties": {
"Node name for S&R": "KSampler"
},
"widgets_values": [
970844206805732,
"randomize",
50,
3,
"ddim",
"ddim_uniform",
1
],
"color": "#223",
"bgcolor": "#335"
},
{
"id": 34,
"type": "StableCascade_EmptyLatentImage",
"pos": [
595,
642
],
"size": {
"0": 315,
"1": 150
},
"flags": {},
"order": 5,
"mode": 0,
"outputs": [
{
"links": [
82
],
"name": "stage_c",
"shape": 3,
"slot_index": 0,
"type": "LATENT"
},
{
"links": [
83
],
"name": "stage_b",
"shape": 3,
"slot_index": 1,
"type": "LATENT"
}
],
"properties": {
"Node name for S&R": "StableCascade_EmptyLatentImage"
},
"widgets_values": [
2048,
2048,
42,
1
]
},
{
"id": 6,
"type": "CLIPTextEncode",
"pos": [
184,
107
],
"size": {
"0": 422.84503173828125,
"1": 164.31304931640625
},
"flags": {},
"order": 7,
"mode": 0,
"inputs": [
{
"link": 93,
"name": "clip",
"type": "CLIP"
}
],
"outputs": [
{
"links": [
107,
109
],
"name": "CONDITIONING",
"slot_index": 0,
"type": "CONDITIONING"
}
],
"properties": {
"Node name for S&R": "CLIPTextEncode"
},
"widgets_values": [
"1girl, solo, close up, female looking at camera, purple hair, brown eyes, realistic, 8k, highly textured"
],
"color": "#233",
"bgcolor": "#355"
},
{
"id": 7,
"type": "CLIPTextEncode",
"pos": [
154,
364
],
"size": {
"0": 425.27801513671875,
"1": 180.6060791015625
},
"flags": {
"collapsed": false
},
"order": 8,
"mode": 0,
"inputs": [
{
"link": 94,
"name": "clip",
"type": "CLIP"
}
],
"outputs": [
{
"links": [
108
],
"name": "CONDITIONING",
"slot_index": 0,
"type": "CONDITIONING"
}
],
"properties": {
"Node name for S&R": "CLIPTextEncode"
},
"widgets_values": [
"ugly, deformed, malformed, blurry, extra face"
],
"color": "#323",
"bgcolor": "#535"
},
{
"id": 37,
"type": "CLIPLoader",
"pos": [
157,
612
],
"size": {
"0": 387.2342834472656,
"1": 208.42730712890625
},
"flags": {},
"order": 6,
"mode": 0,
"outputs": [
{
"links": [
93,
94
],
"name": "CLIP",
"shape": 3,
"slot_index": 0,
"type": "CLIP"
}
],
"properties": {
"Node name for S&R": "CLIPLoader"
},
"widgets_values": [
"cascaemodel.safetensors",
"stable_cascade"
],
"color": "#432",
"bgcolor": "#653"
}
],
"links": [
[
9,
8,
0,
9,
0,
"IMAGE"
],
[
68,
29,
0,
8,
1,
"VAE"
],
[
76,
30,
0,
3,
0,
"MODEL"
],
[
82,
34,
0,
3,
3,
"LATENT"
],
[
83,
34,
1,
33,
3,
"LATENT"
],
[
84,
32,
0,
33,
0,
"MODEL"
],
[
86,
36,
0,
33,
1,
"CONDITIONING"
],
[
88,
3,
0,
36,
1,
"LATENT"
],
[
93,
37,
0,
6,
0,
"CLIP"
],
[
94,
37,
0,
7,
0,
"CLIP"
],
[
98,
33,
0,
8,
0,
"LATENT"
],
[
104,
40,
0,
33,
2,
"CONDITIONING"
],
[
105,
40,
0,
36,
0,
"CONDITIONING"
],
[
107,
6,
0,
3,
1,
"CONDITIONING"
],
[
108,
7,
0,
3,
2,
"CONDITIONING"
],
[
109,
6,
0,
40,
0,
"CONDITIONING"
]
],
"groups": [],
"config": {},
"extra": {
"0246.VERSION": [
0,
0,
4
]
},
"version": 0.4
}
```
@mkDaniel @HalfGawedHalfDevil thanks a bunch for your replies. I might join the discord for starters, I just switched to Linux and need to set some things up first to get everyone up and running.
I think your license is wrong, and should also respect the license of playground, which, e. g., has special clause about commercial use
Thanks for the info. this is not being used commercially and it should also be noted in the usage through civit page but I will check. Also I know the name is confusing but the model is not "PLAYGOUND" base. it is simply the name I used when I made the original version and is intended to be a reference to My personal creative playground. I honestly didn't know there was anything playground related. So to be clear it in no way uses any Playground resources and if there is a naming conflict then it will be up to them to contact me to change it. I hope you liked the model despite the conflict you perceived.
@HalfGawedHalfDevil ah okay, sorry then!
@nikolayulyanov988 No Worries! I appreciate that you actually check permissions.!