Model
Trends
.ai
Model
Trends
.ai
i migliori modelli di IA open source
Esegui in locale
pixelwave_sdxl11.safetensors
6.46 GB · SafeTensor · fp16 · full
I download sono forniti da Civitai. Alcuni creatori richiedono prima l'accesso a Civitai.
AD
Installa / Esegui su Graydient
Richiede un abbonamento
<pixelwave11-xl>
Informazioni su questo modello
STABLE DIFFUSION XL 1.0 · Modelli base
Creato da
humblemikey
su Civitai
PixelWave 11 SDXL by HumbleMikey is a general purpose fine tuned model. Great for art and photo styles. I use 20 steps, DPM2M /karras sampler, guidance 4 to 6 or 40 steps
Note del creatore
PixelWave FLUX.1-schnell 04 - Apache 2.0! Safetensor Files: GGUF Files: Links to Model also available at: and PixelWave FLUX.1 schnell version 04 is an aesthetic fine tune of FLUX.1-schnell. The training images were hand picked to ensure the model has a bias to eye catching images, with beautiful colors, textures and lighting. - Trained on the original schnell model, so Apache 2.0 license! - No special requirements to run. Supports FLUX LoRAs - Euler Normal, 8 steps. You can use more steps to improve finer details, but the output doesn't change much after 8 steps. Shout out to RunDiffusion Huge thank you to (co-creators of Juggernaut) for sponsoring the compute that made training this model possible! Figuring out how to train schnell without de-distilling the model required a lot of experimenting, and being able to utilize RunDiffusion's cloud compute made it a lot easier. For those needing API access for this model, we're partnering with I have made the FLUX.1-dev 04 version exclusive to RunDiffusion and Runware for the time being. When I release version 05 in future, I plan to release the dev 04 open weights. Grateful for their support in getting this model out there, please ! Training Training was done with kohya_ss/sd-scripts. You can find my fork of , which also contains changes to the sd-scripts submodule, make sure you clone both. Use the fine tuning tab. I found the best results with the pagedlion8bit optimizer which also could run on my 4090 GPU 24GB. I found other optimizers struggle to learn anything. I have frozen the time_in, vector_in and mod/modulation parameters. This stops the 'de-distillation'. I avoid training single blocks over 15. You can set which blocks to train in the FLUX section. LR 5e-6 trains fast, but you have to stop after a few thousand steps as it starts to corrupt blocks and slow down learning. You can then block merge with an earlier checkpoint, replacing the corrupt blocks, and then continue training further. Signs of corrupt blocks: paper texture over most images, loss of background details. Contact For business or commercial inquiries please reach out to us at . Licensing flux fine tunes. Customer training projects. Commercial AI development. The team can do it all! PixelWave Flux.1-dev 03 fine tuned! Safetensor Files: GGUF Files: Links to The 'diffusers' files are actually the Q8_0 and Q4_K_M GGUF versions. I fine tuned version 03 from base FLUX.1-dev for over 5 weeks on my 4090. It is able to do different art styles, photography, and anime. I used dpmpp 2m sgm uniform 30 steps for the showcase images. If you want a neater/cleaner output, try increasing the guidance. Also mentioning a style can help, so the model doesn't have to guess. I also recommend try adding the upscale latent by node, and scale the latent by 1.5, e.g. generating an image that is 1536x1536 instead of 1024x1024. PixelWave Flux.1-schnell 03 Safetensor Files: GGUF Files: I used dpmpp 2m sgm uniform 8 steps for the showcase images. You can start with 4 steps, but there are less errors with anatomy if you run with more steps. PixelWave Flux.1-dev 02 Safetensor Files: GGUF Files: Version 02 has greatly improved black and dark images, and more reliable outputs with fewer issues with hands. I recommend using dpmpp_2s_ancestral, beta, 14 steps. Or euler, simple, 20 steps. PixelWave 11 SDXL. A general purpose fine tuned model. Great for art and photo styles. I use 20 steps, DPM++ SDE, CFG 4 to 6 or 40 steps, 2M SDE Karras Accelerated Version - 5+ Steps, DPM++ SDE Karras, 2.5 CFG ⚡Recommend 1.5 Scale, with CFG 3. ⭐You don't need to use 'quality' terms such as 4K, 8K, masterpiece, high def, high quality, etc. Unless you want it, I recommend not using words such as 'vibrant, intense, bright, high contrast, neon, dramatic' for photographic styles if you a wanting a more natural look. This can cause images to look 'overcooked', but it's just the CLIP following your prompt. 🙂 If you do want vibrant, neon photos PixelWave will provide! The focus for version 10 was to train the CLIP models, which improves the reliability, ensures you can produce a wide variety of styles, and better at following prompts. Thanks to my friends who helped test: , , , , . No need for the refiner model. This model is not a mix of other models. I also created which contains a lot of useful nodes. You can install it through comfy manager.
3,818 download · 146 mi piace su Civitai
SHA256
4CE82A86FC6709ED8AFBC8BDC8444D31919C8FE7C70F415FCBD47068C3211192
ID modello ModelTrends.ai
#11023
Segnala contenuto
Render di esempio
Prompt e impostazioni condivisi da chi ha realizzato questi render su Civitai. Scegli un render per vedere come è stato fatto.
Impostazioni
Sampler
Euler a
Passi
30
Guidance
4
Seed
3632628304
Dimensioni
832x1216
Prompt
giallo aesthetics photo, depth map, encaustic. a folk music album cover art <lora:artfully_DEPTHMAP:0.6>, vivid color gel, dramatic shadows, fashion backdrop, deep reds and blues, gothic atmosphere, expressionist lighting, technicolor, dramatic shadow work, murder mystery, slasher, thriller, psychological horror, psychological thriller
Prompt negativo
natural lighting, realistic colors, documentary style, minimalist set, chibi, loli, child, kid, teen, teenager, tattoo, dirty, messy, nude
Impostazioni
Sampler
dpmpp_2m
Passi
30
Guidance
5
Seed
1027298399748081
Dimensioni
896x1152
Prompt
forest of coral fungus glowing in a gothic garden, backlit, low-key, highly detailed, high quality, 8k, moody atmosphere
Prompt negativo
photoshop, video game, ugly, tiling, poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, mutation, mutated, extra limbs, extra legs, extra arms, disfigured, deformed, body out of frame, bad art, bad anatomy, 3d render, double, clones, twins, brothers, same face, repeated person, long neck, make up, ugly, animated, hat, poorly drawn, out of frame, text, watermark, signature, logo, split image, copyright, cartoon, desaturated
Impostazioni
Sampler
DPM++ 2M
Passi
40
Guidance
7
Seed
1967099363
Dimensioni
1024x1024
Prompt
A damaged Surrealist painting, (peeling paint on sandpaper:1.2). A grotesque elderly ethereal female elf being a (indigo:0.5) Tiger in a decrepit mountain river, rapids. (Large patches of broken paint reveal a world of lemon). Intricate details. Victorian botanical. white-tinted, white wavy patterns. Symbolism.
Prompt negativo
(Vertical symmetry), (Horizontal symmetry), horror, nudity, naked, nude, Superman, Superwoman, Supergirl, USA flag, American flag
Impostazioni
Sampler
dpmpp_2m
Passi
30
Guidance
6
Seed
1027298399746188
Dimensioni
896x1152
Prompt
Realistic portrait photograph, contemporary style. Close-up of woman, Average height, sleek bob. Soft lighting creates a dramatic, moody ambiance with a dark, textured background. Detailed focus on her eyes. High-resolution image emphasizing texture and natural beauty.
Prompt negativo
photoshop, video game, ugly, tiling, poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, mutation, mutated, extra limbs, extra legs, extra arms, disfigured, deformed, body out of frame, bad art, bad anatomy, 3d render, double, clones, twins, brothers, same face, repeated person, long neck, make up, ugly, animated, hat, poorly drawn, out of frame, text, watermark, signature, logo, split image, copyright, cartoon, desaturated
Impostazioni
Sampler
DPM++ SDE Karras
Passi
28
Guidance
2.4
Seed
100416726572151
Dimensioni
1024x1536
Prompt
breathtaking, professional, highly detailed, a giant lightbulb with a magical fairylight kingdom inside, tiltshift macro hypermaximalist detail
Impostazioni
Sampler
dpmpp_2m
Passi
30
Guidance
6
Seed
1027298399746199
Dimensioni
896x1152
Prompt
Realistic portrait photograph, fantasy style. Close-up of a Garuda (Hindu Bird Creature), anthropomorphic hybrid creature. Soft lighting creates a dramatic, moody ambiance. Detailed focus on their eyes. High-resolution image emphasizing texture.
Prompt negativo
photoshop, video game, ugly, tiling, poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, mutation, mutated, extra limbs, extra legs, extra arms, disfigured, deformed, body out of frame, bad art, bad anatomy, 3d render, double, clones, twins, brothers, same face, repeated person, long neck, make up, ugly, animated, hat, poorly drawn, out of frame, text, watermark, signature, logo, split image, copyright, cartoon, desaturated
Impostazioni
Sampler
dpmpp_2m
Passi
30
Guidance
5
Seed
1027298399748114
Dimensioni
896x1152
Prompt
SYMMETRIC, baroque devilish queen of rot and decay skull, portrait, patina, face, close-up, portrait!!! deer skull. patina LIQUID GOLD, GLITTER, sculpture made of patina bronze and charcoal and high-tech robot panels!!!!. jellyfish phoenix head, nautilus, orchid, betta fish, intricate artwork by Tooth Wu and wlop and beeple. octane render, trending on artstation, greg rutkowski very coherent symmetrical artwork. cinematic, hyper realism, high
Prompt negativo
photoshop, video game, ugly, tiling, poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, mutation, mutated, extra limbs, extra legs, extra arms, disfigured, deformed, body out of frame, bad art, bad anatomy, 3d render, double, clones, twins, brothers, same face, repeated person, long neck, make up, ugly, animated, hat, poorly drawn, out of frame, text, watermark, signature, logo, split image, copyright, cartoon, desaturated
Impostazioni
Sampler
dpmpp_2m
Passi
30
Guidance
6
Seed
1027298399746247
Dimensioni
896x1152
Prompt
Realistic portrait photograph, fantasy style. Close-up of a Inferno elemental spirit. Soft lighting creates a dramatic, moody ambiance. Detailed focus on their eyes. High-resolution image emphasizing texture.
Prompt negativo
photoshop, video game, ugly, tiling, poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, mutation, mutated, extra limbs, extra legs, extra arms, disfigured, deformed, body out of frame, bad art, bad anatomy, 3d render, double, clones, twins, brothers, same face, repeated person, long neck, make up, ugly, animated, hat, poorly drawn, out of frame, text, watermark, signature, logo, split image, copyright, cartoon, desaturated
Modelli di IA per generare immagini, video e testo
pixelwave11 xl è un modello base per la famiglia Stable Diffusion XL 1.0 presente su ModelTrends.ai, un catalogo in sola lettura di modelli di IA open source per immagini, video e testo. Confrontalo con gli altri modelli Stable Diffusion XL 1.0, controlla il punteggio di calore per vedere la tendenza e aprilo su PirateDiffusion o BitVector per provarlo.
Sfoglia per famiglia di modelli
Sfoglia tutti i modelli