Diffus
Get started
models/PixelWave - FLUX.1-dev 03

PixelWave - FLUX.1-dev 03

humblemikey
|
7/15/2025
|
4:40:46 AM
| Discussion
A woman in a black dress reading a book on a dark red velvet sofa in a cozy, dimly lit library room with a lit fireplace, floral painting, and tall bookshelves.
Daytime photo of a Los Angeles suburban neighborhood showing a white SUV parked on the street in front of houses and palm trees.
Young woman in short jeans and white tanktop leaning against a 1950s red car on a colorful Cuban street in Havana with pastel tenement buildings.
A scenic aerial view of a Roman city set in a hilly Italian landscape with dry dirt paths in the foreground, mountains in the background, and the ocean to the left under a clear blue sky.

Recommended Parameters

samplers

Euler Normal, dpmpp 2m sgm uniform, dpmpp_2s_ancestral, euler, DPM++ SDE, 2M SDE Karras, DPM++ SDE Karras, DPM++ 2M

steps

4 - 40

cfg

2.5 - 7

resolution

1024x1024, 1536x1536

vae

ae.safetensors - unknown

Recommended Hires (High-Resolution) Parameters

upscale

1.5 - null

Tips

You can use more steps to improve finer details, but the output doesn't change much after 8 steps.

If you want a neater/cleaner output, try increasing the guidance scale (CFG).

Mentioning a style in the prompt can help the model generate better results.

Try adding the upscale latent by node, and scale the latent by 1.5 to generate higher resolution images.

Avoid using 'quality' terms like 4K, 8K, masterpiece, high def, high quality unless necessary; can cause images to look overcooked.

For photographic styles, avoid terms like 'vibrant, intense, bright, high contrast, neon, dramatic' if you want a natural look.

Training was done with kohya_ss/sd-scripts using pagedlion8bit optimizer.

Freezing 'time_in', 'vector_in' and modulation parameters stops 'de-distillation'.

Avoid training single blocks over 15; set training blocks in FLUX section.

Learning rate 5e-6 trains fast but stop after a few thousand steps to avoid block corruption.

Version Highlights

Fine tuned for 5 weeks on my 4090.

Creator Sponsors

Model also available at: RunDiffusion and Runware.ai

Huge thank you to RunDiffusion for sponsoring the compute that made training this model possible!

For API access, partner with Runware.ai

PixelWave FLUX.1-schnell 04 - Apache 2.0!

Safetensor Files: 💾BF16 💾FP8 💾bnb FP4

GGUF Files: 💾Q8_0 🤗Q6_K 💾Q4_K_M

Links to 🤗VAE 🤗T5xxl 🤗CLIP L

Model also available at: RunDiffusion and Runware.ai

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 RunDiffusion (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 Runware.ai

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 check them out!

Training

Training was done with kohya_ss/sd-scripts. You can find my fork of Kohya here , 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 pixelwave@rundiffusion.com. 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: 💾BF16 💾FP8 💾NF4

GGUF Files: 💾Q8_0 🤗Q6_K 💾Q4_K_M

Links to 🤗VAE 🤗T5xxl 🤗CLIP L

The 'diffusers' files are actually the Q8_0 and Q4_K_M GGUF versions. GGUF files also available on huggingface.

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. Trick I discovered to help with LoRAs.

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: 💾FP8 💾NF4

GGUF Files: go to huggingface

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: 💾BF16 💾FP8

GGUF Files: 💾Q8_0 🤗Q6_K 💾Q4_K_M

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.

Comfyui-GGUF Nodes

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

PAG Recommended⚡Recommend 1.5 Scale, with CFG 3. Link to workflow

🔗Link to Expanded Gallery 🖼️

⭐Link to prompting guide.⭐ 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: masslevel, blink, socalguitarist, klinter, wizard whitebeard.

Guide: Upscaling Prompts with LM Studio and Mikey Nodes

Guide: Add more details to your image using the skip step method

No need for the refiner model.

This model is not a mix of other models.

I also created Mikey Nodes which contains a lot of useful nodes. You can install it through comfy manager.

Contributor

humblemikey avatar

humblemikey

Previous
Artify´s Fantastic Flux Landscape Lora - artilands_v1.0
Next
Project0* - v4.0 Art_Realism_FP8
Use this model

Model Details

Model type

Checkpoint

Base model

Flux.1 D

Model version

FLUX.1-dev 03

Model hash

49b429b788

Creator

humblemikey's avatar
humblemikey

Discussion

Please log in to leave a comment.

Images by PixelWave - FLUX.1-dev 03

A woman in a black dress reading a book on a dark red velvet sofa in a cozy, dimly lit library room with a lit fireplace, floral painting, and tall bookshelves.
Daytime photo of a Los Angeles suburban neighborhood showing a white SUV parked on the street in front of houses and palm trees.
Young woman in short jeans and white tanktop leaning against a 1950s red car on a colorful Cuban street in Havana with pastel tenement buildings.
A scenic aerial view of a Roman city set in a hilly Italian landscape with dry dirt paths in the foreground, mountains in the background, and the ocean to the left under a clear blue sky.

anime Images

Anime couple lying in a field of flowers, a girl with dark brown hair peacefully sleeping on top of a blonde boy under a blue sky with clouds.
Digital art of Lust from FMA with long black hair, red eyes, a confident smile, wearing a black off-shoulder dress and elbow gloves, glowing with a blue aura.
Anime-style artwork of a blond-haired boy and orange-haired girl sharing an upside-down kiss while lying on grass, with vibrant colors and cinematic lighting.
Two anime girls with distinctive features, one with cat ears and heterochromia holding a cat perched on the shoulder of the other girl with dark hair and chopsticks, set against a gray background.
A towering female android glowing red with mechanical plating stands facing a man in a futuristic coat, illuminated by molten energy in a dark sci-fi scene.
Anime-style depiction of a muscular girl with brown hair in a ponytail sitting barefoot on a bench in a changing room, rendered with a fisheye lens effect.
Mature female with black kimono and white sash, blue eyes, braided ponytail, smiling with hand on hip outdoors under blue sky.
A detailed digital painting of an anime girl with blonde hair and striking blue eyes, illuminated by soft, dreamlike light in a CGI style.
Close-up portrait of Dio Brando with blonde hair and green headband, surrounded by sparkle effects under a bright blue sky.
A cyberpunk bar glowing with violet neon lights, filled with futuristic patrons wearing helmets and cybernetic gear, featuring holographic screens and a high-tech atmosphere.

base model Images

Photorealistic scene of undead characters including zombies and skeletons walking through a spooky cemetery illuminated by glowing jack-o'-lanterns under a dark, ominous sky.

digital art Images

Digital art of D.VA from Overwatch in a tight blue and white bodysuit, holding a handgun while kneeling, with a large close-up of her brown-eyed face in pink tones in the background.
Digital art of Lust from FMA with long black hair, red eyes, a confident smile, wearing a black off-shoulder dress and elbow gloves, glowing with a blue aura.
A digital painting of a tiny, distressed white kitten with chaotic fur and large, malevolent orange eyes, styled with black outlines and an Art Nouveau influence.
A hooded skeletal figure emerges from deep shadow with neon magenta and indigo colors, featuring painterly textures and glitch effects in a graphic novel style.
High-detail digital artwork of a cybernetic girl with blue hair and reflective robotic armor sitting on the ground with a sword behind her, shown from above.
Detailed digital illustration of a rhinoceros head with golden intricate patterns and a teal-green horn set against a dark brown background.
Shiny black male android squatting on a bed surrounded by intricate seafoam and silver swirling light trails made of engraved glass with billowing bright dust in the background.
Stylized digital portrait profile in black and gold with geometric abstraction, showing a woman holding a cigarette, detailed with chiaroscuro lighting and metallic textures.
Silhouette of a black cat with a neon pink collar and bow on its tail walking on a rainy street with reflective puddles under fluorescent lights at night.
A damaged robot girl with a transparent metal body, glowing red circular details on her chest and head, sharp angular blades protruding from her head in a dark, abandoned, futuristic environment.

photography Images

Full-body figure wearing an orange hoodie and black jogger pants with a bored face emoji mask, standing sideways in a minimalistic open space with blurred figures in motion around.
A futuristic robot girl with metallic skin and a blonde braid stands on the moon's surface, holding a glowing star with Earth and a large moon in the background under a starry sky.
Man in jean shorts and white tank top drinking a can of beer while pushing a lawn mower in a suburban yard with a white fence, American flag waving, and a golden retriever chasing a ball.
Highly detailed, realistic full body portrait of Pikachu with cinematic lighting, showing it in sharp focus on a dark background.
Beautiful blonde maid with blue eyes and short hair in a detailed white and black maid outfit, standing by a window overlooking Tokyo city.
Close up portrait of an extraordinary Blue Jay bird at dawn featuring detailed feathers, vibrant blue crest, and sharp eye with subtle motion blur.
Blonde woman with freckles and smile sitting outdoors wearing a maroon v-neck t-shirt and floral microskirt under natural lighting
Grandpa with gray hair and woman with high ponytail gray hair standing in a turquoise pool with a white dog and a kangaroo near pink walls
Dark and moody modern architecture featuring tiered concrete structures illuminated by a warm orange glow at night.
A mystical nighttime landscape featuring ancient stone ruins with steps, a glowing full moon setting behind distant mountains, a winding river valley, glowing stars, and a warm, magical sky illuminated by cinematic lighting.

traditional art Images

A determined girl wearing a white hooded cloak crouches in a narrow alley holding a sword illuminating the ground with dramatic sunlight, painted in a traditional style.
A confident female Roman guardswoman wearing intricately detailed bronze battle armor, standing in a historic city street setting during daylight.
Oriental ink wash painting depicting dramatic waterfalls cascading through rugged mountain cliffs with misty atmosphere and faint calligraphy
A calico cat sitting serenely among vibrant Japanese watercolor style flowers under a large red sun with elegant ink wash effects.
Close-up of a girl with shiny hair and clear skin, eyes closed.
Anime girl with long blonde hair in a traditional Japanese school uniform with a blue bow
A white tiger and a girl in traditional clothing on a misty mountain background. AI generated image using stable diffusion.
A dramatic scene with a lone samurai standing on water, facing a traditional Japanese pagoda in the distance under a stormy sky with swirling clouds and mist, generated using Stable Diffusion.
AI generated image using Stable Diffusion of a beautiful woman dressed in traditional Chinese attire with flowing hair, detailed ancient clothing, and a serene oriental background with a pagoda and foliage.