diff --git a/CHANGELOG.md b/CHANGELOG.md index a8d3138d4..e54e74de7 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,6 +1,6 @@ # Change Log for SD.Next -## Update for 2024-02-14 +## Update for 2024-02-15 - **improvements**: - **IP Adapter** major refactor @@ -69,6 +69,7 @@ - fix interrogate api endpoint - control fix resize causing runtime errors - control fix processor override image after processor change + - control fix display grid with batch - handle pipelines that return dict instead of object - fix inpaint mask only for diffusers - fix vae dtype mismatch, thanks @Disty0 diff --git a/TODO.md b/TODO.md index 0d6a59904..bb156fccb 100644 --- a/TODO.md +++ b/TODO.md @@ -4,9 +4,10 @@ Main ToDo list can be found at [GitHub projects](https://github.com/users/vladma ## Candidates for next release +- zluda +- stable cascade - control second pass: - onediff: -- regional prompting pipeline: - diffusers public callbacks - image2video: pia and vgen pipelines - video2video diff --git a/javascript/sdnext.css b/javascript/sdnext.css index 5eddb7007..9bffabcb8 100644 --- a/javascript/sdnext.css +++ b/javascript/sdnext.css @@ -77,7 +77,7 @@ button.custom-button{ border-radius: var(--button-large-radius); padding: var(-- #control_results { margin: 0; padding: 0; } #control_gallery { height: calc(100vw/3 + 60px); } #txt2img_gallery, #img2img_gallery { height: 50vh; } -#control-result { padding: 0.5em; } +#control-result { padding: 0 0.2em 0 0.2em; background: var(--input-background-fill); line-height: 2em; } #control-inputs { margin-top: 1em; } #txt2img_prompt_container, #img2img_prompt_container, #control_prompt_container { margin-right: var(--layout-gap) } #txt2img_footer, #img2img_footer, #control_footer { height: fit-content; display: none; } diff --git a/modules/control/run.py b/modules/control/run.py index 55db87747..c7f67ff6b 100644 --- a/modules/control/run.py +++ b/modules/control/run.py @@ -480,15 +480,16 @@ def control_run(units: List[unit.Unit], inputs, inits, mask, unit_type: str, is_ t3 += time.time() - t3 # outputs - if output is not None and len(output) > 0: - output_image = output[0] + output = output or [] + for i, output_image in enumerate(output): if output_image is not None: # resize after + is_grid = len(output) == p.batch_size * p.n_iter + 1 and i == 0 if selected_scale_tab_after == 1: width_after = int(output_image.width * scale_by_after) height_after = int(output_image.height * scale_by_after) - if resize_mode_after != 0 and resize_name_after != 'None': + if resize_mode_after != 0 and resize_name_after != 'None' and not is_grid: debug(f'Control resize: op=after image={output_image} width={width_after} height={height_after} mode={resize_mode_after} name={resize_name_after}') output_image = images.resize_image(resize_mode_after, output_image, width_after, height_after, resize_name_after) @@ -524,11 +525,9 @@ def control_run(units: List[unit.Unit], inputs, inits, mask, unit_type: str, is_ if len(output_images) == 0: output_images = None image_txt = 'images=None' - elif len(output_images) == 1: - output_images = output_images[0] - image_txt = f'| Images 1 | Size {output_images.width}x{output_images.height}' if output_image is not None else 'None' else: - image_txt = f'| Images {len(output_images)} | Size {output_images[0].width}x{output_images[0].height}' if output_image is not None else 'None' + image_str = [f'{image.width}x{image.height}' for image in output_images] + image_txt = f'| Images {len(output_images)} | Size {" ".join(image_str)}' if video_type != 'None' and isinstance(output_images, list): p.do_not_save_grid = True # pylint: disable=attribute-defined-outside-init diff --git a/modules/face/__init__.py b/modules/face/__init__.py index 1e601a97f..f26d841eb 100644 --- a/modules/face/__init__.py +++ b/modules/face/__init__.py @@ -44,6 +44,8 @@ class Script(scripts.Script): # return signature is array of gradio components def ui(self, _is_img2img): + with gr.Row(): + gr.HTML("  Face module
") with gr.Row(): mode = gr.Dropdown(label='Mode', choices=['None', 'FaceID', 'FaceSwap', 'InstantID', 'PhotoMaker'], value='None') with gr.Group(visible=False) as cfg_faceid: diff --git a/modules/ui_control.py b/modules/ui_control.py index 7adaf0815..ff6f883a1 100644 --- a/modules/ui_control.py +++ b/modules/ui_control.py @@ -76,6 +76,10 @@ def create_ui(_blocks: gr.Blocks=None): txt_prompt_img.change(fn=images.image_data, inputs=[txt_prompt_img], outputs=[prompt, txt_prompt_img]) with gr.Group(elem_id="control_interface", equal_height=False): + + with gr.Row(elem_id='control_status'): + result_txt = gr.HTML(elem_classes=['control-result'], elem_id='control-result') + with gr.Row(elem_id='control_settings'): with gr.Accordion(open=False, label="Input", elem_id="control_input", elem_classes=["small-accordion"]): @@ -126,9 +130,6 @@ def create_ui(_blocks: gr.Blocks=None): extra_networks_ui = ui_extra_networks.create_ui(extra_networks_ui, btn_extra, 'control', skip_indexing=shared.opts.extra_network_skip_indexing) timer.startup.record('ui-en') - with gr.Row(elem_id='control_status'): - result_txt = gr.HTML(elem_classes=['control-result'], elem_id='control-result') - with gr.Row(elem_id='control-inputs'): with gr.Column(scale=9, elem_id='control-input-column', visible=True) as _column_input: gr.HTML('Control input

') @@ -173,7 +174,7 @@ def create_ui(_blocks: gr.Blocks=None): with gr.Tab('Preview', id='preview-image') as tab_image: preview_process = gr.Image(label="Preview", show_label=False, type="pil", source="upload", interactive=False, height=gr_height, visible=True, elem_id='control_preview', elem_classes=['control-image']) - with gr.Accordion('Control elements'): + with gr.Accordion('Control elements', open=False): with gr.Tabs(elem_id='control-tabs') as _tabs_control_type: with gr.Tab('ControlNet') as _tab_controlnet: diff --git a/scripts/blipdiffusion.py b/scripts/blipdiffusion.py index 50ae01021..bff6dd315 100644 --- a/scripts/blipdiffusion.py +++ b/scripts/blipdiffusion.py @@ -13,6 +13,8 @@ class Script(scripts.Script): return is_img2img if shared.backend == shared.Backend.DIFFUSERS else False def ui(self, _is_img2img): + with gr.Row(): + gr.HTML('  BLIP Diffusion
') with gr.Row(): source_subject = gr.Textbox(value='', label='Source subject') with gr.Row(): diff --git a/scripts/img2imgalt.py b/scripts/img2imgalt.py deleted file mode 100644 index 1fe75e86a..000000000 --- a/scripts/img2imgalt.py +++ /dev/null @@ -1,176 +0,0 @@ -from collections import namedtuple -import numpy as np -from tqdm import trange -import torch -import k_diffusion as K -import gradio as gr -import modules.scripts as scripts -from modules import processing, shared, sd_samplers, sd_samplers_common - - -def find_noise_for_image(p, cond, uncond, cfg_scale, steps): - x = p.init_latent - s_in = x.new_ones([x.shape[0]]) - if shared.sd_model.parameterization == "v": - dnw = K.external.CompVisVDenoiser(shared.sd_model) - skip = 1 - else: - dnw = K.external.CompVisDenoiser(shared.sd_model) - skip = 0 - sigmas = dnw.get_sigmas(steps).flip(0) - shared.state.sampling_steps = steps - - for i in trange(1, len(sigmas)): - shared.state.sampling_step += 1 - x_in = torch.cat([x] * 2) - sigma_in = torch.cat([sigmas[i] * s_in] * 2) - cond_in = torch.cat([uncond, cond]) - image_conditioning = torch.cat([p.image_conditioning] * 2) - cond_in = {"c_concat": [image_conditioning], "c_crossattn": [cond_in]} - c_out, c_in = [K.utils.append_dims(k, x_in.ndim) for k in dnw.get_scalings(sigma_in)[skip:]] - t = dnw.sigma_to_t(sigma_in) - eps = shared.sd_model.apply_model(x_in * c_in, t, cond=cond_in) - denoised_uncond, denoised_cond = (x_in + eps * c_out).chunk(2) - denoised = denoised_uncond + (denoised_cond - denoised_uncond) * cfg_scale - d = (x - denoised) / sigmas[i] - dt = sigmas[i] - sigmas[i - 1] - x = x + d * dt - sd_samplers_common.store_latent(x) - # This shouldn't be necessary, but solved some VRAM issues - del x_in, sigma_in, cond_in, c_out, c_in, t, - del eps, denoised_uncond, denoised_cond, denoised, d, dt - - shared.state.nextjob() - return x / x.std() - - -Cached = namedtuple("Cached", ["noise", "cfg_scale", "steps", "latent", "original_prompt", "original_negative_prompt", "sigma_adjustment"]) - - -# Based on changes suggested by briansemrau in https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/736 -def find_noise_for_image_sigma_adjustment(p, cond, uncond, cfg_scale, steps): - x = p.init_latent - s_in = x.new_ones([x.shape[0]]) - if shared.sd_model.parameterization == "v": - dnw = K.external.CompVisVDenoiser(shared.sd_model) - skip = 1 - else: - dnw = K.external.CompVisDenoiser(shared.sd_model) - skip = 0 - sigmas = dnw.get_sigmas(steps).flip(0) - - shared.state.sampling_steps = steps - - for i in trange(1, len(sigmas)): - shared.state.sampling_step += 1 - x_in = torch.cat([x] * 2) - sigma_in = torch.cat([sigmas[i - 1] * s_in] * 2) - cond_in = torch.cat([uncond, cond]) - image_conditioning = torch.cat([p.image_conditioning] * 2) - cond_in = {"c_concat": [image_conditioning], "c_crossattn": [cond_in]} - c_out, c_in = [K.utils.append_dims(k, x_in.ndim) for k in dnw.get_scalings(sigma_in)[skip:]] - if i == 1: - t = dnw.sigma_to_t(torch.cat([sigmas[i] * s_in] * 2)) - else: - t = dnw.sigma_to_t(sigma_in) - eps = shared.sd_model.apply_model(x_in * c_in, t, cond=cond_in) - denoised_uncond, denoised_cond = (x_in + eps * c_out).chunk(2) - denoised = denoised_uncond + (denoised_cond - denoised_uncond) * cfg_scale - if i == 1: - d = (x - denoised) / (2 * sigmas[i]) - else: - d = (x - denoised) / sigmas[i - 1] - dt = sigmas[i] - sigmas[i - 1] - x = x + d * dt - sd_samplers_common.store_latent(x) - # This shouldn't be necessary, but solved some VRAM issues - del x_in, sigma_in, cond_in, c_out, c_in, t, - del eps, denoised_uncond, denoised_cond, denoised, d, dt - - shared.state.nextjob() - return x / sigmas[-1] - - -class Script(scripts.Script): - def __init__(self): - self.cache = None - - def title(self): - return "Alternative" - - def show(self, is_img2img): - return is_img2img - - def ui(self, is_img2img): - info = gr.Markdown(''' - * `CFG Scale` should be 2 or lower. - ''') - override_sampler = gr.Checkbox(label="Override `Sampling method` to Euler", value=True, elem_id=self.elem_id("override_sampler")) - override_prompt = gr.Checkbox(label="Override `prompt` to the same value as `original prompt`", value=True, elem_id=self.elem_id("override_prompt")) - original_prompt = gr.Textbox(label="Original prompt", lines=1, elem_id=self.elem_id("original_prompt")) - original_negative_prompt = gr.Textbox(label="Original negative prompt", lines=1, elem_id=self.elem_id("original_negative_prompt")) - override_steps = gr.Checkbox(label="Override `Sampling Steps` to the same value as `Decode steps`?", value=True, elem_id=self.elem_id("override_steps")) - st = gr.Slider(label="Decode steps", minimum=1, maximum=150, step=1, value=50, elem_id=self.elem_id("st")) - override_strength = gr.Checkbox(label="Override `Denoising strength` to 1?", value=True, elem_id=self.elem_id("override_strength")) - cfg = gr.Slider(label="Decode CFG scale", minimum=0.0, maximum=15.0, step=0.1, value=1.0, elem_id=self.elem_id("cfg")) - randomness = gr.Slider(label="Randomness", minimum=0.0, maximum=1.0, step=0.01, value=0.0, elem_id=self.elem_id("randomness")) - sigma_adjustment = gr.Checkbox(label="Sigma adjustment for finding noise for image", value=False, elem_id=self.elem_id("sigma_adjustment")) - - return [ - info, - override_sampler, - override_prompt, original_prompt, original_negative_prompt, - override_steps, st, - override_strength, - cfg, randomness, sigma_adjustment, - ] - - def run(self, p, _, override_sampler, override_prompt, original_prompt, original_negative_prompt, override_steps, st, override_strength, cfg, randomness, sigma_adjustment): # pylint: disable=arguments-differ - # Override - if override_sampler: - p.sampler_name = "Euler" - if override_prompt: - p.prompt = original_prompt - p.negative_prompt = original_negative_prompt - if override_steps: - p.steps = st - if override_strength: - p.denoising_strength = 1.0 - - def sample_extra(conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength, prompts): # pylint: disable=unused-argument - lat = (p.init_latent.cpu().numpy() * 10).astype(int) - same_params = self.cache is not None and self.cache.cfg_scale == cfg and self.cache.steps == st \ - and self.cache.original_prompt == original_prompt \ - and self.cache.original_negative_prompt == original_negative_prompt \ - and self.cache.sigma_adjustment == sigma_adjustment - same_everything = same_params and self.cache.latent.shape == lat.shape and np.abs(self.cache.latent-lat).sum() < 100 - if same_everything: - rec_noise = self.cache.noise - else: - shared.state.job_count += 1 - cond = p.sd_model.get_learned_conditioning(p.batch_size * [original_prompt]) - uncond = p.sd_model.get_learned_conditioning(p.batch_size * [original_negative_prompt]) - if sigma_adjustment: - rec_noise = find_noise_for_image_sigma_adjustment(p, cond, uncond, cfg, st) - else: - rec_noise = find_noise_for_image(p, cond, uncond, cfg, st) - self.cache = Cached(rec_noise, cfg, st, lat, original_prompt, original_negative_prompt, sigma_adjustment) - - rand_noise = processing.create_random_tensors(p.init_latent.shape[1:], seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength, seed_resize_from_h=p.seed_resize_from_h, seed_resize_from_w=p.seed_resize_from_w, p=p) - combined_noise = ((1 - randomness) * rec_noise + randomness * rand_noise) / ((randomness**2 + (1-randomness)**2) ** 0.5) - sampler = sd_samplers.create_sampler(p.sampler_name, p.sd_model) - sigmas = sampler.model_wrap.get_sigmas(p.steps) - noise_dt = combined_noise - (p.init_latent / sigmas[0]) - p.seed = p.seed + 1 - return sampler.sample_img2img(p, p.init_latent, noise_dt, conditioning, unconditional_conditioning, image_conditioning=p.image_conditioning) - - p.sample = sample_extra - p.extra_generation_params["Decode prompt"] = original_prompt - p.extra_generation_params["Decode negative prompt"] = original_negative_prompt - p.extra_generation_params["Decode CFG scale"] = cfg - p.extra_generation_params["Decode steps"] = st - p.extra_generation_params["Randomness"] = randomness - p.extra_generation_params["Sigma Adjustment"] = sigma_adjustment - processed = processing.process_images(p) - - return processed diff --git a/scripts/loopback.py b/scripts/loopback.py index cc4b5a6ee..af4844b8e 100644 --- a/scripts/loopback.py +++ b/scripts/loopback.py @@ -15,10 +15,14 @@ class Script(scripts.Script): return is_img2img def ui(self, is_img2img): - loops = gr.Slider(minimum=1, maximum=32, step=1, label='Loops', value=4, elem_id=self.elem_id("loops")) - final_denoising_strength = gr.Slider(minimum=0, maximum=1, step=0.01, label='Final denoising strength', value=0.5, elem_id=self.elem_id("final_denoising_strength")) - denoising_curve = gr.Dropdown(label="Denoising strength curve", choices=["Aggressive", "Linear", "Lazy"], value="Linear") - append_interrogation = gr.Dropdown(label="Append interrogated prompt at each iteration", choices=["None", "CLIP", "DeepBooru"], value="None") + with gr.Row(): + gr.HTML("  Loopback
") + with gr.Row(): + loops = gr.Slider(minimum=1, maximum=32, step=1, label='Loops', value=4, elem_id=self.elem_id("loops")) + final_denoising_strength = gr.Slider(minimum=0, maximum=1, step=0.01, label='Final denoising strength', value=0.5, elem_id=self.elem_id("final_denoising_strength")) + with gr.Row(): + denoising_curve = gr.Dropdown(label="Denoising strength curve", choices=["Aggressive", "Linear", "Lazy"], value="Linear") + append_interrogation = gr.Dropdown(label="Append interrogated prompt at each iteration", choices=["None", "CLIP", "DeepBooru"], value="None") return [loops, final_denoising_strength, denoising_curve, append_interrogation] diff --git a/scripts/outpainting_mk_2.py b/scripts/outpainting_mk_2.py index d9ec0c02b..383587cc6 100644 --- a/scripts/outpainting_mk_2.py +++ b/scripts/outpainting_mk_2.py @@ -109,12 +109,15 @@ class Script(scripts.Script): def ui(self, is_img2img): if not is_img2img: return None - info = gr.HTML("

Recommended settings: Sampling Steps: 80-100, Sampler: Euler a, Denoising strength: 0.8

") - pixels = gr.Slider(label="Pixels to expand", minimum=8, maximum=256, step=8, value=128, elem_id=self.elem_id("pixels")) - mask_blur = gr.Slider(label='Mask blur', minimum=0, maximum=64, step=1, value=8, elem_id=self.elem_id("mask_blur")) + with gr.Row(): + info = gr.HTML("  Outpainting
") + with gr.Row(): + pixels = gr.Slider(label="Pixels to expand", minimum=8, maximum=256, step=8, value=128, elem_id=self.elem_id("pixels")) + mask_blur = gr.Slider(label='Mask blur', minimum=0, maximum=64, step=1, value=8, elem_id=self.elem_id("mask_blur")) direction = gr.CheckboxGroup(label="Outpainting direction", choices=['left', 'right', 'up', 'down'], value=['left', 'right', 'up', 'down'], elem_id=self.elem_id("direction")) - noise_q = gr.Slider(label="Fall-off exponent (lower=higher detail)", minimum=0.0, maximum=4.0, step=0.01, value=1.0, elem_id=self.elem_id("noise_q")) - color_variation = gr.Slider(label="Color variation", minimum=0.0, maximum=1.0, step=0.01, value=0.05, elem_id=self.elem_id("color_variation")) + with gr.Row(): + noise_q = gr.Slider(label="Fall-off exponent (lower=higher detail)", minimum=0.0, maximum=4.0, step=0.01, value=1.0, elem_id=self.elem_id("noise_q")) + color_variation = gr.Slider(label="Color variation", minimum=0.0, maximum=1.0, step=0.01, value=0.05, elem_id=self.elem_id("color_variation")) return [info, pixels, mask_blur, direction, noise_q, color_variation] def run(self, p, _, pixels, mask_blur, direction, noise_q, color_variation): # pylint: disable=arguments-differ diff --git a/scripts/poor_mans_outpainting.py b/scripts/poor_mans_outpainting.py index 3f6cbf335..690dd1911 100644 --- a/scripts/poor_mans_outpainting.py +++ b/scripts/poor_mans_outpainting.py @@ -17,14 +17,17 @@ class Script(scripts.Script): def ui(self, is_img2img): if not is_img2img: return None - - pixels = gr.Slider(label="Pixels to expand", minimum=8, maximum=256, step=8, value=128, elem_id=self.elem_id("pixels")) - mask_blur = gr.Slider(label='Mask blur', minimum=0, maximum=64, step=1, value=4, elem_id=self.elem_id("mask_blur")) - inpainting_fill = gr.Radio(label='Masked content', choices=['fill', 'original', 'latent noise', 'latent nothing'], value='fill', type="index", elem_id=self.elem_id("inpainting_fill")) - direction = gr.CheckboxGroup(label="Outpainting direction", choices=['left', 'right', 'up', 'down'], value=['left', 'right', 'up', 'down'], elem_id=self.elem_id("direction")) + with gr.Row(): + gr.HTML("  Outpainting alternative
") + with gr.Row(): + pixels = gr.Slider(label="Pixels to expand", minimum=8, maximum=256, step=8, value=128, elem_id=self.elem_id("pixels")) + mask_blur = gr.Slider(label='Mask blur', minimum=0, maximum=64, step=1, value=4, elem_id=self.elem_id("mask_blur")) + with gr.Row(): + inpainting_fill = gr.Radio(label='Masked content', choices=['fill', 'original', 'latent noise', 'latent nothing'], value='fill', type="index", elem_id=self.elem_id("inpainting_fill")) + direction = gr.CheckboxGroup(label="Outpainting direction", choices=['left', 'right', 'up', 'down'], value=['left', 'right', 'up', 'down'], elem_id=self.elem_id("direction")) return [pixels, mask_blur, inpainting_fill, direction] - def run(self, p, pixels, mask_blur, inpainting_fill, direction): + def run(self, p, pixels, mask_blur, inpainting_fill, direction): # pylint: disable=arguments-differ initial_seed = None initial_info = None p.mask_blur = mask_blur * 2 diff --git a/scripts/postprocessing_video.py b/scripts/postprocessing_video.py index 0fbe5984f..4011f3b5b 100644 --- a/scripts/postprocessing_video.py +++ b/scripts/postprocessing_video.py @@ -17,6 +17,8 @@ class ScriptPostprocessingUpscale(scripts_postprocessing.ScriptPostprocessing): gr.update(visible=video_type == 'MP4'), ] + with gr.Row(): + gr.HTML("  Video
") with gr.Row(): video_type = gr.Dropdown(label='Video file', choices=['None', 'GIF', 'PNG', 'MP4'], value='None') duration = gr.Slider(label='Duration', minimum=0.25, maximum=10, step=0.25, value=2, visible=False) diff --git a/scripts/sd_upscale.py b/scripts/sd_upscale.py index 8e22febbe..0799e2c79 100644 --- a/scripts/sd_upscale.py +++ b/scripts/sd_upscale.py @@ -15,14 +15,17 @@ class Script(scripts.Script): return is_img2img def ui(self, is_img2img): - info = gr.HTML("

Will upscale the image by the selected scale factor; use width and height sliders to set tile size

") - overlap = gr.Slider(minimum=0, maximum=256, step=16, label='Tile overlap', value=64, elem_id=self.elem_id("overlap")) - scale_factor = gr.Slider(minimum=1.0, maximum=4.0, step=0.05, label='Scale Factor', value=2.0, elem_id=self.elem_id("scale_factor")) - upscaler_index = gr.Dropdown(label='Upscaler', choices=[x.name for x in shared.sd_upscalers], value=shared.sd_upscalers[0].name, type="index", elem_id=self.elem_id("upscaler_index")) + with gr.Row(): + info = gr.HTML("  SD Upscale
") + with gr.Row(): + overlap = gr.Slider(minimum=0, maximum=256, step=16, label='Tile overlap', value=64, elem_id=self.elem_id("overlap")) + scale_factor = gr.Slider(minimum=1.0, maximum=4.0, step=0.05, label='Scale Factor', value=2.0, elem_id=self.elem_id("scale_factor")) + with gr.Row(): + upscaler_index = gr.Dropdown(label='Upscaler', choices=[x.name for x in shared.sd_upscalers], value=shared.sd_upscalers[0].name, type="index", elem_id=self.elem_id("upscaler_index")) return [info, overlap, upscaler_index, scale_factor] - def run(self, p, _, overlap, upscaler_index, scale_factor): + def run(self, p, _, overlap, upscaler_index, scale_factor): # pylint: disable=arguments-differ if isinstance(upscaler_index, str): upscaler_index = [x.name.lower() for x in shared.sd_upscalers].index(upscaler_index.lower()) processing.fix_seed(p) diff --git a/scripts/stablevideodiffusion.py b/scripts/stablevideodiffusion.py index 3e20c4373..80a20cf45 100644 --- a/scripts/stablevideodiffusion.py +++ b/scripts/stablevideodiffusion.py @@ -24,6 +24,8 @@ class Script(scripts.Script): gr.update(visible=video_type == 'MP4'), ] + with gr.Row(): + gr.HTML('  Stable Video Diffusion
') with gr.Row(): num_frames = gr.Slider(label='Frames', minimum=1, maximum=50, step=1, value=14) min_guidance_scale = gr.Slider(label='Min guidance', minimum=0.0, maximum=10.0, step=0.1, value=1.0)