Model
Trends
.ai
Model
Trends
.ai
the best open source ai models
Run Locally
colossusProjectXLSFW_v49BakedVAE.safetensors
6.46 GB · SafeTensor · fp16 · full
Downloads are served by Civitai. Some creators ask for a Civitai login first.
AD
Install / Run on Graydient
Requires membership
<colossus49b-xl>
About This Model
STABLE DIFFUSION XL 1.0 · Base Models
Created by
Afroman4peace
on Civitai
Colossus Project XL (SFW&NSFW) by Afroman4peace. A Colossus arise.. again.. Deep under a mountain lives a sleeping giant, capable to eighter help humanity or create destruction... This SD 1.0XL-Checkpoint is capable to produce nearly everything.. Colossus is very good creating extremly realistic pictures, anime and art. This is a merge of my best models I have created so far. Its heavily based on Hephaistos V3.31 and The Talos Project (This is a project I have created with freek22). Then I added parts of my Asmodeus 3.0 model (which isn't released yet). To improve some skin textures I added a small percentage of the Realistic Stock Photo model and Newdawn XL.. Version 4.9b Experime
Creator notes
A Colossus arise.. again.. Deep under a mountain lives a sleeping giant, capable to eighter help humanity or create destruction... This SD 1.0XL-Checkpoint is capable to produce nearly everything.. Colossus is very good creating extremly realistic pictures, anime and art. If you like it, feel free to give me some feedback. Also if you want to support me you can do this here. Version 12C Experimental_3 This is basically a new trained model. It uses parts of DEMONCORE Research and ArtCore. It also got additional training on faces, eyes, hair and landscapes. This version works well on its own but truly shines in combination with DemonFlux. I've created a special workflow for it. Version 10B "NeoDEMON" This version is a pruned FP16 version from the model down below. In my tests it performed similar. So you can save 4GB of diskspace. Note that some images can be different than the full 10.6GB model. Version 10B "NeoDEMON" (Experimental Trained) This version is a complete rebuild based on the dataset of Version 5.3. Its based on my new not yet published DEMONCORE V4 "NeoDEMON". Parts of the graphics are from my Hephaistos 3.31. This Version is better suited for realism but also it handles drawings better. Also it can create amazing details. I have created a special Comfy Workflow for it. Here is the link to the article. The checkpoint also works well with Forge or A1111. Please tell me your opinion about the new checkpoint. Keep in mind V10 MidgardDEMON is very good too.. which got some benefits regarding creating lets say anthro creatures. So its also worth a look. Also check out my other versions like V9 Hera and so on :-) Have fun creating! Enhancer I highly recommend to download my enhancer.. It works well with it :-) The main use of it is within my workflow above. I have tested it also with Forge and it worked well with around 0.05- 0.2 but be aware that it can cause some problems with some samplers. Here is a image I have used it with Forge though.. Usage and Sampler Some advise.. Yes it can create on low steps but I recommend using about 12-16 steps with it. For the sampler.. Feel free to experiment here. I really don't recommend using Heun 2M (normal), 2M SDE (normal), 2M SDE Heun, PLMS) The other sampler should work well. Some tricks I want to share: I don't use much negatives with it. This can boost the overall quality. You can use them though to "force" a style. Like if you want to create drawing... In this case you can put in "photo, realistic". Or when you want a ultra realistic image use "illustration, drawings" in the negatives. I don't recommend embeddings. You can try it but don't blame the checkpoint if it looks bad. If something appears like text or watermarks but these things in the negatives. Also you can put in NSFW in the negatives.. use CLIP skip 2 (or 3 in some cases) The standart for this model is Clip skip 2... Feel free to try other settings though. Here are some examples: Prompt: cinematic, a snowy mointain, a female adventurer in the foreground, dragon on mountain in the background CLIP Skip 1 (this is not how it should be) Clip Skip 2 (this shows the correct image) Version 10th (X) "MidgardDEMON" Well, I never thought to even make ten versions of this checkpoint. Here is it.. a sort of anniversary edition. Thank for all your support :-) Finally I managed to get rid of the most of sampler bugs.. For this I had to basically rebuilt the entire checkpoint structure new from ground up. I used a further delvelopment Hephaistos 3.31 as base and then I added parts from the latest MIDGARD model I created with Freek22 and DEMONCORE Research. . I merged this with the 8 step SDXL Hyper from bytedance. The complete visuals are crafted all over again with own trained Loras I had in my archives. This process alone took about 14 hours of worktime alone... And this was just the first step of many.. I tried to recreate everything you love about Colossus. Even with that the visuals are a bit different. Tell me if you like it :-) So why so much effort? The benefits are truly outstanding.. First the images are much sharper in many situations.. Second I have now a clean canvas to work with in the future. Another benefit is the shocking cfg/scale ratio of this thing. I will add the full version in the training data folder.. For sampler: I will also add a sampler image in the training data. The model itself works from 5 steps or less.. For the test above I used DPM++ 2S a as sampler with 16 steps.. with higher steps you can get more details some times.. Feel free to experiment with it. There are some exeptions from the rule: DON'T use: Heun, DPM++ 2M SDE, DPM++ 2M SDE HEUN, I also don't recommend using DPM++ 2M/Karras. Its way better than before.. For a more detailed look download the training data. Version 9.0 "HERA" This version is a long time in the making.. Its based on a own trained model called "Hera" which isn't public and mixed with parts of my existing version 6.0 and my Hephaistos Lightning model. It also got my SDXL Enhancer Lora and Freek22s Furry enhancer Lora mixed in. This also a sort of restart of this series. Its less censored than my last version.. This was more like a bug in the last version. Also it works with lower steps than version 6.0 Thanks to freek22 for your Furry Enhancer Feel free to give me some feedback about this version. A known bug of the model: It can't produce male organs. I know this already. Use a Lora or another model for this. Here is some technical stuff: I trained on more hand and feet images, so this should be better. Keep in mind that this is still SDXL and it got some limitations.. Version 9 needs less steps to start working. I recommend to start from 4 steps.. Higher steps can and will still improve the image. In my test down below I tried a range from 3-16 steps.. and 1-7cfg. As you can see: with a higher step count you can run higher or even lower cfgs. For the working samplers go down to ve
3,833 downloads · 169 likes on Civitai
SHA256
DD78F6FD1591B971BC1B7A1B818BE69CE63311055190C533B8136BF9462353E7
ModelTrends.ai Model ID
#8035
Flag content
Example renders
Prompts and settings shared by the people who made these renders on Civitai. Pick a render to see how it was made.
Settings
Sampler
DPM++ 2M Karras
Steps
40
Guidance
7
Seed
313275797
Size
512x904
Clip skip
2
Prompt
A masterful composition, gritty and realistic photo, a colossal and scary old mechanized sentient locomotive robot running on a train track with legs, illuminating the night with flames and lights, in a foggy valley, leaving a trail of smoldering coals, HDR, extremely detailed, detailed background, high contrast, bold shifts of light and dark, cinematic, complex and multidimensional lighting, eerie, <lora:xl_more_art-full_v1:0.6>
Negative prompt
worst quality, low quality, ugly, blurry, unaesthetic,
Settings
Sampler
DPM++ SDE Karras
Steps
80
Guidance
6
Size
2016x2592
Prompt
A Photograph capturing the essence of a young cyborg woman with fiery red hair. Her face fills the frame, bathed in neon hues, exuding determination and mystery amidst a futuristic backdrop., undefined
Negative prompt
((blurry)), worst quality, 3D, cgi, drawing, undefined
Settings
Sampler
DPM++ SDE Karras
Steps
30
Guidance
9
Seed
320368383
Size
1024x1024
Prompt
roman gladiator fighting in the colosseum,helmet,blood,audience,game art, pixel art, lucasarts adventure game,lcas artstyle<lora:Lucasarts Artstyle - (Trigger is lcas artstyle):0.8>
Negative prompt
easynegative
Settings
Sampler
Euler a
Steps
48
Guidance
7
Seed
450252794
Size
1160x880
Clip skip
2
Prompt
framed antique painting of <lora:Bosch_Creatures:0.6> Smurfs Bosch_Creatures many dwarves with blue skin wearing medieval clothing with white hats, 2d surreal garden landscape, sinister mushroom creatures in background, (Cracked Paint Texture:1.1), Hieronymus Bosch Creature Style <lora:Hieronymus_Bosch_-_Godfather_of_Religious_Disturbism:0.7> , <lora:Escher_SDXL:0.9> escher infinite city pattern,
Negative prompt
photo, 3d, anime, realistic, nsfw, closeup, cartoon, reality, cgi, animals,
Settings
Sampler
DPM++ SDE Karras
Steps
20
Guidance
7
Seed
3086727946
Size
1024x1024
Prompt
eye of a woman, (Highest Quality, 4k, masterpiece, Amazing Details:1.1), film grain, Fujifilm XT3, photography,
Negative prompt
anime, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured, (worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch)
Settings
Sampler
dpmpp_3m_sde_gpu
Steps
30
Guidance
4.5
Seed
233669299643692
Size
2320x3072
Prompt
void sanrio, hydrodip lion golem with ceramic paintings, kantha style with kintsugi elements, standing in a mysterious forest
Negative prompt
blurry, text. watermarks
Settings
Sampler
DPM++ 3M SDE Karras
Steps
40
Guidance
7
Seed
1726094204
Size
1024x1024
Prompt
Real estate photography style, Adorable 3D Character of cinematic photo photorealistic colorful microscopy shot Tilt-shift photo of a ((pink fluffy cat curious forest spirit flying around)) ritual , (Rhizoid spores, mycelium, gemmae, algue globules, transparent plants protonema , glassy gametophytes, magical virophage organisms), space photography universe tiny, transformed, , tilt-shift (subsurface scattering, soft-body physics, cloth physics) colorful pollen clouds, shimmering dust, ((optical dirty lens, aesthetic lens effects, chromatic aberration)), <lora:add-detail-xl:2.5> . 35mm photograph, film, bokeh, professional, 4k, highly detailed, 3D render, adorable character, 3D art , Professional, inviting, well-lit, high-resolution, property-focused, commercial, highly detailed
Negative prompt
dark, blurry, unappealing, noisy, unprofessional, ugly, deformed, noisy, blurry, low contrast, grunge, sloppy, unkempt, photograph, photo, realistic, drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly, (worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch),tooth, open mouth, dull, blurry,watermark,low quality, black and white, city, fish, big breast, NSFW, jewelry, hairpins, bows, bokeh, blurry, DOF
Settings
Sampler
Euler
Steps
50
Guidance
6.5
Seed
2703424418
Size
768x1024
Prompt
ZIP2D, SK_COMIC, xh, 1girl, solo, female focus, short messy black hair, black long sleeve latex button blouse, white footwear, latex pants, standing, full body, dynamic pose, simple red background highly impressive & realistic, Hyper-detailed, Insane Details, Intricate Details, Cinematics, Editorial Art, Tilt Blur, Super-Resolution, Megapixels, Unreal Engine 5, Studio Lighting, Volumetric, Optical, Diffusion Glowing, Shadows, Proportions, Rough, Shimmery, Ray Tracing Reflections, Glossy, Lumen Reflections, Screen Space Reflections, Diffraction Rating, Chromatic Aberration, GB Shift, Ray Tracing, Ray Tracing Ambient Occlusion Anti-Ali asing, Post-Processing, Post-Production, Cel Shading, Tone Mapping, Incredibly Detailed and Intricate, Hypermaximalist, Sleek, Hyper Realistic, Super Detailed, Dynamic Pose, Hyperrealism, HDI, 8k dramatic lighting, dark colors, wide angle view, (dominant colors are black, white and dark red:1.5), (extreme low key:1.3), high contrast <lora:epi_noiseoffset2:0.3> <lora:add-detail-xl:1> <lora:xl_more_art-full_v1:0.3> <lora:xuehua:1>
Negative prompt
(worst quality, greyscale), ac_neg2, zip2d_neg, ziprealism_neg, watermark, username, signature, text, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, jpeg artifacts, bad feet, extra fingers, mutated hands, poorly drawn hands, bad proportions, extra limbs, disfigured, bad anatomy, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, mutated hands, fused fingers, too many fingers, long neck
AI Models for Image, Video & Text Generation
colossus49b xl is a base model for the Stable Diffusion XL 1.0 family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Stable Diffusion XL 1.0 models, check its heat score to see how it is trending, and open it on PirateDiffusion or BitVector to try it.
Browse by Model Family
Browse all models